{"object":"viablelab.api_metadata","version":"2026-10-17-openai-retirements","base_url":"https://api.viablelab.org","agent_guide_url":"https://developers.viablelab.org/agents/viablelab-api.md","default_model":"gpt-6-luna","default_models_by_mode":{"chat":"gpt-6-luna","embedding":"nomic-embed-text-v1.5","image_generation":"flux.2-klein","audio_transcription":"whisper-large-v3","audio_speech":"kokoro"},"modes":{"chat":[{"id":"gpt-6-astra","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Astra model for the hardest end-to-end reasoning, coding, research, computer-use, and document workflows.","owned_by":"openai","intelligence":"Highest","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":10,"output_per_million":50,"cached_input_per_million":1,"cache_write_per_million":12.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":20,"long_context_cached_input_per_million":2,"long_context_cache_write_per_million":25,"long_context_output_per_million":75,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $10 input, $1 cached input, $12.50 cache writes, $50 output. Above 272K input: $20 input, $2 cached input, $25 cache writes, $75 output."}},{"id":"gpt-6.1-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6.1 Sol reasoning model for complex coding and professional work, with near-Astra performance at lower cost. Chat Completions supports streaming but not tool calling; reasoning effort ranges from low to max.","owned_by":"openai","intelligence":"Very High","speed":"Not listed","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":10,"cached_input_per_million":0.1,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.2,"long_context_cache_write_per_million":5,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2 input, $0.10 cached input, $2.50 cache writes, $10 output. Above 272K input: $4 input, $0.20 cached input, $5 cache writes, $15 output."}},{"id":"gpt-6-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Sol model for complex coding and agentic workflows. Chat Completions function calling requires reasoning_effort: none.","owned_by":"openai","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":10,"cached_input_per_million":0.2,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":5,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2 input, $0.2 cached input, $2.5 cache writes, $10 output. Above 272K input: $4 input, $0.4 cached input, $5 cache writes, $15 output."}},{"id":"gpt-6-luna","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Luna model for focused, cost-sensitive, high-volume tasks. Chat Completions function calling requires reasoning_effort: none.","owned_by":"openai","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.1,"output_per_million":0.5,"cached_input_per_million":0.01,"cache_write_per_million":0.125,"long_context_threshold_tokens":272000,"long_context_input_per_million":0.2,"long_context_cached_input_per_million":0.02,"long_context_cache_write_per_million":0.25,"long_context_output_per_million":0.75,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $0.1 input, $0.01 cached input, $0.125 cache writes, $0.5 output. Above 272K input: $0.2 input, $0.02 cached input, $0.25 cache writes, $0.75 output."}},{"id":"gpt-5.6-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Sol frontier model for complex professional, coding, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Highest","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":4,"output_per_million":20,"cached_input_per_million":0.4,"cache_write_per_million":5,"long_context_threshold_tokens":272000,"long_context_input_per_million":8,"long_context_cached_input_per_million":0.8,"long_context_cache_write_per_million":10,"long_context_output_per_million":30,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $4 input, $0.40 cached input, $5 cache writes, $20 output. Above 272K input: $8 input, $0.80 cached input, $10 cache writes, $30 output."}},{"id":"gpt-5.6-terra","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Terra model for workloads that balance intelligence, speed, and cost.","owned_by":"openai","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":12,"cached_input_per_million":0.2,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":5,"long_context_output_per_million":18,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $2 input, $0.20 cached input, $2.50 cache writes, $12 output. Above 272K input: $4 input, $0.40 cached input, $5 cache writes, $18 output."}},{"id":"gpt-5.6-luna","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Luna model optimized for fast, cost-sensitive, high-volume workloads.","owned_by":"openai","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.2,"output_per_million":1.2,"cached_input_per_million":0.02,"cache_write_per_million":0.25,"long_context_threshold_tokens":272000,"long_context_input_per_million":0.4,"long_context_cached_input_per_million":0.04,"long_context_cache_write_per_million":0.5,"long_context_output_per_million":1.8,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $0.20 input, $0.02 cached input, $0.25 cache writes, $1.20 output. Above 272K input: $0.40 input, $0.04 cached input, $0.50 cache writes, $1.80 output."}},{"id":"gpt-5.5","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.5 model configuration for advanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":5,"output_per_million":30,"cached_input_per_million":0.5,"cache_write_per_million":null,"long_context_threshold_tokens":272000,"long_context_input_per_million":10,"long_context_cached_input_per_million":1,"long_context_cache_write_per_million":null,"long_context_output_per_million":45,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $5 input, $0.50 cached input, $30 output. Above 272K input: $10 input, $1 cached input, $45 output."}},{"id":"gpt-5.4","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.4 model configuration for advanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2.5,"output_per_million":15,"cached_input_per_million":0.25,"cache_write_per_million":null,"long_context_threshold_tokens":272000,"long_context_input_per_million":5,"long_context_cached_input_per_million":0.5,"long_context_cache_write_per_million":null,"long_context_output_per_million":22.5,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2.50 input, $0.25 cached input, $15 output. Above 272K input: $5 input, $0.50 cached input, $22.50 output."}},{"id":"gpt-5.4-mini","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.4 mini model configuration for balanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"High","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":400000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":4.5,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard public pricing, per 1M tokens: $0.75 input, $0.075 cached input, $4.50 output."}},{"id":"gpt-4.1","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4.1. Flagship OpenAI model for complex tasks. It is well suited for problem solving across domains. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1047576,"max_output_tokens":32768,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":2,"output_per_million":8,"cached_input_per_million":0.5,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-4.1-mini","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4.1 mini, balancing intelligence, speed, and cost for many use cases. