{"object":"list","data":[{"id":"openai/gpt-6-astra","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-6 Astra","description":"OpenAI flagship — GPT-6 generation, tuned for long-horizon agentic work and computer use. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5,"long_context":[{"threshold":272000,"inclusive":false,"input":20,"output":75,"cache_read":2,"cache_write":25}]}},{"id":"openai/gpt-6.1-sol","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-6.1 Sol","description":"Refreshed GPT-6 Sol — complex coding and agentic workflows below the Astra flagship, April 2026 knowledge. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5,"long_context":[{"threshold":272000,"inclusive":false,"input":4,"output":15,"cache_read":0.2,"cache_write":5}]}},{"id":"openai/gpt-6-sol","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-6 Sol","description":"Cost-efficient GPT-6 tier — complex coding and agentic workflows below the Astra flagship. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"long_context":[{"threshold":272000,"inclusive":false,"input":4,"output":15,"cache_read":0.4,"cache_write":5}]}},{"id":"openai/gpt-6-luna","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-6 Luna","description":"Fast, low-cost GPT-6 tier — high-volume chat, classification and lightweight agentic work. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125,"long_context":[{"threshold":272000,"inclusive":false,"input":0.2,"output":0.75,"cache_read":0.02,"cache_write":0.25}]}},{"id":"openai/gpt-5.6-sol","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Sol","description":"Top GPT-5.6 tier — deepest reasoning for complex coding, agentic workflows, and long-horizon problems. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"long_context":[{"threshold":272000,"inclusive":false,"input":8,"output":30,"cache_read":0.8,"cache_write":10}]}},{"id":"openai/gpt-5.6-terra","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 tier — everyday coding, reasoning, and agentic tasks at half the flagship price. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"long_context":[{"threshold":272000,"inclusive":false,"input":4,"output":18,"cache_read":0.4,"cache_write":5}]}},{"id":"openai/gpt-5.6-luna","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 tier for high-volume, latency-sensitive chat and lightweight agentic workflows. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"long_context":[{"threshold":272000,"inclusive":false,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}]}},{"id":"openai/gpt-5.6-sol-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Sol Pro","description":"Highest-capability GPT-5.6 — Sol with pro reasoning mode for the hardest problems and long-running agentic work. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"long_context":[{"threshold":272000,"inclusive":false,"input":8,"output":30,"cache_read":0.8,"cache_write":10}]}},{"id":"openai/gpt-5.6-terra-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Terra Pro","description":"GPT-5.6 Terra with pro reasoning mode — deeper responses on complex tasks at half the standard Terra rate. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"long_context":[{"threshold":272000,"inclusive":false,"input":4,"output":18,"cache_read":0.4,"cache_write":5}]}},{"id":"openai/gpt-5.6-luna-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.6 Luna Pro","description":"GPT-5.6 Luna with pro reasoning mode — budget tier with deeper reasoning for high-volume workloads. 1M context","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"long_context":[{"threshold":272000,"inclusive":false,"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}]}},{"id":"openai/gpt-5.5","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.5","description":"First fully retrained base since GPT-4.5. 1M context, 128K output, native agent + computer use","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":30,"cache_read":0.5,"long_context":[{"threshold":272000,"inclusive":false,"input":10,"output":45,"cache_read":1}]}},{"id":"openai/gpt-5.5-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.5 Pro","description":"Premium GPT-5.5 with maximum compute for the hardest problems","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":30,"output":180,"long_context":[{"threshold":272000,"inclusive":false,"input":60,"output":270}]}},{"id":"openai/chat-latest","object":"model","created":1700000000,"owned_by":"openai","name":"ChatGPT Instant (GPT-5.5)","description":"ChatGPT's default model — the rolling `chat-latest` alias, currently GPT-5.5 Instant. Tuned for speed and concision, same price as GPT-5.5","context_window":128000,"max_output":128000,"categories":["chat","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":30,"cache_read":0.5}},{"id":"openai/gpt-5.4","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.4","description":"GPT-5.4 frontier model with 1M context, native computer use, and thinking mode","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"long_context":[{"threshold":272000,"inclusive":false,"input":5,"output":22.5,"cache_read":0.5}]}},{"id":"openai/gpt-5.4-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.4 Pro","description":"Premium