{"object":"list","data":[{"id":"claude-opus-4-6","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","display_name":"Claude Opus 4.6","quality_index":53.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"claude-opus-4-7","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","display_name":"Claude Opus 4.7","quality_index":54.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"claude-opus-4-8","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Anthropic flagship model, May 28 2026. Best coding, agentic tasks, honesty.","display_name":"Claude Opus 4.8","quality_index":55.7,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"claude-sonnet-4-6","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75},"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","display_name":"Claude Sonnet 4.6","quality_index":47.2,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":1.8,"output":9.0,"cache_read":0.18,"cache_write":2.25}},{"id":"claude-sonnet-5","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":2.0,"output":10.0,"cache_read":0.2,"cache_write":2.5},"display_name":"Claude Sonnet 5","quality_index":53.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":1.2,"output":6.0,"cache_read":0.12,"cache_write":1.5}},{"id":"deepseek-v4-flash","object":"model","created":0,"is_free":false,"context_window":1048576,"max_output_tokens":384000,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0.0},"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","display_name":"DeepSeek V4 Flash","quality_index":40.3,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.084,"output":0.168,"cache_read":0.0017,"cache_write":0.0}},{"id":"deepseek-v4-pro","object":"model","created":0,"is_free":false,"context_window":1048576,"max_output_tokens":384000,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0.0},"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","display_name":"DeepSeek V4 Pro","quality_index":44.3,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.261,"output":0.522,"cache_read":0.0022,"cache_write":0.0}},{"id":"fable-5","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":10.0,"output":50.0,"cache_read":1.0,"cache_write":12.5},"description":"Claude Fable 5 alias","display_name":"Claude Fable 5","supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":6.0,"output":30.0,"cache_read":0.6,"cache_write":7.5}},{"id":"gemini-3.1-pro-preview","object":"model","created":0,"is_free":false,"context_window":1048576,"max_output_tokens":65536,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":2.0,"output":12.0,"cache_read":0.2,"cache_write":0.0},"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","display_name":"Gemini 3.1 Pro Preview","quality_index":46.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":1.2,"output":7.2,"cache_read":0.12,"cache_write":0.0}},{"id":"gemini-3.5-flash","object":"model","created":0,"is_free":false,"context_window":1048576,"max_output_tokens":65536,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":1.5,"output":9.0,"cache_read":0.15,"cache_write":0.0},"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","display_name":"Gemini 3.5 Flash","quality_index":50.2,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.9,"output":5.4,"cache_read":0.09,"cache_write":0.0}},{"id":"gemma-4-31b","object":"model","created":0,"is_free":false,"context_window":262144,"max_output_tokens":8192,"reasoning":false,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.12,"output":0.35,"cache_read":0.09,"cache_write":0.0},"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","display_name":"Gemma 4 31B (free)","supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.072,"output":0.21,"cache_read":0.054,"cache_write":0.0}},{"id":"glm-5.2","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":131072,"reasoning":false,"supports_vision":false,"supports_tools":true,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0.0},"tags":["coding","glm","zai"],"description":"Z.ai's GLM-5.2 — strong open-weight model for coding and agentic tasks.","display_name":"GLM-5.2","quality_index":51.1,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.84,"output":2.64,"cache_read":0.156,"cache_write":0.0}},{"id":"gpt-5.4-mini","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.0},"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","display_name":"GPT-5.4 Mini","quality_index":40.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.45,"output":2.7,"cache_read":0.045,"cache_write":0.0}},{"id":"gpt-5.5","object":"model","created":0,"is_free":false,"context_window":1050000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":30.0,"cache_read":0.5,"cache_write":0.0},"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","display_name":"GPT-5.5","quality_index":54.8,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":3.0,"output":18.0,"cache_read":0.3,"cache_write":0.0}},{"id":"gpt-5.6-luna","object":"model","created":0,"is_free":false,"context_window":1050000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":1.0,"output":6.0,"cache_read":0.1,"cache_write":0.0},"display_name":"GPT-5.6 Luna","quality_index":42.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.6,"output":3.6,"cache_read":0.06,"cache_write":0.0}},{"id":"gpt-5.6-sol","object":"model","created":0,"is_free":false,"context_window":1050000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":30.0,"cache_read":0.5,"cache_write":0.0},"display_name":"GPT-5.6 Sol","quality_index":56.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":3.0,"output":18.0,"cache_read":0.3,"cache_write":0.0}},{"id":"gpt-5.6-terra","object":"model","created":0,"is_free":false,"context_window":1050000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":2.5,"output":15.0,"cache_read":0.25,"cache_write":0.0},"display_name":"GPT-5.6 Terra","quality_index":54.8,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":1.5,"output":9.0,"cache_read":0.15,"cache_write":0.0}},{"id":"gpt-oss-120b","object":"model","created":0,"is_free":false,"context_window":131072,"max_output_tokens":65536,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.04,"output":0.18,"cache_read":0.0,"cache_write":0.0},"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","display_name":"GPT-OSS 120B","supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.024,"output":0.108,"cache_read":0.0,"cache_write":0.0}},{"id":"gpt-oss-20b","object":"model","created":0,"is_free":false,"context_window":131072,"max_output_tokens":131072,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.03,"output":0.14,"cache_read":0.0,"cache_write":0.0},"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","display_name":"GPT-OSS 20B","supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.018,"output":0.084,"cache_read":0.0,"cache_write":0.0}},{"id":"grok-4.3","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":16384,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0.0},"description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","display_name":"xAI: Grok 4.3","quality_index":37.6,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.75,"output":1.5,"cache_read":0.12,"cache_write":0.0}},{"id":"kimi-k2.6","object":"model","created":0,"is_free":false,"context_window":262144,"max_output_tokens":262144,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":0.95,"output":4.0,"cache_read":0.16,"cache_write":0.0},"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","display_name":"Kimi K2.6","quality_index":42.8,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.57,"output":2.4,"cache_read":0.096,"cache_write":0.0}},{"id":"kimi-k2.7-code","object":"model","created":0,"is_free":false,"context_window":262144,"max_output_tokens":131072,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":0.95,"output":4.0,"cache_read":0.19,"cache_write":0.0},"tags":["coding","kimi","moonshot"],"description":"Moonshot's Kimi K2.7, tuned for long-horizon coding and agentic workflows.","display_name":"Kimi K2.7 Code","quality_index":42.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.57,"output":2.4,"cache_read":0.114,"cache_write":0.0}},{"id":"minimax-m3","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":0.0},"description":"Frontier multimodal coding model, 1M context, MSA attention, May 31 2026","display_name":"MiniMax M3","quality_index":44.4,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.36,"output":1.44,"cache_read":0.072,"cache_write":0.0}},{"id":"nemotron-3-ultra","object":"model","created":0,"is_free":false,"context_window":262144,"max_output_tokens":16384,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.5,"output":2.2,"cache_read":0.0,"cache_write":0.0},"description":"NVIDIA Nemotron 3 Ultra — large reasoning model for agentic tasks.","display_name":"Nemotron 3 Ultra","quality_index":37.8,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.3,"output":1.32,"cache_read":0.0,"cache_write":0.0}},{"id":"qwen3.5-397b","object":"model","created":0,"is_free":false,"context_window":262144,"max_output_tokens":32768,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.6,"output":3.6,"cache_read":0.0,"cache_write":0.0},"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","display_name":"Qwen3.5 397B A17B","quality_index":33.7,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.36,"output":2.16,"cache_read":0.0,"cache_write":0.0}},{"id":"qwen3.7-max","object":"model","created":0,"is_free":false,"context_window":1048576,"max_output_tokens":65536,"reasoning":true,"supports_vision":false,"supports_tools":true,"pricing":{"input":1.25,"output":3.75,"cache_read":0.0,"cache_write":0.0},"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","display_name":"Qwen 3.7 Max","quality_index":46.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.75,"output":2.25,"cache_read":0.0,"cache_write":0.0}},{"id":"solar-pro-3","object":"model","created":0,"is_free":false,"context_window":128000,"max_output_tokens":16384,"reasoning":false,"supports_vision":false,"supports_tools":true,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.0},"description":"Upstage Solar Pro 3 — efficient model for general-purpose tasks.","display_name":"Solar Pro 3","supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice"],"architecture":{"input_modalities":["text"],"output_modalities":["text"]},"discount_pct":40.0,"effective_pricing":{"input":0.09,"output":0.36,"cache_read":0.009,"cache_write":0.0}},{"id":"claude-opus-4.6","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","display_name":"Claude Opus 4.6","quality_index":53.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-opus-4-6","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"claude-opus-4.7","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","display_name":"Claude Opus 4.7","quality_index":54.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-opus-4-7","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"gpt-5.5(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":16384,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":30.0,"cache_read":0.5,"cache_write":0.0},"description":"Pi 400K profile","display_name":"GPT-5.5","quality_index":54.8,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"gpt-5.5","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":18.0,"cache_read":0.3,"cache_write":0.0}},{"id":"opus-4.6(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":16384,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Pi 400K profile","display_name":"Claude Opus 4.6","quality_index":53.0,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-opus-4-6","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"opus-4.7(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":16384,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Pi 400K profile","display_name":"Claude Opus 4.7","quality_index":54.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-opus-4-7","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"opus-4.8(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":5.0,"output":25.0,"cache_read":0.5,"cache_write":6.25},"description":"Pi 400K profile","display_name":"Claude Opus 4.8","quality_index":55.7,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-opus-4-8","discount_pct":40.0,"effective_pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75}},{"id":"sonnet-4.6(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":16384,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":3.0,"output":15.0,"cache_read":0.3,"cache_write":3.75},"description":"Pi 400K profile","display_name":"Claude Sonnet 4.6","quality_index":47.2,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-sonnet-4-6","discount_pct":40.0,"effective_pricing":{"input":1.8,"output":9.0,"cache_read":0.18,"cache_write":2.25}},{"id":"sonnet-5","object":"model","created":0,"is_free":false,"context_window":1000000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":2.0,"output":10.0,"cache_read":0.2,"cache_write":2.5},"description":"Claude Sonnet 5","display_name":"Claude Sonnet 5","quality_index":53.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-sonnet-5","discount_pct":40.0,"effective_pricing":{"input":1.2,"output":6.0,"cache_read":0.12,"cache_write":1.5}},{"id":"sonnet-5(400k)","object":"model","created":0,"is_free":false,"context_window":400000,"max_output_tokens":128000,"reasoning":true,"supports_vision":true,"supports_tools":true,"pricing":{"input":2.0,"output":10.0,"cache_read":0.2,"cache_write":2.5},"description":"Claude Sonnet 5 (400K)","display_name":"Claude Sonnet 5","quality_index":53.5,"supported_parameters":["messages","temperature","top_p","stream","tools","tool_choice","reasoning","reasoning_effort","image_url"],"architecture":{"input_modalities":["text","image"],"output_modalities":["text"]},"alias_of":"claude-sonnet-5","discount_pct":40.0,"effective_pricing":{"input":1.2,"output":6.0,"cache_read":0.12,"cache_write":1.5}}]}