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"High","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1047576,"max_output_tokens":32768,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":0.4,"output_per_million":1.6,"cached_input_per_million":0.1,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-4o","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4o. Fast, intelligent, flexible GPT model. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"High","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":16384,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":2.5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gemini-3.8-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Google's most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.","owned_by":"google","intelligence":"Highest","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.8 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.7-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"High-speed Gemini Flash model for everyday coding, agentic tool use, and reliable multi-step execution.","owned_by":"google","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.7 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.6-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Previous-generation Gemini Flash model balancing speed and multimodal capability for general agentic and everyday work.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.6 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.5-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Earlier Gemini Flash model for routine, high-throughput multimodal work.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":1.5,"output_per_million":9,"cached_input_per_million":0.15,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.5 Flash standard paid-tier pricing: $1.50/M input, $0.15/M cached input, and $9/M output. Explicit cache storage is separately listed at $1/M tokens per hour."}},{"id":"gemini-3.5-flash-lite","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Cost-efficient Gemini model for high-volume agentic tasks, translation, document parsing, and simple data processing.","owned_by":"google","intelligence":"Average","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.3,"output_per_million":2.5,"cached_input_per_million":0.03,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.5 Flash-Lite standard paid-tier pricing: $0.30/M input, $0.03/M cached input, and $2.50/M output. Explicit cache storage is separately listed at $1/M tokens per hour."}},{"id":"gemini-3.1-pro-preview","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Preview Gemini Pro model for advanced multimodal reasoning, software engineering, and precise multi-step agentic workflows.","owned_by":"google","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":12,"cached_input_per_million":0.2,"cache_write_per_million":null,"long_context_threshold_tokens":200000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":null,"long_context_output_per_million":18,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.1 Pro Preview standard paid-tier pricing. Up to 200K input tokens: $2/M input, $0.20/M cached input, and $12/M output. Above 200K: $4/M input, $0.40/M cached input, and $18/M output. Explicit cache storage is billed separately."}},{"id":"gemini-2.5-pro","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Gemini thinking model for complex coding, mathematics, STEM, large datasets, codebases, and documents.","owned_by":"google","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":1.25,"output_per_million":10,"cached_input_per_million":0.125,"cache_write_per_million":null,"long_context_threshold_tokens":200000,"long_context_input_per_million":2.5,"long_context_cached_input_per_million":0.25,"long_context_cache_write_per_million":null,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Pro standard paid-tier pricing. Up to 200K input tokens: $1.25/M input, $0.125/M cached input, and $10/M output. Above 200K: $2.50/M input, $0.25/M cached input, and $15/M output. Explicit cache storage is billed separately."}},{"id":"gemini-2.5-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to Gemini 2.5 Flash. Optimized for speed and cost-effective multimodal generation.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["none","minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.3,"output_per_million":2.5,"cached_input_per_million":0.03,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Flash standard paid-tier text/image/video pricing: $0.30/M input, $0.03/M cached input, and $2.50/M output. Audio input and explicit cache storage are billed separately."}},{"id":"gemini-2.5-flash-lite","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Cost-efficient Gemini 2.5 model for high-volume classification, simple extraction, and low-latency multimodal work.","owned_by":"google","intelligence":"Average","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["none","minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.1,"output_per_million":0.4,"cached_input_per_million":0.01,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Flash-Lite standard paid-tier text/image/video pricing: $0.10/M input, $0.01/M cached input, and $0.40/M output. Audio input and explicit cache storage are billed separately."}},{"id":"gpt-oss-120b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight 120B model for cost-efficient text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.06,"output_per_million":0.15,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-oss-20b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight 20B model for low-cost text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"Average","speed":"Fast","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.03,"output_per_million":0.07,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gemma-4-31b-it","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight Google Gemma 4 31B instruction model for image understanding, long-context reasoning, coding, and text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text","image"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.12,"output_per_million":0.36,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Navigator registered pricing, per 1M tokens: $0.12 input, $0.36 output."}},{"id":"nemotron-3-super-120b-a12b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight NVIDIA Nemotron 3 Super model for agentic reasoning, coding, planning, and long-context text workflows through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":262144,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.06,"output_per_million":0.24,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Navigator registered pricing, per 1M tokens: $0.06 input, $0.24 output."}},{"id":"mistral-small-3.1","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Mistral Small 3.1 model for cost-efficient open-weight text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"Average","speed":"Fast","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.2,"output_per_million":0.6,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Registered pricing, per 1M tokens: $0.20 input, $0.60 output."}},{"id":"llama-3.3-70b-instruct","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Llama 3.3 70B Instruct model for strong open-weight text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.4,"output_per_million":0.4,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Registered pricing, per 1M tokens: $0.40 input, $0.40 output."