GPT-5.4 with maximum compute for the hardest problems","context_window":1050000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":30,"output":180,"long_context":[{"threshold":272000,"inclusive":false,"input":60,"output":270}]}},{"id":"openai/gpt-5.1","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.1","description":"Frontier model with 400K context and configurable reasoning effort","context_window":400000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1.25,"output":10,"cache_read":0.125}},{"id":"openai/gpt-5.2","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.2","description":"Frontier model with 400K context and adaptive reasoning","context_window":400000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1.75,"output":14,"cache_read":0.175}},{"id":"openai/gpt-5.4-mini","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.4 Mini","description":"Strongest mini model for coding, computer use, and subagents with GPT-5.4 capabilities","context_window":400000,"max_output":128000,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075}},{"id":"openai/gpt-5-mini","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5 Mini","description":"Cost-optimized reasoning and chat","context_window":200000,"max_output":128000,"categories":["chat","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.25,"output":2,"cache_read":0.025}},{"id":"openai/gpt-5.4-nano","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.4 Nano","description":"Fastest and most affordable GPT-5.4 model for high-throughput tasks","context_window":1050000,"max_output":128000,"categories":["chat"],"billing_mode":"paid","available":true,"pricing":{"input":0.2,"output":1.25,"cache_read":0.02}},{"id":"openai/gpt-5.2-pro","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.2 Pro","description":"Uses more compute for consistently better answers","context_window":400000,"max_output":128000,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":21,"output":168}},{"id":"openai/gpt-5.3-codex","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-5.3 Codex","description":"Industry-leading agentic coding model. 400K context, reasoning, tool use, and complex execution","context_window":400000,"max_output":128000,"categories":["coding","reasoning","chat"],"billing_mode":"paid","available":true,"pricing":{"input":1.75,"output":14,"cache_read":0.175}},{"id":"openai/gpt-4.1","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-4.1","description":"Latest GPT-4 generation model","context_window":128000,"max_output":32768,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":8,"cache_read":0.5}},{"id":"openai/gpt-4.1-mini","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-4.1 Mini","description":"Fast and affordable GPT-4.1 model","context_window":128000,"max_output":32768,"categories":["chat","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.4,"output":1.6,"cache_read":0.1}},{"id":"openai/gpt-4.1-nano","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-4.1 Nano","description":"Ultra-fast and cost-effective GPT-4.1","context_window":128000,"max_output":32768,"categories":["chat"],"billing_mode":"paid","available":true,"pricing":{"input":0.1,"output":0.4,"cache_read":0.025}},{"id":"openai/gpt-4o","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-4o","description":"Multimodal model with vision and audio","context_window":128000,"max_output":16384,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2.5,"output":10,"cache_read":1.25}},{"id":"openai/gpt-4o-mini","object":"model","created":1700000000,"owned_by":"openai","name":"GPT-4o Mini","description":"Fast and affordable GPT-4o model","context_window":128000,"max_output":16384,"categories":["chat","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075}},{"id":"openai/o1","object":"model","created":1700000000,"owned_by":"openai","name":"o1","description":"Advanced reasoning model for complex tasks","context_window":200000,"max_output":100000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":15,"output":60,"cache_read":7.5}},{"id":"openai/o3","object":"model","created":1700000000,"owned_by":"openai","name":"o3","description":"o-series reasoning model with improved performance","context_window":200000,"max_output":100000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":8,"cache_read":0.5}},{"id":"openai/o3-mini","object":"model","created":1700000000,"owned_by":"openai","name":"o3-mini","description":"Efficient reasoning model for STEM tasks","context_window":128000,"max_output":100000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.1,"output":4.4,"cache_read":0.55}},{"id":"openai/o4-mini","object":"model","created":1700000000,"owned_by":"openai","name":"o4-mini","description":"Efficient o4-generation reasoning model","context_window":128000,"max_output":100000,"categories":["reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.1,"output":4.4,"cache_read":0.275}},{"id":"anthropic/claude-haiku-4.5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Haiku 4.5","description":"Fastest and most efficient Claude, near-frontier intelligence","context_window":200000,"max_output":64000,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25}},{"id":"anthropic/claude-sonnet-5.5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Sonnet 