Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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: long code refactors, front-end and visual...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Anthropic: Claude Sonnet 4anthropic/claude-sonnet-4 | 200K | $3 | $15 | — | |||
| grok-4.20-reasoning-latestxai/grok-4.20-reasoning-latest | 1M | $1.25 | $2.5 | — | |||
| grok-4.20-non-reasoningxai/grok-4.20-non-reasoning | 1M | $1.25 | $2.5 | — | |||
| Qwen/Qwen3.5-27Bdeepinfra/qwen/qwen3.5-27b | 262.144K | $0.26 | $2.6 | — | |||
| Qwen/Qwen3.6-35B-A3Bdeepinfra/qwen/qwen3.6-35b-a3b | 262.144K | $0.1 | $0.95 | — | |||
| grok-4.20-non-reasoning-latestxai/grok-4.20-non-reasoning-latest | 1M | $1.25 | $2.5 | — | |||
| mistral-medium-3.5mistral/mistral-medium-3.5 | 262.144K | $1.5 | $7.5 | — | |||
| mistral-vibe-cli-latestmistral/mistral-vibe-cli-latest | 262.144K | $1.5 | $7.5 | — | |||
| SpaceXAI: Grok 4.3x-ai/grok-4.3 | 1M | $1.25 | $2.5 | — | |||
| anthropic/claude-opus-5deepinfra/anthropic/claude-opus-5 | 1M | $5 | $25 | — | |||
| thinkingmachines/Inklingdeepinfra/thinkingmachines/inkling | 524.288K | $0.95 | $4.05 | — | |||
| moonshotai/Kimi-K2.6deepinfra/moonshotai/kimi-k2.6 | 262.144K | $0.75 | $3.5 | — | |||
| deepseek-ai/DeepSeek-V4-Pro-0813deepinfra/deepseek-ai/deepseek-v4-pro-0813 | 1.04858M | $1.3 | $2.6 | — | |||
| Qwen/Qwen3.7-Maxdeepinfra/qwen/qwen3.7-max | 256K | $2.5 | $7.5 | — | |||
| ByteDance/Seed-2.0-minideepinfra/bytedance/seed-2.0-mini | 256K | $0.1 | $0.4 | — | |||
| mistral-vibe-cli-with-toolsmistral/mistral-vibe-cli-with-tools | 262.144K | $1.5 | $7.5 | — | |||
| Qwen/Qwen3.8-2.4T-A95Bdeepinfra/qwen/qwen3.8-2.4t-a95b | 262.144K | $2 | $6 | — | |||
| MiniMaxAI/MiniMax-M3deepinfra/minimaxai/minimax-m3 | 524.288K | $0.28 | $1.1 | — | |||
| google/gemini-3.1-flash-litedeepinfra/google/gemini-3.1-flash-lite | 1M | $0.25 | $1.5 | — | |||
| google/gemini-3.7-flashdeepinfra/google/gemini-3.7-flash | 1M | $0.75 | $3.75 | — | |||
| stepfun-ai/Step-3.7-Flashdeepinfra/stepfun-ai/step-3.7-flash | 262.144K | $0.2 | $1.15 | — | |||
| Qwen/Qwen3.5-35B-A3Bdeepinfra/qwen/qwen3.5-35b-a3b | 262.144K | $0.14 | $1 | — | |||
| ByteDance/Seed-1.8deepinfra/bytedance/seed-1.8 | 256K | $0.25 | $2 | — | |||
| OpenAI: o4 Mini High (batch)openai/o4-mini-high:batch | 200K | $0.55 | $2.2 | — | |||
| tencent/Hy3deepinfra/tencent/hy3 | 262.144K | $0.14 | $0.58 | — | |||
| ByteDance/Seed-2.0-codedeepinfra/bytedance/seed-2.0-code | 256K | $0.5 | $3 | — | |||
| ByteDance/Seed-2.0-prodeepinfra/bytedance/seed-2.0-pro | 256K | $0.5 | $3 | — | |||
| zai-org/GLM-5deepinfra/zai-org/glm-5 | 202.752K | $0.6 | $2.08 | — | |||
| nvidia/Nemotron-3-Nano-30B-A3Bdeepinfra/nvidia/nemotron-3-nano-30b-a3b | 262.144K | $0.05 | $0.2 | — | |||
| moonshotai/Kimi-K2.7-Codedeepinfra/moonshotai/kimi-k2.7-code | 262.144K | $0.68 | $3.4 | — | |||
| anthropic/claude-sonnet-5deepinfra/anthropic/claude-sonnet-5 | 1M | $2 | $10 | — | |||
| mistral-vibe-cli-fastmistral/mistral-vibe-cli-fast | 262.144K | $0.15 | $0.6 | — | |||
| Anthropic: Claude Opus 4.6 (batch)anthropic/claude-opus-4.6:batch | 1M | $2.5 | $12.5 | — | |||
| Qwen/Qwen3.5-397B-A17Bdeepinfra/qwen/qwen3.5-397b-a17b | 262.144K | $0.45 | $3 | — | |||
| mistral-code-agent-latestmistral/mistral-code-agent-latest | 256K | $0.4 | $2 | — | |||
| labs-leanstral-1-5-1mistral/labs-leanstral-1-5-1 | 262.144K | — | — | — | |||
| deepseek-ai/DeepSeek-V4-Flash-0731deepinfra/deepseek-ai/deepseek-v4-flash-0731 | 1.04858M | $0.08 | $0.18 | — | |||
| Qwen/Qwen3.8-Maxdeepinfra/qwen/qwen3.8-max | 256K | $1.65 | $4.951 | — | |||
| anthropic/claude-fable-5deepinfra/anthropic/claude-fable-5 | 1M | $10 | $50 | — | |||
| Anthropic: Claude Fable 5.1 (batch)anthropic/claude-fable-5.1:batch | 1M | $5 | $25 | — | |||
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bdeepinfra/nvidia/nvidia-nemotron-3-ultra-550b-a55b | 262.144K | $0.5 | $2.2 | — | |||
| Qwen/Qwen3.5-122B-A10Bdeepinfra/qwen/qwen3.5-122b-a10b | 262.144K | $0.29 | $2.4 | — | |||
| zai-org/GLM-5.1deepinfra/zai-org/glm-5.1 | 202.752K | $1.05 | $3.5 | — | |||
| accounts/fireworks/models/glm-5p3fireworks_ai/accounts/fireworks/models/glm-5p3 | 1.04858M | $1.4 | $4.4 | — | |||
| deepseek-ai/DeepSeek-V4-Prodeepinfra/deepseek-ai/deepseek-v4-pro | 1.04858M | $1.3 | $2.6 | — | |||
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12Bdeepinfra/nvidia/nvidia-nemotron-3-super-120b-a12b | 262.144K | $0.085 | $0.4 | — | |||
| zai-org/GLM-5.2deepinfra/zai-org/glm-5.2 | 1.04858M | $0.75 | $2.4 | — | |||
| moonshotai/Kimi-K3deepinfra/moonshotai/kimi-k3 | 1.04858M | $2.85 | $14.25 | — | |||
| anthropic/claude-opus-4-7deepinfra/anthropic/claude-opus-4-7 | 1M | $5 | $25 | — | |||
| Qwen/Qwen3.6-27Bdeepinfra/qwen/qwen3.6-27b | 262.144K | $0.32 | $3.2 | — |