}}],"embedding":[{"id":"nomic-embed-text-v1.5","object":"model","mode":"embedding","endpoint":"/v1/embeddings","description":"Text embedding model for semantic search, clustering, retrieval, and ranking workflows.","owned_by":"viable-lab","intelligence":"Embedding","speed":"Fast","input_modalities":["text"],"output_modalities":["embedding"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":true,"image_generation":false},"pricing":{"input_per_million":0.005,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"docs_inferred","note":"Derived from provider docs: 250,000 pages per dollar at approximately 800 tokens per page."}}],"image_generation":[{"id":"gpt-image-2.5-sunburst","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Precise image generation with strong editing fidelity.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high","xhigh","max"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-2.5-flare","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Fast, high-quality everyday image generation.","owned_by":"openai","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high","xhigh","max"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-2","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"GPT Image generation with flexible resolutions.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-1.5","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Earlier GPT Image generation model.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":32,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-1-mini","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Cost-efficient GPT Image generation.","owned_by":"openai","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":2,"output_per_million":null,"cached_input_per_million":0.2,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":2.5,"cached_image_input_per_million":0.25,"image_output_per_million":8,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"chatgpt-image-latest","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Moving alias for the image model used in ChatGPT.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":32,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gemini-3.1-flash-image","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Nano Banana 2: fast image generation at 0.5K, 1K, 2K, or 4K.","owned_by":"google","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":1,"size_values":["0.5K","1K","2K","4K","512x512","1024x1024","2048x2048","4096x4096","1024x1536","1536x1024"],"aspect_ratio_values":["1:1","3:2","2:3","3:4","4:3","4:5","5:4","9:16","16:9","21:9","1:4","4:1","1:8","8:1"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":0.5,"output_per_million":3,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":0.5,"cached_image_input_per_million":null,"image_output_per_million":60,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini Standard paid-tier rates. At 747/1120/1680/2520 image tokens, output alone costs $0.04482/$0.0672/$0.1008/$0.1512. Input and text/thinking tokens are additional. No free API tier. Batch, search grounding, editing, and streaming are not exposed by this endpoint."}},{"id":"gemini-3.1-flash-lite-image","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Nano Banana 2 Lite: low-latency, cost-efficient 1K image generation.","owned_by":"google","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":1,"size_values":["1K","1024x1024","1024x1536","1536x1024"],"aspect_ratio_values":["1:1","3:2","2:3","3:4","4:3","4:5","5:4","9:16","16:9","21:9"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":0.25,"output_per_million":1.5,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":0.25,"cached_image_input_per_million":null,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini Standard paid-tier rates. At 1120 image tokens, 1K output alone costs $0.0336. Input and text/thinking tokens are additional. No free API tier. Batch, search grounding, editing, and streaming are not exposed by this endpoint."}},{"id":"flux.2-klein","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Image generation model for prompt-to-image workflows.","owned_by":"viable-lab","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":0.014,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"starts_at","note":"Provider docs list pricing from $0.014 per image; final cost varies by resolution/model variant."}}],"audio_transcription":[{"id":"whisper-large-v3","object":"model","mode":"audio_transcription","endpoint":"/v1/audio/transcriptions","description":"Speech-to-text model for audio transcription.","owned_by":"viable-lab","intelligence":"Audio","speed":"Medium","input_modalities":["audio","file"],"output_modalities":["text"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":false,"images":false,"files":true,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.006,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Provider docs list $0.006 per minute of input audio."}},{"id":"gpt-transcribe","object":"model","mode":"audio_transcription","endpoint":"/v1/audio/transcriptions","description":"OpenAI file transcription with prompt, keyword and multiple language hints. This gateway returns non-streaming JSON.","owned_by":"openai","intelligence":"Audio","speed":"Medium","input_modalities":["audio","file"],"output_modalities":["text"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":false,"images":false,"files":true,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.0045,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI lists an estimated $0.0045 per minute of input audio. Cost is unknown when duration is unavailable."}}],"audio_speech":[{"id":"kokoro","object":"model","mode":"audio_speech","endpoint":"/v1/audio/speech","description":"Text-to-speech model for generated speech audio.","owned_by":"viable-lab","intelligence":"Audio","speed":"Fast","input_modalities":["text"],"output_modalities":["audio"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"voice":true,"voice_values":["af_heart","af_alloy","af_aoede","af_bella","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","pf_dora","pm_alex","pm_santa"],"response_format":true,"response_format_values":["mp3","opus","flac","wav","pcm"],"speed":true,"instructions":false},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"default_voice":"af_heart","pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.006,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Provider docs list $0.006 per minute of generated audio."}}]},"models":[{"id":"viable-1","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Quality-focused model for complex reasoning, careful evaluation, and detailed writing.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":12,"cached_input_per_million":0.2,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":5,"long_context_output_per_million":18,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"VIABLE Lab token rates; any long-context tiers are listed separately."}},{"id":"viable-2","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Balanced model for everyday conversations, multimodal tasks, and general-purpose work.","owned_by":"viable-lab","intelligence":"Balanced","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["none","minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.3,"output_per_million":2.5,"cached_input_per_million":0.03,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"VIABLE Lab token rates; any long-context tiers are listed separately."