5.5","description":"Newest Sonnet — fast, capable everyday coding and agent work at Sonnet cost. 1M context, 128k output, adaptive thinking, vision","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}},{"id":"anthropic/claude-sonnet-5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Sonnet 5","description":"Sonnet 5 — near-Opus coding/agentic quality at Sonnet cost. 1M context, 128k output, adaptive thinking, vision","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}},{"id":"anthropic/claude-sonnet-4.6","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Sonnet 4.6","description":"Sonnet 4.6 — a balance of intelligence, speed, and cost","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75}},{"id":"anthropic/claude-sonnet-4.5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Sonnet 4.5","description":"Sonnet 4.5 — strong coding and agentic performance, vision","context_window":200000,"max_output":64000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75}},{"id":"anthropic/claude-opus-4.5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Opus 4.5","description":"Claude Opus 4.5 — enhanced reasoning and creativity","context_window":200000,"max_output":64000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}},{"id":"anthropic/claude-opus-4.7","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Opus 4.7","description":"Powerful Claude Opus for complex reasoning and agentic coding. 1M context, 128k output, adaptive thinking","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}},{"id":"anthropic/claude-fable-5.1","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Fable 5.1","description":"Anthropic's most capable model — successor to Fable 5 in the same tier at the same price, for the most demanding reasoning and long-horizon agentic work. 1M context, 128K output, always-on thinking","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":10,"output":50,"cache_read":0.25,"cache_write":12.5}},{"id":"anthropic/claude-fable-5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Fable 5","description":"Mythos-class tier above Opus, for the most demanding reasoning and long-horizon agentic work. 1M context, 128K output, always-on thinking","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5}},{"id":"anthropic/claude-opus-4.8","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Opus 4.8","description":"Most capable Claude 4-series Opus for complex reasoning and agentic coding. 1M context, 128k output, adaptive thinking","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}},{"id":"anthropic/claude-opus-5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Opus 5","description":"Opus 5 — step-change over Opus 4.8 for deep reasoning and agentic coding at the same price. 1M context, 128k output, adaptive thinking","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}},{"id":"anthropic/claude-opus-5.5","object":"model","created":1700000000,"owned_by":"anthropic","name":"Claude Opus 5.5","description":"Newest Opus — Opus-class deep reasoning and agentic coding at a lower price than Opus 5. 1M context, 128k output, always-on adaptive thinking, vision","context_window":1000000,"max_output":128000,"categories":["chat","coding","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":4,"output":20,"cache_read":0.2,"cache_write":5}},{"id":"google/gemini-4-argon","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 4 Argon","description":"Google's frontier reasoning model, built for long multi-step agent work, complex software engineering and deep math and science problems","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.1}},{"id":"google/gemini-3.1-pro","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.1 Pro","description":"Gemini 3.1 Pro with improved thinking, token efficiency, and agentic capabilities. Optimized for software engineering (requires new SDK)","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":12,"cache_read":0.2,"long_context":[{"threshold":200000,"inclusive":false,"input":4,"output":18,"cache_read":0.4}]}},{"id":"google/gemini-3-flash-preview","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3 Flash Preview","description":"Frontier-class performance with Pro-level intelligence at Flash speed and pricing. Includes thinking mode (requires new SDK)","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.5,"output":3}},{"id":"google/gemini-3.8-flash","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.8 Flash","description":"Newest-generation Flash with built-in thinking mode — frontier-class quality at Flash speed","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.75,"output":3.75,"cache_read":0.075}},{"id":"google/gemini-3.6-flash","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.6 Flash","description":"Gemini 3.6 Flash with built-in thinking mode — frontier-class quality at Flash speed","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.75,"output":3.75,"cache_read":0.075}},{"id":"google/gemini-3.5-flash","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.5 Flash","description":"Gemini 3.5 Flash with built-in thinking mode — frontier-class quality