Reasoning models
Reasoning models emit internal chain-of-thought tokens before their final answer. Higher latency, much higher accuracy on hard problems.
50 models in this category. See also the “Best AI reasoning models” ranking with editorial picks and FAQ.
| Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|
| Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5 | Anthropic | 1M Ultra context (1M+) | $2.00 | Standard |
| Anthropic: Claude Sonnet 5 (batch) anthropic/claude-sonnet-5:batch | Anthropic | 1M Ultra context (1M+) | $1.00 | Standard |
| Google: Gemini 2.5 Flash google/gemini-2.5-flash | 1.0M Ultra context (1M+) | $0.30 | Budget | |
| Google: Gemini 2.5 Flash (batch) google/gemini-2.5-flash:batch | 1.0M Ultra context (1M+) | $0.15 | Budget | |
| Google: Gemini 2.5 Flash Lite Preview 09-2025 google/gemini-2.5-flash-lite-preview-09-2025 | 1.0M Ultra context (1M+) | $0.10 | Budget | |
| Google: Gemini 2.5 Pro google/gemini-2.5-pro | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| Google: Gemini 2.5 Pro (batch) google/gemini-2.5-pro:batch | 1.0M Ultra context (1M+) | $0.63 | Budget | |
| Google: Gemini 2.5 Pro Preview 05-06 google/gemini-2.5-pro-preview-05-06 | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| Google: Gemini 2.5 Pro Preview 06-05 google/gemini-2.5-pro-preview | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| Google: Gemini 3 Flash Preview google/gemini-3-flash-preview | 1.0M Ultra context (1M+) | $0.50 | Budget | |
| Google: Gemini 3 Flash Preview (batch) google/gemini-3-flash-preview:batch | 1.0M Ultra context (1M+) | $0.25 | Budget | |
| Qwen: Qwen Plus 0728 (thinking) qwen/qwen-plus-2025-07-28:thinking | Qwen | 1M Ultra context (1M+) | $0.26 | Budget |
| Qwen: Qwen3.8 27B qwen/qwen3.8-27b | Qwen | 1M Ultra context (1M+) | $0.04 | Budget |
| Thinking Machines: Inkling (free) thinkingmachines/inkling:free | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| Thinking Machines: Inkling Small (free) thinkingmachines/inkling-small:free | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| Anthropic: Claude 3.7 Sonnet (thinking) anthropic/claude-3.7-sonnet:thinking | Anthropic | 200K Long context (128K+) | $3.00 | Standard |
| Arcee AI: Trinity Large Thinking arcee-ai/trinity-large-thinking | Arcee Ai | 262K Long context (128K+) | $0.25 | Budget |
| ByteDance Seed: Seed 1.6 bytedance-seed/seed-1.6 | Bytedance Seed | 262K Long context (128K+) | $0.25 | Budget |
| ByteDance Seed: Seed 1.6 Flash bytedance-seed/seed-1.6-flash | Bytedance Seed | 262K Long context (128K+) | $0.07 | Budget |
| Google: Gemma 4 31B google/gemma-4-31b-it | 262K Long context (128K+) | $0.09 | Budget | |
| Google: Gemma 4 31B (batch) google/gemma-4-31b-it:batch | 262K Long context (128K+) | $0.39 | Budget | |
| Google: Gemma 4 31B (free) google/gemma-4-31b-it:free | 262K Long context (128K+) | $0.00 | Budget | |
| inclusionAI: Ring-2.6-1T inclusionai/ring-2.6-1t | Inclusionai | 262K Long context (128K+) | $0.07 | Budget |
| MoonshotAI: Kimi K2 Thinking moonshotai/kimi-k2-thinking | Moonshotai | 262K Long context (128K+) | $0.60 | Budget |
| OpenAI: o1 openai/o1 | OpenAI | 200K Long context (128K+) | $15.00 | Premium |
| OpenAI: o1 (batch) openai/o1:batch | OpenAI | 200K Long context (128K+) | $7.50 | Premium |
| OpenAI: o1-pro openai/o1-pro | OpenAI | 200K Long context (128K+) | $150.00 | Premium |
| OpenAI: o1-pro (batch) openai/o1-pro:batch | OpenAI | 200K Long context (128K+) | $75.00 | Premium |
| OpenAI: o3 Pro openai/o3-pro | OpenAI | 200K Long context (128K+) | $20.00 | Premium |
| OpenAI: o3 Pro (batch) openai/o3-pro:batch | OpenAI | 200K Long context (128K+) | $10.00 | Premium |
| Qwen: Qwen3 Max Thinking qwen/qwen3-max-thinking | Qwen | 262K Long context (128K+) | $0.78 | Budget |
| Qwen: Qwen3 Next 80B A3B Thinking qwen/qwen3-next-80b-a3b-thinking | Qwen | 262K Long context (128K+) | $0.15 | Budget |
| Qwen: Qwen3 VL 30B A3B Thinking qwen/qwen3-vl-30b-a3b-thinking | Qwen | 262K Long context (128K+) | $0.29 | Budget |
| Qwen: Qwen3.8 27B (free) qwen/qwen3.8-27b:free | Qwen | 262K Long context (128K+) | $0.00 | Budget |
| Thinking Machines: Inkling thinkingmachines/inkling | Thinkingmachines | 524K Long context (128K+) | $1.00 | Standard |
| Thinking Machines: Inkling (batch) thinkingmachines/inkling:batch | Thinkingmachines | 524K Long context (128K+) | $1.00 | Standard |
| Thinking Machines: Inkling Small thinkingmachines/inkling-small | Thinkingmachines | 524K Long context (128K+) | $0.45 | Budget |
| Thinking Machines: Inkling Small (batch) thinkingmachines/inkling-small:batch | Thinkingmachines | 524K Long context (128K+) | $0.50 | Budget |
| Xiaomi: MiMo-V2-Flash xiaomi/mimo-v2-flash | Xiaomi | 262K Long context (128K+) | $0.09 | Budget |
| Baidu: ERNIE 4.5 21B A3B Thinking baidu/ernie-4.5-21b-a3b-thinking | Baidu | 131K Long context (128K+) | $0.07 | Budget |
| DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 | DeepSeek | 164K Long context (128K+) | $0.25 | Budget |
| DeepSeek: DeepSeek V3.1 Terminus (exacto) deepseek/deepseek-v3.1-terminus:exacto | DeepSeek | 164K Long context (128K+) | $0.21 | Budget |
| Qwen: Qwen3 32B qwen/qwen3-32b | Qwen | 131K Long context (128K+) | $0.08 | Budget |
| Qwen: Qwen3 8B qwen/qwen3-8b | Qwen | 131K Long context (128K+) | $0.12 | Budget |
| Nous: Hermes 4 405B nousresearch/hermes-4-405b | Nousresearch | 131K Long context (128K+) | $1.00 | Standard |
| NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 nvidia/llama-3.1-nemotron-ultra-253b-v1 | Nvidia | 131K Long context (128K+) | $0.60 | Budget |
| NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 nvidia/llama-3.3-nemotron-super-49b-v1.5 | Nvidia | 131K Long context (128K+) | $0.10 | Budget |
| Perplexity: Sonar Reasoning Pro perplexity/sonar-reasoning-pro | Perplexity | 128K Long context (128K+) | $2.00 | Standard |
| Qwen: Qwen3 235B A22B qwen/qwen3-235b-a22b | Qwen | 131K Long context (128K+) | $0.46 | Budget |
| Qwen: Qwen3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 128K Long context (128K+) | $0.45 | Budget |