}},{"id":"viable-3","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Speed-focused model for quick answers, concise summaries, and routine tasks. Runs without reasoning unless reasoning_effort is set.","owned_by":"viable-lab","intelligence":"Standard","speed":"Very fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.1,"output_per_million":0.5,"cached_input_per_million":0.01,"cache_write_per_million":0.125,"long_context_threshold_tokens":272000,"long_context_input_per_million":0.2,"long_context_cached_input_per_million":0.02,"long_context_cache_write_per_million":0.25,"long_context_output_per_million":0.75,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"VIABLE Lab token rates; any long-context tiers are listed separately."}},{"id":"gpt-6-astra","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Astra model for the hardest end-to-end reasoning, coding, research, computer-use, and document workflows.","owned_by":"openai","intelligence":"Highest","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":10,"output_per_million":50,"cached_input_per_million":1,"cache_write_per_million":12.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":20,"long_context_cached_input_per_million":2,"long_context_cache_write_per_million":25,"long_context_output_per_million":75,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $10 input, $1 cached input, $12.50 cache writes, $50 output. Above 272K input: $20 input, $2 cached input, $25 cache writes, $75 output."}},{"id":"gpt-6.1-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6.1 Sol reasoning model for complex coding and professional work, with near-Astra performance at lower cost. Chat Completions supports streaming but not tool calling; reasoning effort ranges from low to max.","owned_by":"openai","intelligence":"Very High","speed":"Not listed","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":10,"cached_input_per_million":0.1,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.2,"long_context_cache_write_per_million":5,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2 input, $0.10 cached input, $2.50 cache writes, $10 output. Above 272K input: $4 input, $0.20 cached input, $5 cache writes, $15 output."}},{"id":"gpt-6-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Sol model for complex coding and agentic workflows. Chat Completions function calling requires reasoning_effort: none.","owned_by":"openai","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":10,"cached_input_per_million":0.2,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":5,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2 input, $0.2 cached input, $2.5 cache writes, $10 output. Above 272K input: $4 input, $0.4 cached input, $5 cache writes, $15 output."}},{"id":"gpt-6-luna","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-6 Luna model for focused, cost-sensitive, high-volume tasks. Chat Completions function calling requires reasoning_effort: none.","owned_by":"openai","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.1,"output_per_million":0.5,"cached_input_per_million":0.01,"cache_write_per_million":0.125,"long_context_threshold_tokens":272000,"long_context_input_per_million":0.2,"long_context_cached_input_per_million":0.02,"long_context_cache_write_per_million":0.25,"long_context_output_per_million":0.75,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $0.1 input, $0.01 cached input, $0.125 cache writes, $0.5 output. Above 272K input: $0.2 input, $0.02 cached input, $0.25 cache writes, $0.75 output."}},{"id":"gpt-5.6-sol","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Sol frontier model for complex professional, coding, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Highest","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":4,"output_per_million":20,"cached_input_per_million":0.4,"cache_write_per_million":5,"long_context_threshold_tokens":272000,"long_context_input_per_million":8,"long_context_cached_input_per_million":0.8,"long_context_cache_write_per_million":10,"long_context_output_per_million":30,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $4 input, $0.40 cached input, $5 cache writes, $20 output. Above 272K input: $8 input, $0.80 cached input, $10 cache writes, $30 output."}},{"id":"gpt-5.6-terra","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Terra model for workloads that balance intelligence, speed, and cost.","owned_by":"openai","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":12,"cached_input_per_million":0.2,"cache_write_per_million":2.5,"long_context_threshold_tokens":272000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":5,"long_context_output_per_million":18,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $2 input, $0.20 cached input, $2.50 cache writes, $12 output. Above 272K input: $4 input, $0.40 cached input, $5 cache writes, $18 output."}},{"id":"gpt-5.6-luna","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.6 Luna model optimized for fast, cost-sensitive, high-volume workloads.","owned_by":"openai","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh","max"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.2,"output_per_million":1.2,"cached_input_per_million":0.02,"cache_write_per_million":0.25,"long_context_threshold_tokens":272000,"long_context_input_per_million":0.4,"long_context_cached_input_per_million":0.04,"long_context_cache_write_per_million":0.5,"long_context_output_per_million":1.8,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI listed pricing per 1M tokens. Up to 272K input: $0.20 input, $0.02 cached input, $0.25 cache writes, $1.20 output. Above 272K input: $0.40 input, $0.04 cached input, $0.50 cache writes, $1.80 output."}},{"id":"gpt-5.5","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.5 model configuration for advanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":5,"output_per_million":30,"cached_input_per_million":0.5,"cache_write_per_million":null,"long_context_threshold_tokens":272000,"long_context_input_per_million":10,"long_context_cached_input_per_million":1,"long_context_cache_write_per_million":null,"long_context_output_per_million":45,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $5 input, $0.50 cached input, $30 output. Above 272K input: $10 input, $1 cached input, $45 output."}},{"id":"gpt-5.4","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.4 model configuration for advanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1050000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["none","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2.5,"output_per_million":15,"cached_input_per_million":0.25,"cache_write_per_million":null,"long_context_threshold_tokens":272000,"long_context_input_per_million":5,"long_context_cached_input_per_million":0.5,"long_context_cache_write_per_million":null,"long_context_output_per_million":22.5,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard pricing per 1M tokens. Up to 272K input: $2.50 input, $0.25 cached input, $15 output. Above 272K input: $5 input, $0.50 cached input, $22.50 output."}},{"id":"gpt-5.4-mini","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"GPT-5.4 mini model configuration for balanced chat, reasoning, and multimodal workflows.","owned_by":"openai","intelligence":"High","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":400000,"max_output_tokens":128000,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":true,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high","xhigh"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":4.5,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI standard public pricing, per 1M tokens: $0.75 input, $0.075 cached input, $4.50 output."