at Flash speed","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1.5,"output":9,"cache_read":0.15}},{"id":"google/gemini-2.5-pro","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 2.5 Pro","description":"Gemini 2.5 Pro — strong reasoning, coding, and mathematics","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"long_context":[{"threshold":200000,"inclusive":false,"input":2.5,"output":15,"cache_read":0.25}]}},{"id":"google/gemini-2.5-flash","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 2.5 Flash","description":"Fast and efficient Gemini model with vision support","context_window":1048576,"max_output":65536,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03}},{"id":"google/gemini-3.5-flash-lite","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.5 Flash Lite","description":"Latest Flash Lite — ultra-fast, lightweight Gemini with thinking mode for high-throughput tasks","context_window":1048576,"max_output":65536,"categories":["chat","reasoning"],"billing_mode":"paid","available":true,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03}},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 3.1 Flash Lite","description":"Ultra-fast and lightweight Gemini 3.1 model with thinking mode for high-throughput tasks","context_window":1048576,"max_output":65536,"categories":["chat","reasoning"],"billing_mode":"paid","available":true,"pricing":{"input":0.25,"output":1.5,"cache_read":0.025}},{"id":"google/gemini-2.5-flash-lite","object":"model","created":1700000000,"owned_by":"google","name":"Gemini 2.5 Flash Lite","description":"Most economical Gemini model - ultra-fast and lightweight (requires new SDK)","context_window":1048576,"max_output":65536,"categories":["chat"],"billing_mode":"paid","available":true,"pricing":{"input":0.1,"output":0.4,"cache_read":0.01}},{"id":"deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1700000000,"owned_by":"deepseek","name":"DeepSeek V4 Flash Vision","description":"DeepSeek V4 Flash Vision — 1M context with text and image input. Experimental multimodal tier of the V4 Flash family.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006}},{"id":"deepseek/deepseek-v4-pro","object":"model","created":1700000000,"owned_by":"deepseek","name":"DeepSeek V4 Pro","description":"DeepSeek V4 flagship — 1.6T MoE / 49B active, 1M context. Strongest open-weight reasoner. Thinking mode default.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.32,"output":3.96,"cache_read":0.044}},{"id":"deepseek/deepseek-v4.1-flash","object":"model","created":1700000000,"owned_by":"deepseek","name":"DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash in non-thinking mode — 1M context at $0.14 in / $0.28 out. Production-grade reliability and 5MB request bodies.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.14,"output":0.28,"cache_read":0.006}},{"id":"deepseek/deepseek-chat","object":"model","created":1700000000,"owned_by":"deepseek","name":"DeepSeek Chat (V4.1 Flash)","description":"Compatibility id for DeepSeek V4.1 Flash in non-thinking mode ($0.14 in / $0.28 out) — same model, price and routing as deepseek/deepseek-v4.1-flash. Production-grade reliability and 5MB request bodies.","context_window":1048576,"max_output":65536,"categories":["chat","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.14,"output":0.28,"cache_read":0.006}},{"id":"deepseek/deepseek-reasoner","object":"model","created":1700000000,"owned_by":"deepseek","name":"DeepSeek Reasoner (V4.1 Flash)","description":"Compatibility id for DeepSeek V4.1 Flash in thinking mode for reasoning tasks ($0.14 in / $0.28 out). Same upstream as deepseek/deepseek-v4.1-flash but with thinking enabled by default.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.14,"output":0.28,"cache_read":0.006}},{"id":"moonshot/kimi-k3.1-pro","object":"model","created":1700000000,"owned_by":"moonshot","name":"Kimi K3.1 Pro","description":"Moonshot's flagship — post-trained successor to Kimi K3 for long-horizon coding and agents. 1M context, image + text input, returns reasoning_content.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":10,"cache_read":0.2}},{"id":"zai/glm-5.3","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5.3","description":"Z.AI's flagship — 1M-token context with always-on reasoning, strong at long-horizon coding. Verified live on Z.AI.","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26}},{"id":"zai/glm-5.3-flash","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5.3 Flash","description":"Z.AI's first natively multimodal GLM-5 — 320B/18B MoE with image input, 1M-token context, and always-on reasoning at value-tier pricing. Verified live on Z.AI.","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.15,"output":0.5,"cache_read":0.03}},{"id":"zai/glm-5.2","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5.2","description":"Z.AI GLM-5.2 — 1M-token context, strong open-source long-horizon coding. Verified live on Z.AI.","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26}},{"id":"zai/glm-5.1","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5.1","description":"Z.AI's GLM-5.1 — #1 open source on SWE-Bench Pro, 8-hour autonomous execution. 