Available models · Provider routing · Real-time pricing
anthropic/claude-fable-5.1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end generation, and financial…
anthropic/claude-haiku-5.5
Claude Haiku 5.5 is Anthropic's fast, lightweight model for high-volume tasks such as classification, extraction, summarization, customer support, and coding subagents. It accepts text and images and produces text, with…
anthropic/claude-opus-5
Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work.
anthropic/claude-opus-5.5
Claude Opus 5.5 succeeds Claude Opus 5 as Anthropic's flagship for demanding reasoning, coding, and long-horizon agentic work, delivering sharper reasoning and extended output at lower cost.
anthropic/claude-sonnet-5.5
Claude Sonnet 5.5 is Anthropic's fast model for everyday coding, bug fixes, document analysis, and agentic workflows. It accepts text and image inputs and produces text, with a 1,000,000-token context window and up to 1…
deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731 is the generally available, updated post-training release of V4 Flash. Its sparse MoE architecture has 284B total parameters and 13B active parameters. It targets coding, reasoning, and agent work…
deepseek/deepseek-v4-pro-0813
DeepSeek V4 Pro 0813 is an open-weight text reasoning model with a 1.6T-parameter backbone (49B active) and DSpark speculative decoding. It supports a 1,048,576-token context, up to 393,216 output tokens, tool calling,…
deepseek/deepseek-v4.1-flash
DeepSeek V4.1 Flash uses a sparse MoE Causal Encoder-Decoder architecture with 552B total parameters, activating 8B during input processing and 16B during output generation. It natively understands text and images and t…
deepseek/deepseek-v4.1-flash-1017
DeepSeek V4.1 Flash 1017 is an updated multimodal reasoning model for coding, agent workflows and visual understanding. It accepts text and images and generates text, with a 1,048,576-token context window and up to 393,…
moonshotai/kimi-k2.6
Kimi K2.6 is Moonshot AI’s multimodal model for long-running coding, UI generation from visual references, and multi-agent coordination. It supports end-to-end development across languages such as Python, Rust, and Go,…
moonshotai/kimi-k3
Kimi K3 is Moonshot AI's open-weight multimodal reasoning model. Its mixture-of-experts architecture has 2.8 trillion total parameters with 104 billion activated per token, and supports a 1,048,576-token context. It acc…
openai/gpt-5.6-luna
GPT-5.6 Luna is the fast, cost-efficient tier of OpenAI's GPT-5.6 series, built for latency-sensitive interactive applications.
openai/gpt-5.6-sol
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series, delivering the family's strongest reasoning and coding performance for demanding professional work.
openai/gpt-5.6-terra
GPT-5.6 Terra is the balanced tier of OpenAI's GPT-5.6 series, positioned between the flagship Sol and the cost-efficient Luna for general production workloads.
openai/gpt-6-astra
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work, pairing the GPT-6 generation's deepest reasoning with a 1M-token context window.
openai/gpt-6-luna
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol for interactive, latency-sensitive workloads.
openai/gpt-6-sol
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.
openai/gpt-6.1-sol
GPT-6.1 Sol is an upgraded GPT-6 Sol model from OpenAI for agentic coding, computer use, document analysis, and multi-step business workflows. It improves factual reliability and adherence to user intent and explicit re…
qwen/qwen3.8-flash
Qwen3.8 Flash accepts text, images, and video and generates text. It supports a 1,000,000-token context, up to 131,072 output tokens, reasoning, tool calling, and structured outputs.
qwen/qwen3.8-max
Qwen3.8 Max is a 2.4-trillion-parameter MoE model for coding and agent tasks. It accepts text, images, and video, with a 1,000,000-token context and up to 131,072 output tokens.
qwen/qwen3.8-omni-flash
Qwen3.8 Omni Flash understands text, images, audio, and video and produces text. It offers a 1,000,000-token context and up to 131,072 output tokens, with reasoning, tool calling, and implicit caching.
xiaomi/mimo-v2.6-flash
MiMo-V2.6-Flash is the efficient model in Xiaomi's MiMo-V2.6 series, striking the best balance between intelligence, efficiency, and cost. It is a sparse mixture-of-experts model with 309B total parameters and 15B activ…
z-ai/glm-5.2
GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineer…
z-ai/glm-5.3
GLM-5.3 is Z.ai’s text reasoning model for complex software engineering and long-running agent tasks. It improves coding and token efficiency over GLM-5.2. Reasoning is always enabled, with low, high, and max effort lev…
z-ai/glm-5.3-flash
GLM-5.3-Flash is a native multimodal model for efficient coding, visual understanding, and long-running agent tasks. Its hybrid sparse and linear attention architecture reduces compute overhead. It accepts text, images,…
z-ai/glm-5.3-flashx
GLM-5.3-FlashX is the faster serving variant of GLM-5.3-Flash, reaching up to 200 tokens per second. It shares the hybrid sparse and linear attention architecture, with 320B total and 18B active parameters, and accepts…
Try adjusting your search or filters.