}},{"id":"gpt-4.1","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4.1. Flagship OpenAI model for complex tasks. It is well suited for problem solving across domains. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1047576,"max_output_tokens":32768,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":2,"output_per_million":8,"cached_input_per_million":0.5,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-4.1-mini","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4.1 mini, balancing intelligence, speed, and cost for many use cases. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"High","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1047576,"max_output_tokens":32768,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":0.4,"output_per_million":1.6,"cached_input_per_million":0.1,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-4o","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to GPT-4o. Fast, intelligent, flexible GPT model. OpenAI retires it on January 14, 2027; migrate to gpt-6-luna.","owned_by":"openai","intelligence":"High","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":16384,"open_weights":false,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"retires_at":"2027-01-14","pricing":{"input_per_million":2.5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gemini-3.8-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Google's most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.","owned_by":"google","intelligence":"Highest","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.8 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.7-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"High-speed Gemini Flash model for everyday coding, agentic tool use, and reliable multi-step execution.","owned_by":"google","intelligence":"Higher","speed":"Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.7 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.6-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Previous-generation Gemini Flash model balancing speed and multimodal capability for general agentic and everyday work.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.75,"output_per_million":3.75,"cached_input_per_million":0.075,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"introductory","note":"Gemini 3.6 Flash standard paid-tier introductory pricing through December 31, 2026: $0.75/M input, $0.075/M cached input, and $3.75/M output. Starting January 1, 2027, the listed rates become $1.50/M input, $0.15/M cached input, and $7.50/M output. Explicit cache storage is billed separately."}},{"id":"gemini-3.5-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Earlier Gemini Flash model for routine, high-throughput multimodal work.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":1.5,"output_per_million":9,"cached_input_per_million":0.15,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.5 Flash standard paid-tier pricing: $1.50/M input, $0.15/M cached input, and $9/M output. Explicit cache storage is separately listed at $1/M tokens per hour."}},{"id":"gemini-3.5-flash-lite","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Cost-efficient Gemini model for high-volume agentic tasks, translation, document parsing, and simple data processing.","owned_by":"google","intelligence":"Average","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.3,"output_per_million":2.5,"cached_input_per_million":0.03,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.5 Flash-Lite standard paid-tier pricing: $0.30/M input, $0.03/M cached input, and $2.50/M output. Explicit cache storage is separately listed at $1/M tokens per hour."}},{"id":"gemini-3.1-pro-preview","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Preview Gemini Pro model for advanced multimodal reasoning, software engineering, and precise multi-step agentic workflows.","owned_by":"google","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":false,"top_p":false,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":2,"output_per_million":12,"cached_input_per_million":0.2,"cache_write_per_million":null,"long_context_threshold_tokens":200000,"long_context_input_per_million":4,"long_context_cached_input_per_million":0.4,"long_context_cache_write_per_million":null,"long_context_output_per_million":18,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 3.1 Pro Preview standard paid-tier pricing. Up to 200K input tokens: $2/M input, $0.20/M cached input, and $12/M output. Above 200K: $4/M input, $0.40/M cached input, and $18/M output. Explicit cache storage is billed separately."}},{"id":"gemini-2.5-pro","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Gemini thinking model for complex coding, mathematics, STEM, large datasets, codebases, and documents.","owned_by":"google","intelligence":"Higher","speed":"Medium","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":1.25,"output_per_million":10,"cached_input_per_million":0.125,"cache_write_per_million":null,"long_context_threshold_tokens":200000,"long_context_input_per_million":2.5,"long_context_cached_input_per_million":0.25,"long_context_cache_write_per_million":null,"long_context_output_per_million":15,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Pro standard paid-tier pricing. Up to 200K input tokens: $1.25/M input, $0.125/M cached input, and $10/M output. Above 200K: $2.50/M input, $0.25/M cached input, and $15/M output. Explicit cache storage is billed separately."}},{"id":"gemini-2.5-flash","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Direct access to Gemini 2.5 Flash. Optimized for speed and cost-effective multimodal generation.","owned_by":"google","intelligence":"High","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["none","minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.3,"output_per_million":2.5,"cached_input_per_million":0.03,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Flash standard paid-tier text/image/video pricing: $0.30/M input, $0.03/M cached input, and $2.50/M output. Audio input and explicit cache storage are billed separately."}},{"id":"gemini-2.5-flash-lite","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Cost-efficient Gemini 2.5 model for high-volume classification, simple extraction, and low-latency multimodal work.","owned_by":"google","intelligence":"Average","speed":"Very Fast","input_modalities":["text","image","file","pdf"],"output_modalities":["text"],"context_window":1048576,"max_output_tokens":65536,"open_weights":false,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["none","minimal","low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":true,"pdf":true,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.1,"output_per_million":0.4,"cached_input_per_million":0.01,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini 2.5 Flash-Lite standard paid-tier text/image/video pricing: $0.10/M input, $0.01/M cached input, and $0.40/M output. Audio input and explicit cache storage are billed separately."}},{"id":"nomic-embed-text-v1.5","object":"model","mode":"embedding","endpoint":"/v1/embeddings","description":"Text embedding model for semantic search, clustering, retrieval, and ranking workflows.","owned_by":"viable-lab","intelligence":"Embedding","speed":"Fast","input_modalities":["text"],"output_modalities":["embedding"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":true,"image_generation":false},"pricing":{"input_per_million":0.005,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"docs_inferred","note":"Derived from provider docs: 250,000 pages per dollar at approximately 800 tokens per page."