200K context","context_window":200000,"max_output":128000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26}},{"id":"zai/glm-5","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5","description":"Z.AI's foundation model with 200K context. Strong reasoning and agentic capabilities","context_window":200000,"max_output":128000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1,"output":3.2,"cache_read":0.2}},{"id":"zai/glm-5-turbo","object":"model","created":1700000000,"owned_by":"zai","name":"GLM-5 Turbo","description":"Optimized GLM-5 variant with faster inference","context_window":200000,"max_output":128000,"categories":["chat","reasoning"],"billing_mode":"paid","available":true,"pricing":{"input":1.2,"output":4}},{"id":"xai/grok-4.3","object":"model","created":1700000000,"owned_by":"xai","name":"Grok 4.3","description":"xAI's Grok 4.3 reasoning model. 1M context, vision-capable, tuned for agentic workflows and instruction-following.","context_window":1000000,"max_output":16384,"categories":["reasoning","coding","vision","chat"],"billing_mode":"paid","available":true,"pricing":{"input":1.25,"output":2.5,"cache_read":0.2,"long_context":[{"threshold":200000,"inclusive":true,"input":2.5,"output":5,"cache_read":0.4}]}},{"id":"xai/grok-build-0.1","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Build 0.1","description":"xAI's fast agentic coding model, trained for interactive software-engineering workflows. 256K context, text + image input.","context_window":256000,"max_output":16384,"categories":["coding","chat"],"billing_mode":"paid","available":true,"pricing":{"input":1,"output":2,"cache_read":0.2,"long_context":[{"threshold":200000,"inclusive":true,"input":2,"output":4,"cache_read":0.4}]}},{"id":"xai/grok-4.7","object":"model","created":1700000000,"owned_by":"xai","name":"Grok 4.7","description":"xAI's flagship Grok 4.7 — 500K context, vision, always-on reasoning with selectable effort (low to xhigh). Supports Live Search (+$0.30 per call)","context_window":500000,"max_output":16384,"categories":["reasoning","coding","vision","chat","search"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":6,"cache_read":0.5,"long_context":[{"threshold":200000,"inclusive":true,"input":4,"output":12,"cache_read":1}]}},{"id":"xai/grok-4.6","object":"model","created":1700000000,"owned_by":"xai","name":"Grok 4.6","description":"xAI's Grok 4.6 — 500K context, chain-of-thought reasoning with selectable effort. Supports Live Search (+$0.30 per call)","context_window":500000,"max_output":16384,"categories":["reasoning","coding","vision","chat","search"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":6,"cache_read":0.5,"long_context":[{"threshold":200000,"inclusive":true,"input":4,"output":12,"cache_read":1}]}},{"id":"xai/grok-4.5","object":"model","created":1700000000,"owned_by":"xai","name":"Grok 4.5","description":"xAI's Grok 4.5 — 500K context, vision-capable, chain-of-thought reasoning. Supports Live Search (+$0.30 per call)","context_window":500000,"max_output":16384,"categories":["reasoning","coding","vision","chat","search"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":6,"cache_read":0.3,"long_context":[{"threshold":200000,"inclusive":true,"input":4,"output":12,"cache_read":0.6}]}},{"id":"minimax/minimax-m2.7","object":"model","created":1700000000,"owned_by":"minimax","name":"MiniMax M2.7","description":"MiniMax's M2.7 reasoning model with recursive self-improvement. Great value for complex tasks (~60 tps)","context_window":204800,"max_output":16384,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.3,"output":1.2}},{"id":"minimax/minimax-m3","object":"model","created":1700000000,"owned_by":"minimax","name":"MiniMax M3","description":"MiniMax's M3 flagship — 1M context, strong reasoning + coding.","context_window":1048576,"max_output":65536,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.3,"output":1.2}},{"id":"qwen/qwen3.8-max","object":"model","created":1700000000,"owned_by":"qwen","name":"Qwen3.8 Max","description":"Alibaba's Qwen3.8 Max — current flagship of the Qwen line. 1M context, 131K output.","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":2,"output":6}},{"id":"qwen/qwen3.7-max","object":"model","created":1700000000,"owned_by":"qwen","name":"Qwen3.7 Max","description":"Alibaba's Qwen3.7 Max tier. 1M context, strong reasoning, coding, and agentic tool use. Live-verified 2026-07-20.","context_window":1000000,"max_output":65536,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":1.475,"output":4.425}},{"id":"qwen/qwen3.7-plus","object":"model","created":1700000000,"owned_by":"qwen","name":"Qwen3.7 Plus","description":"Alibaba's balanced Qwen tier — 1M context with reasoning, coding, and agentic tool use at a fraction of the Max price","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.32,"output":1.28,"long_context":[{"threshold":256000,"inclusive":true,"input":0.96,"output":3.84}]}},{"id":"qwen/qwen3.7-flash","object":"model","created":1700000000,"owned_by":"qwen","name":"Qwen3.7 Flash","description":"Alibaba's fastest Qwen tier — 1M context reasoning for high-volume, latency-sensitive