}},{"id":"gpt-image-2.5-sunburst","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Precise image generation with strong editing fidelity.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high","xhigh","max"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-2.5-flare","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Fast, high-quality everyday image generation.","owned_by":"openai","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high","xhigh","max"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-2","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"GPT Image generation with flexible resolutions.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":null,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-1.5","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Earlier GPT Image generation model.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":32,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gpt-image-1-mini","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Cost-efficient GPT Image generation.","owned_by":"openai","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":2,"output_per_million":null,"cached_input_per_million":0.2,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":2.5,"cached_image_input_per_million":0.25,"image_output_per_million":8,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"chatgpt-image-latest","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Moving alias for the image model used in ChatGPT.","owned_by":"openai","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":10,"quality_values":["auto","low","medium","high"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":5,"output_per_million":10,"cached_input_per_million":1.25,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":8,"cached_image_input_per_million":2,"image_output_per_million":32,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI Standard token rates; billed from reported text/image usage, not a fixed per-image price. Direct Images API requests do not receive GPT Image 2/2.5 cached-input discounts. Batch, Responses image tools, editing, and partial-image streaming are not exposed by this endpoint."}},{"id":"gemini-3.1-flash-image","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Nano Banana 2: fast image generation at 0.5K, 1K, 2K, or 4K.","owned_by":"google","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":1,"size_values":["0.5K","1K","2K","4K","512x512","1024x1024","2048x2048","4096x4096","1024x1536","1536x1024"],"aspect_ratio_values":["1:1","3:2","2:3","3:4","4:3","4:5","5:4","9:16","16:9","21:9","1:4","4:1","1:8","8:1"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":0.5,"output_per_million":3,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":0.5,"cached_image_input_per_million":null,"image_output_per_million":60,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini Standard paid-tier rates. At 747/1120/1680/2520 image tokens, output alone costs $0.04482/$0.0672/$0.1008/$0.1512. Input and text/thinking tokens are additional. No free API tier. Batch, search grounding, editing, and streaming are not exposed by this endpoint."}},{"id":"gemini-3.1-flash-lite-image","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Nano Banana 2 Lite: low-latency, cost-efficient 1K image generation.","owned_by":"google","intelligence":"Image","speed":"Fast","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{"n_max":1,"size_values":["1K","1024x1024","1024x1536","1536x1024"],"aspect_ratio_values":["1:1","3:2","2:3","3:4","4:3","4:5","5:4","9:16","16:9","21:9"]},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":0.25,"output_per_million":1.5,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_input_per_million":0.25,"cached_image_input_per_million":null,"image_output_per_million":30,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Gemini Standard paid-tier rates. At 1120 image tokens, 1K output alone costs $0.0336. Input and text/thinking tokens are additional. No free API tier. Batch, search grounding, editing, and streaming are not exposed by this endpoint."}},{"id":"flux.2-klein","object":"model","mode":"image_generation","endpoint":"/v1/images/generations","description":"Image generation model for prompt-to-image workflows.","owned_by":"viable-lab","intelligence":"Image","speed":"Medium","input_modalities":["text"],"output_modalities":["image"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":true},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":0.014,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"starts_at","note":"Provider docs list pricing from $0.014 per image; final cost varies by resolution/model variant."}},{"id":"whisper-large-v3","object":"model","mode":"audio_transcription","endpoint":"/v1/audio/transcriptions","description":"Speech-to-text model for audio transcription.","owned_by":"viable-lab","intelligence":"Audio","speed":"Medium","input_modalities":["audio","file"],"output_modalities":["text"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":false,"images":false,"files":true,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.006,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Provider docs list $0.006 per minute of input audio."}},{"id":"gpt-transcribe","object":"model","mode":"audio_transcription","endpoint":"/v1/audio/transcriptions","description":"OpenAI file transcription with prompt, keyword and multiple language hints. This gateway returns non-streaming JSON.","owned_by":"openai","intelligence":"Audio","speed":"Medium","input_modalities":["audio","file"],"output_modalities":["text"],"context_window":null,"max_output_tokens":null,"open_weights":false,"reasoning_model":false,"parameter_support":{},"supports_streaming":false,"capabilities":{"text":false,"images":false,"files":true,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.0045,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"OpenAI lists an estimated $0.0045 per minute of input audio. Cost is unknown when duration is unavailable."}},{"id":"kokoro","object":"model","mode":"audio_speech","endpoint":"/v1/audio/speech","description":"Text-to-speech model for generated speech audio.","owned_by":"viable-lab","intelligence":"Audio","speed":"Fast","input_modalities":["text"],"output_modalities":["audio"],"context_window":null,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"voice":true,"voice_values":["af_heart","af_alloy","af_aoede","af_bella","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","pf_dora","pm_alex","pm_santa"],"response_format":true,"response_format_values":["mp3","opus","flac","wav","pcm"],"speed":true,"instructions":false},"supports_streaming":false,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":true,"tools":false,"embeddings":false,"image_generation":false},"default_voice":"af_heart","pricing":{"input_per_million":null,"output_per_million":null,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":0.006,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Provider docs list $0.006 per minute of generated audio."}},{"id":"gpt-oss-120b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight 120B model for cost-efficient text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.06,"output_per_million":0.15,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gpt-oss-20b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight 20B model for low-cost text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"Average","speed":"Fast","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":true,"reasoning_effort_values":["low","medium","high"]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.03,"output_per_million":0.07,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":null}},{"id":"gemma-4-31b-it","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight Google Gemma 4 31B instruction model for image understanding, long-context reasoning, coding, and text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text","image"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":true,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.12,"output_per_million":0.36,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Navigator registered pricing, per 1M tokens: $0.12 input, $0.36 output."}},{"id":"nemotron-3-super-120b-a12b","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Open-weight NVIDIA Nemotron 3 Super model for agentic reasoning, coding, planning, and long-context text workflows through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":262144,"max_output_tokens":null,"open_weights":true,"reasoning_model":true,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":false,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.06,"output_per_million":0.24,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Navigator registered pricing, per 1M tokens: $0.06 input, $0.24 output."}},{"id":"mistral-small-3.1","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Mistral Small 3.1 model for cost-efficient open-weight text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"Average","speed":"Fast","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.2,"output_per_million":0.6,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Registered pricing, per 1M tokens: $0.20 input, $0.60 output."}},{"id":"llama-3.3-70b-instruct","object":"model","mode":"chat","endpoint":"/v1/chat/completions","description":"Llama 3.3 70B Instruct model for strong open-weight text generation through the VIABLE API.","owned_by":"viable-lab","intelligence":"High","speed":"Medium","input_modalities":["text"],"output_modalities":["text"],"context_window":128000,"max_output_tokens":null,"open_weights":true,"reasoning_model":false,"parameter_support":{"temperature":true,"top_p":true,"max_tokens":true,"max_completion_tokens":false,"reasoning_effort":false,"reasoning_effort_values":[]},"supports_streaming":true,"capabilities":{"text":true,"images":false,"files":false,"pdf":false,"audio":false,"tools":true,"embeddings":false,"image_generation":false},"pricing":{"input_per_million":0.4,"output_per_million":0.4,"cached_input_per_million":null,"cache_write_per_million":null,"long_context_threshold_tokens":null,"long_context_input_per_million":null,"long_context_cached_input_per_million":null,"long_context_cache_write_per_million":null,"long_context_output_per_million":null,"input_character_per_million":null,"image_per_unit":null,"audio_per_minute":null,"audio_output_per_million":null,"fallback_audio_per_minute":null,"status":"documented","note":"Registered pricing, per 1M tokens: $0.40 input, $0.40 output."}}],"endpoints":[{"method":"POST","path":"/v1/chat/completions","mode":"chat","request_format":"OpenAI Chat Completions JSON","streaming":true,"notes":["Send model plus messages. The API accepts supported aliases and model IDs while keeping routing details internal.","Text, image data URLs, files, and PDFs are accepted by compatible models."]},{"method":"POST","path":"/v1/agents/{slug}/runs","mode":"agent","request_format":"Published agent run JSON","streaming":false,"notes":["Run one turn of a published visual/code agent workflow with an API key that has agents:execute scope.","Send input as a string, a content-part array, or an OpenAI Responses-style user message array for the latest end-user turn. Use input_text/text for text and input_image/image_url for images.","Multimodal input is passed only to LLM nodes that consume the user turn; those nodes must use models whose input_modalities include the requested media type.","Preserve the returned conversation_id and send it on later turns to continue the same agent chat thread.","Use conversation_id only with published agent runs. For direct chat or VETTING, include the context required by that request and treat any app- or provider-level session state as separate from this field.","Each run returns run_id, output, usage, cost, and input_assets for archived turn media; request logs expose both the run summary and internal provider calls.","Inline assets are limited to 8 MiB each and 10 MiB decoded total inside a 12 MiB JSON body. At most 8 MiB of prior private media is materialized per model request."]},{"method":"POST","path":"/v1/agents/{slug}/chat/completions","mode":"agent","request_format":"Non-streaming Chat Completions envelope","streaming":false,"notes":["Use the agent slug as model and send role-preserving messages. Client-owned history is the default; no conversation is created.","Tools, streaming and generation overrides are rejected. The published graph owns generation settings."]},{"method":"POST","path":"/v1/agents/{slug}/jobs","mode":"agent","request_format":"Native Agent JSON with required Idempotency-Key","streaming":false,"notes":["Returns 202 with a job ID and status_url. Poll with the same API key.","Queued work is durable; uncertain execution is marked recovery_required, never blindly restarted."]},{"method":"GET","path":"/v1/agents/{slug}/jobs/{id}","mode":"agent","request_format":"Authenticated job status/result","streaming":false,"notes":["Statuses: queued, running, completed, failed, recovery_required. Completed responses include result in native Agent format."]},{"method":"POST","path":"/v1/chat/vetting","mode":"chat","request_format":"OpenAI Chat Completions JSON with vetting metadata","streaming":false,"notes":["Use the chat request shape when you want a vetted educational response.","The response preserves chat completion choices and adds vetting_info.","Uses the same chat model registry as /v1/chat/completions; non-chat models are rejected."]},{"method":"POST","path":"/v1/vetting/full","mode":"chat","request_format":"Full VETTING workflow JSON","streaming":false,"notes":["Use for structured educational verification against questions and answer keys.","chatModel and verificationModel can use different chat-capable providers.","This endpoint is intentionally non-streaming."]},{"method":"POST","path":"/v1/embeddings","mode":"embedding","request_format":"OpenAI Embeddings JSON","streaming":false,"notes":["Send input text or an array of strings. Default model is nomic-embed-text-v1.5."]},{"method":"POST","path":"/v1/images/generations","mode":"image_generation","request_format":"OpenAI Images JSON","streaming":false,"notes":["Send prompt, optional size/n/quality/response_format. Default model is flux.2-klein; GPT Image and Gemini image models are also listed.","Gemini supports n=1, size resolution tiers and aspect_ratio; Lite supports only 1K. Portrait/landscape pixel presets select a 1K aspect ratio rather than exact dimensions.","GPT Image and Gemini cost uses reported text/image tokens at Standard rates. Missing modality usage leaves cost unknown. Batch, editing, search grounding and partial-image streaming are not exposed.","response_format=url returns a public https://api.viablelab.org/v1/assets/... URL when the provider returns inline image data.","response_format=b64_json returns inline base64 to the caller; logs redact base64 and include an asset URL preview when asset storage is available."]