workloads","context_window":1000000,"max_output":65536,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.03,"output":0.13,"long_context":[{"threshold":32000,"inclusive":true,"input":0.1,"output":0.4},{"threshold":256000,"inclusive":true,"input":0.2,"output":0.8}]}},{"id":"qwen/qwen3.8-flash","object":"model","created":1700000000,"owned_by":"qwen","name":"Qwen3.8 Flash","description":"Alibaba's Qwen3.8 Flash — 125B MoE with hybrid attention, 1M context, image input. Outperforms the Qwen3.7 Plus tier at a lower price.","context_window":1000000,"max_output":131072,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.15,"output":0.47}},{"id":"tencent/hy4-preview","object":"model","created":1700000000,"owned_by":"tencent","name":"Tencent Hy4 Preview","description":"Tencent's Hy4 — 770B mixture-of-experts, Apache 2.0, 1M context. A large open flagship at a fraction of closed-model pricing.","context_window":1048576,"max_output":64000,"categories":["chat","reasoning","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.834,"output":2.501}},{"id":"xiaomi/mimo-v2.5","object":"model","created":1700000000,"owned_by":"xiaomi","name":"MiMo V2.5","description":"Xiaomi's MiMo V2.5 — 310B sparse MoE, natively multimodal, 1M context. Accepts text and images.","context_window":1048576,"max_output":131072,"categories":["chat","reasoning","vision"],"billing_mode":"paid","available":true,"pricing":{"input":0.14,"output":0.28}},{"id":"xiaomi/mimo-v2.5-pro","object":"model","created":1700000000,"owned_by":"xiaomi","name":"Xiaomi MiMo-V2.5 Pro","description":"Xiaomi's MiMo-V2.5 Pro — 1M context reasoning model, priced well below the frontier tier.","context_window":1048576,"max_output":131072,"categories":["chat","reasoning"],"billing_mode":"paid","available":true,"pricing":{"input":0.435,"output":0.87}},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","object":"model","created":1700000000,"owned_by":"nvidia","name":"Nemotron 3 Nano Omni (Free)","description":"NVIDIA's multimodal reasoning Nemotron Nano Omni, free. 31B / 3.2B active MoE. Accepts text, images, video, audio. ChartQA 90.3, DocVQA 95.6, MMMU 70.8 — the only free model in our catalog that takes video and audio as well as images","context_window":256000,"max_output":16384,"categories":["chat","reasoning","vision"],"billing_mode":"free","available":false,"pricing":{"input":0,"output":0}},{"id":"nvidia/nemotron-3.5-lightning","object":"model","created":1700000000,"owned_by":"nvidia","name":"Nemotron 3.5 Lightning (Free)","description":"NVIDIA Nemotron 3.5 Lightning 30B-A3B, free. Thinking-mode reasoning with a 1M-token context.","context_window":1000000,"max_output":16384,"categories":["chat","reasoning"],"billing_mode":"free","available":true,"pricing":{"input":0,"output":0}},{"id":"nvidia/llama-3.2-11b-vision","object":"model","created":1700000000,"owned_by":"nvidia","name":"Llama 3.2 11B Vision (Free)","description":"Meta's Llama 3.2 11B Vision hosted free by NVIDIA. Accepts images; 128K context.","context_window":128000,"max_output":16384,"categories":["chat","vision"],"billing_mode":"free","available":true,"pricing":{"input":0,"output":0}},{"id":"nvidia/nemotron-3-ultra-550b","object":"model","created":1700000000,"owned_by":"nvidia","name":"Nemotron 3 Ultra 550B (Free)","description":"NVIDIA Nemotron 3 Ultra 550B-A55B, free. 550B total / 55B active MoE with a 1M-token context — the largest free model in the catalog.","context_window":1000000,"max_output":16384,"categories":["chat","reasoning"],"billing_mode":"free","available":true,"pricing":{"input":0,"output":0}},{"id":"cohere/north-mini-code","object":"model","created":1700000000,"owned_by":"cohere","name":"Cohere North Mini Code (Free)","description":"Cohere's North Mini Code, free. Compact coding model, 256K context, sub-second responses.","context_window":256000,"max_output":16384,"categories":["chat","coding"],"billing_mode":"free","available":false,"pricing":{"input":0,"output":0}},{"id":"poolside/laguna-xs-2.1","object":"model","created":1700000000,"owned_by":"nvidia","name":"Poolside Laguna XS 2.1 (Free)","description":"Poolside Laguna XS 2.1 hosted free by NVIDIA. Fast compact coding model (~161 tok/s).","context_window":131072,"max_output":16384,"categories":["chat","coding"],"billing_mode":"free","available":false,"pricing":{"input":0,"output":0}},{"id":"poolside/laguna-s-2.1","object":"model","created":1700000000,"owned_by":"poolside","name":"Laguna S 2.1","description":"Poolside's Laguna S 2.1 — 118B open-weight coding model, 1M context, very cheap per token.","context_window":1048576,"max_output":131072,"categories":["chat","coding"],"billing_mode":"paid","available":true,"pricing":{"input":0.09,"output":0.18}},{"id":"mistral/mistral-large-4","object":"model","created":1700000000,"owned_by":"mistral","name":"Mistral Large 4","description":"Mistral's flagship — multimodal reasoning model for coding and agentic work. 512K context, image input.","context_window":524288,"max_output":262144,"categories":["chat","reasoning","coding","vision"],"billing_mode":"paid","available":true,"pricing":{"input":1.36,"output":4.18}},{"id":"nvidia/muse-glimmer-30b","object":"model","created":1700000000,"owned_by":"nvidia","name":"Muse Glimmer 30B (Free)","description":"Meta's Muse Glimmer 30B — Apache 2.0, 29.6B dense, hosted free by NVIDIA. Meta's open line after Llama.","context_window":131072,"max_output":16384,"categories":["chat","reasoning","coding"],"billing_mode":"free","available":true,"pricing":{"input":0,"output":0}},{"id":"openai/gpt-image-1","object":"model","created":1700000000,"owned_by":"openai","name":"GPT Image 1","description":"Native image generation in GPT-4o","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.021,"transaction_fee":0.001}},{"id":"openai/gpt-image-2","object":"model","created":1700000000,"owned_by":"openai","name":"ChatGPT Images 2.0","description":"OpenAI's GPT Image 2 — reasoning-driven image generation with multilingual text rendering, character consistency, and high-fidelity edits","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.063,"transaction_fee":0.001}},{"id":"openai/gpt-image-2.5-flare","object":"model","created":1700000000,"owned_by":"openai","name":"GPT Image 2.5 Flare","description":"OpenAI GPT Image 2.5 fast model for high-quality everyday image generation","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.294,"transaction_fee":0.001}},{"id":"openai/gpt-image-2.5-sunburst","object":"model","created":1700000000,"owned_by":"openai","name":"GPT Image 2.5 Sunburst","description":"OpenAI GPT Image 2.5 most capable model for image generation and high-precision editing","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.294,"transaction_fee":0.001}},{"id":"google/nano-banana","object":"model","created":1700000000,"owned_by":"google","name":"Nano Banana","description":"Google's Gemini 2.5 Flash image generation - fast and efficient","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.0525,"transaction_fee":0.001}},{"id":"google/nano-banana-2","object":"model","created":1700000000,"owned_by":"google","name":"Nano Banana 2","description":"Google's Gemini 3.1 Flash image generation - pro-level quality at Flash speed","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.0945,"transaction_fee":0.001}},{"id":"google/nano-banana-pro","object":"model","created":1700000000,"owned_by":"google","name":"Nano Banana Pro","description":"Google's Gemini 3 Pro image generation - highest quality up to 4K","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.105,"transaction_fee":0.001}},{"id":"xai/grok-imagine-image","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Imagine","description":"xAI's Grok Imagine image generation. Fast, 300 RPM.","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.021,"transaction_fee":0.001}},{"id":"xai/grok-imagine-image-2.0","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Imagine 2.0","description":"xAI's Grok Imagine 2.0 image generation. Sits between Grok Imagine and the Pro quality tier on price.","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.042,"transaction_fee":0.001}},{"id":"xai/grok-imagine-image-pro","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Imagine Pro","description":"xAI's premium Grok Imagine image generation (quality tier). Higher quality, 30 RPM.","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.0525,"transaction_fee":0.001}},{"id":"bytedance/seedream-5-pro","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedream 5.0 Pro","description":"ByteDance's Seedream 5.0 Pro — flagship image generation and editing, up to 4K-class resolution with reference-image support","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.04725,"transaction_fee":0.001}},{"id":"zai/cogview-4","object":"model","created":1700000000,"owned_by":"zai","name":"CogView-4","description":"Zhipu AI's CogView-4 image generation model — high quality, supports up to 1440x1440","categories":["image"],"billing_mode":"per_image","pricing":{"per_image":0.01575,"transaction_fee":0.001}},{"id":"minimax/music-2.5+","object":"model","created":1700000000,"owned_by":"minimax","name":"MiniMax Music 2.5+","description":"MiniMax's flagship music generation model. Supports lyrics, instrumental, and style prompts. ~3 min output.","categories":["music"],"billing_mode":"per_track","pricing":{"per_track":0.1575,"transaction_fee":0.001}},{"id":"elevenlabs/flash-v2.5","object":"model","created":1700000000,"owned_by":"elevenlabs","name":"ElevenLabs Flash v2.5","description":"Ultra-low-latency (~75ms) speech synthesis for real-time voice agents. 32 languages.","categories":["speech","tts"],"billing_mode":"per_character","pricing":{"per_1k_chars":0.0525,"transaction_fee":0.001,"max_input_chars":40000}},{"id":"elevenlabs/turbo-v2.5","object":"model","created":1700000000,"owned_by":"elevenlabs","name":"ElevenLabs Turbo v2.5","description":"Balanced quality and latency (~250ms) for interactive use cases. 32 languages.","categories":["speech","tts"],"billing_mode":"per_character","pricing":{"per_1k_chars":0.0525,"transaction_fee":0.001,"max_input_chars":40000}},{"id":"elevenlabs/multilingual-v2","object":"model","created":1700000000,"owned_by":"elevenlabs","name":"ElevenLabs Multilingual v2","description":"Highest-consistency voice for long-form narration, audiobooks, and voiceover. 