},{"method":"GET","path":"/v1/assets/{key}","mode":"asset","request_format":"Generated asset URL","streaming":true,"notes":["Serves API-generated assets such as image and speech outputs stored in private R2.","Only unguessable API-generated asset keys are accepted; upload and delete operations are not exposed."]},{"method":"POST","path":"/v1/audio/speech","mode":"audio_speech","request_format":"OpenAI Audio Speech JSON","streaming":false,"notes":["Send input, model, voice, and response_format. Binary audio is returned in the requested format; when asset storage is available, logs include a backup /v1/assets/audio/... URL. Kokoro is the default speech model, with 54 catalog-listed voices, default af_heart, mp3/opus/flac/wav/pcm formats, and no instructions support. Pricing is $0.006 per audio minute. Retired IDs return 410 model_retired without redirection."]},{"method":"POST","path":"/v1/audio/transcriptions","mode":"audio_transcription","request_format":"multipart/form-data","streaming":false,"notes":["Send file and model (whisper-large-v3 by default, or gpt-transcribe). gpt-transcribe uses repeated languages[]/keywords[] fields and non-streaming JSON; singular language or unsupported formats return 400. Estimated price is $0.0045 per minute. Provider duration takes precedence over client duration; missing duration leaves cost unknown. Retired IDs return 410 model_retired without redirection."]}],"quickstarts":{"chat":{"curl":"curl https://api.viablelab.org/v1/chat/completions -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"viable-3\",\"messages\":[{\"role\":\"user\",\"content\":\"Write one sentence.\"}]}'"},"streaming_chat":{"curl":"curl -N https://api.viablelab.org/v1/chat/completions -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"gpt-oss-120b\",\"stream\":true,\"messages\":[{\"role\":\"user\",\"content\":\"Stream one sentence.\"}]}'"},"agent_run":{"curl":"curl https://api.viablelab.org/v1/agents/my-agent/runs -H \"Content-Type: application/json\" -H \"Authorization: Bearer $VIABLE_API_KEY\" -d '{\"input\":\"Can you help me plan a short story?\"}'"},"agent_image_input":{"curl":"curl https://api.viablelab.org/v1/agents/my-agent/runs -H \"Content-Type: application/json\" -H \"Authorization: Bearer $VIABLE_API_KEY\" -d '{\"input\":[{\"type\":\"input_text\",\"text\":\"What is this image?\"},{\"type\":\"input_image\",\"image_url\":\"https://example.com/image.png\",\"filename\":\"classroom.png\"}]}'"},"agent_continue_conversation":{"curl":"curl https://api.viablelab.org/v1/agents/my-agent/runs -H \"Content-Type: application/json\" -H \"Authorization: Bearer $VIABLE_API_KEY\" -d '{\"input\":\"Continue from the last idea.\",\"conversation_id\":\"agtc_...\"}'"},"embedding":{"curl":"curl https://api.viablelab.org/v1/embeddings -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"nomic-embed-text-v1.5\",\"input\":\"Searchable text\"}'"},"image_generation":{"curl":"curl https://api.viablelab.org/v1/images/generations -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"flux.2-klein\",\"prompt\":\"A clean classroom whiteboard UI mockup\",\"size\":\"1024x1024\",\"n\":1,\"response_format\":\"url\"}'"},"image_generation_b64":{"curl":"curl https://api.viablelab.org/v1/images/generations -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"flux.2-klein\",\"prompt\":\"A clean classroom whiteboard UI mockup\",\"size\":\"1024x1024\",\"n\":1,\"response_format\":\"b64_json\"}'"},"speech":{"curl":"curl https://api.viablelab.org/v1/audio/speech -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"kokoro\",\"input\":\"Hello from VIABLE Lab.\",\"voice\":\"af_heart\",\"response_format\":\"mp3\"}' --output speech.mp3"},"transcription":{"curl":"curl https://api.viablelab.org/v1/audio/transcriptions -H \"Authorization: Bearer $VIABLE_API_KEY\" -F model=whisper-large-v3 -F file=@sample.mp3"},"openai_transcription":{"curl":"curl https://api.viablelab.org/v1/audio/transcriptions -H \"Authorization: Bearer $VIABLE_API_KEY\" -F model=gpt-transcribe -F file=@sample.mp3"},"vetted_chat":{"curl":"curl https://api.viablelab.org/v1/chat/vetting -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"viable-3\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain photosynthesis without giving away a homework answer.\"}],\"vettingConfig\":{\"maxAttempts\":3}}'"},"full_vetting":{"curl":"curl https://api.viablelab.org/v1/vetting/full -H \"Authorization: Bearer $VIABLE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"mode\":\"vetting\",\"config\":{\"chatModel\":{\"modelId\":\"viable-3\"},\"verificationModel\":{\"modelId\":\"gemini-2.5-flash\"},\"maxVerificationAttempts\":1},\"prompts\":{\"chatSystemPrompt\":\"Guide the student without giving away the answer.\"},\"context\":{\"items\":[{\"question\":{\"text\":\"What is photosynthesis?\"},\"answerKey\":{\"correctAnswer\":\"Plants convert light, water, and carbon dioxide into glucose and oxygen.\"}}]},\"messages\":[{\"role\":\"user\",\"content\":\"What is photosynthesis?\"}]}'"}},"pricing_notes":["Token prices are registry-backed and logged when providers return token usage.","Image usage can have zero tokens and non-zero cost because it is priced per generated image rather than per token.","Image model pricing is currently documented as a starting price and may vary by resolution.","Speech pricing can be character-based, token-based, or minute-based depending on the model.","Use listed model IDs from /v1/models. Contact VIABLE Lab if you need access to a new or unlisted model.","Models without listed pricing are logged with null cost until pricing is added to the registry."],"logging_notes":["Data-plane request logs retain request and response text by default for research replay, including chat history, prompts, VETTING configuration, and text-to-speech input.","Inline Agent media is archived byte-for-byte in private R2 and represented in D1 logs, traces, and conversation history by authenticated research asset references; exact HTTPS source URLs remain restricted provenance metadata, are not fetched automatically, and may expire at the source.","Credentials, authorization headers, cookies, tokens, passwords, and private keys are always redacted, including when full research logging is configured.","Platform attribution is separate from API key attribution. Use X-Platform-ID and optional X-Platform-Name for product/source labels; otherwise logs fall back to Origin/Referer or direct API call.","Published agent runs add agent_id, agent_run_id, agent_node_id, and agent step/call fields to request logs so run summaries and internal provider calls can be grouped for audit and export.","Automatic enc::... payload decryption is currently limited to documented VETTING prompt fields; encryption utility endpoints can encrypt or decrypt arbitrary text but other model endpoints do not globally decrypt enc:: values.","Credentials, sensitive headers, file bytes, data URI payloads, generated image base64, and standalone encryption utility payloads are not stored directly in D1.","Set LOG_CONTENT_MODE=redacted to store prompt summaries only; LOG_FULL_CONTENT=true is reserved for controlled internal debugging."],"cache":{"status":"miss","ttlSeconds":3600}}