29 languages.","categories":["speech","tts"],"billing_mode":"per_character","pricing":{"per_1k_chars":0.105,"transaction_fee":0.001,"max_input_chars":10000}},{"id":"elevenlabs/v3","object":"model","created":1700000000,"owned_by":"elevenlabs","name":"ElevenLabs v3","description":"Maximum expressiveness and emotional range for creative applications. 70+ languages.","categories":["speech","tts"],"billing_mode":"per_character","pricing":{"per_1k_chars":0.105,"transaction_fee":0.001,"max_input_chars":5000}},{"id":"bytedance/seed-audio-1.0","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seed Audio 1.0","description":"ByteDance's Seed Audio 1.0 — prompt-directed audio creation: describe the voice, emotion, and sound staging in natural language. Up to 120s output, mp3/wav. Billed by audio duration ($0.003/second, estimated from input length).","categories":["speech","tts"],"billing_mode":"per_character","pricing":{"per_1k_chars":0.315,"transaction_fee":0.001,"max_input_chars":3000,"max_output_seconds":120}},{"id":"elevenlabs/sound-effects","object":"model","created":1700000000,"owned_by":"elevenlabs","name":"ElevenLabs Sound Effects","description":"Generate cinematic sound effects and audio textures from a text prompt (up to 22s).","categories":["sound_effect"],"billing_mode":"per_generation","pricing":{"per_generation":0.0525,"transaction_fee":0.001,"max_duration_seconds":22}},{"id":"xai/grok-imagine-video","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Imagine Video","description":"xAI's Grok Imagine video generation. Text or image to video, configurable 1–15s clips. $0.05/sec at 480p (default), $0.07/sec at 720p — official per-second rates, plus a flat $0.001 per generation.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.05,"per_call_surcharge":0.001,"transaction_fee":0.001,"default_duration_seconds":8,"max_duration_seconds":15}},{"id":"xai/grok-imagine-video-1.5","object":"model","created":1700000000,"owned_by":"xai","name":"Grok Imagine Video 1.5","description":"xAI's flagship Grok Imagine Video 1.5 — text or image to video with native synced audio, 1–15s clips. $0.08/sec at 480p (default), $0.14/sec at 720p, $0.25/sec at 1080p — official per-second rates, plus a flat $0.001 per generation.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.08,"per_call_surcharge":0.001,"transaction_fee":0.001,"default_duration_seconds":8,"max_duration_seconds":15}},{"id":"bytedance/seedance-1.5-pro","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedance 1.5 Pro","description":"ByteDance Seedance 1.5 Pro — budget text/image-to-video at 720p with synced audio (t2v), 5s default. Does NOT support RealFace assets.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.070783146,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":5,"max_duration_seconds":12}},{"id":"bytedance/seedance-2.0-fast","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedance 2.0 Fast","description":"ByteDance Seedance 2.0 Fast — fast video at 720p with synced audio (t2v), 5s default. ~60-80s to generate. Supports BytePlus RealFace assets — see /docs/video/real-person-ip for enrollment.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.165160674,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":5,"max_duration_seconds":15}},{"id":"bytedance/seedance-2.0-mini","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedance 2.0 Mini","description":"ByteDance Seedance 2.0 Mini — 720p video with synced audio at half the flagship rate, 5s default. 480p and 720p (no 1080p/4K). Supports BytePlus RealFace assets — see /docs/video/real-person-ip for enrollment.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.07971075,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":5,"max_duration_seconds":15}},{"id":"bytedance/seedance-2.0","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedance 2.0 Pro","description":"ByteDance Seedance 2.0 Pro — premium quality text/image-to-video at 720p with synced audio (t2v), 5s default. Supports BytePlus RealFace assets — see /docs/video/real-person-ip for enrollment.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.22709592675,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":5,"max_duration_seconds":15}},{"id":"bytedance/seedance-2.5","object":"model","created":1700000000,"owned_by":"bytedance","name":"Seedance 2.5","description":"ByteDance Seedance 2.5 — Long-form video up to 30s at 720p, with first/last-frame control, up to 30 reference images, and reference video/audio clips up to 30s each (billed per reference second). For 1080p or 4K use Seedance 2.0 Pro.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.31557485925,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":5,"max_duration_seconds":30}},{"id":"azure/sora-2","object":"model","created":1700000000,"owned_by":"azure","name":"Sora 2","description":"OpenAI Sora 2 via Azure AI Foundry — text-to-video AND image-to-video at 720p with synchronized audio. 4s default; 4, 8, or 12s. Portrait or landscape. Image-to-video takes a non-human reference image (human faces are rejected upstream — use Seedance + RealFace for real people). $0.10/sec.","categories":["video"],"billing_mode":"per_second","pricing":{"per_second":0.105,"per_call_surcharge":0,"transaction_fee":0.001,"default_duration_seconds":4,"max_duration_seconds":12}}],"network":"mainnet","networkName":"Base"}