Compare 1,306 reasoning models across 95 providers. Find the best chain-of-thought model for math, science, coding, and complex analysis.
The top reasoning models compared side by side.
| Model | Provider | Input $/1M | Output $/1M | Context | Tool Call |
|---|---|---|---|---|---|
| o3 | openai | $10 | $40 | 200K | ✅ |
| o3-mini | openai | $1.1 | $4.4 | 200K | ✅ |
| o4-mini | openai | $1.1 | $4.4 | 200K | ✅ |
| o1 | openai | $15 | $60 | 200K | ✅ |
| o1-mini | openai | $1.5 | $6 | 128K | ✅ |
| o1-pro | openai | $150 | $600 | 200K | ✅ |
| deepseek-r1-distill-llama-70b | cerebras | Free | 131K | ||
| gemini-2.5-pro | deepinfra | $1.25 | $10 | 1M | |
| gemini-2.5-flash | deepinfra | $0.3 | $2.5 | 1M | |
| qwen3-235b-a22b | alibaba | $2 | $8 | ? | ✅ |
Reasoning on a budget — most affordable models with reasoning capability.
| Model | Provider | Input $/1M | Output $/1M | Context | Tool Call |
|---|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K | |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K | |
| gpt-oss-20b | deepinfra | $0.03 | $0.14 | 131K | |
| qwen3.5-4b | deepinfra | $0.03 | $0.15 | 262K | |
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? | ✅ |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K | ✅ |
| gpt-oss-120b | deepinfra | $0.039 | $0.19 | 131K | |
| nvidia-nemotron-nano-9b-v2 | deepinfra | $0.04 | $0.16 | 131K | |
| openai--gpt-oss-20b | novitaai | $0.04 | $0.15 | 131K | |
| nemotron-3-nano-30b-a3b | deepinfra | $0.05 | $0.2 | 262K | |
| gpt-oss-120b | inferencenet | $0.05 | $0.45 | 131K | ✅ |
| Qwen--Qwen3.6-35B-A3B | neuralwatt | $0.05 | $0.1 | ? | ✅ |
| openai--gpt-oss-120b | novitaai | $0.05 | $0.25 | 131K | ✅ |
| qwen3-30b-a3b-fp8 | cloudflare | $0.051 | $0.335 | 40K | ✅ |
| glm-4.7-flash | cloudflare | $0.06 | $0.4 | 131K | ✅ |
33 reasoning models at zero cost — perfect for learning and prototyping.
| Model | Provider | Context | Tool Call |
|---|---|---|---|
| deepseek--deepseek-v4-flash--free | openrouter | 1M | ✅ |
| nvidia--nemotron-3-super-120b-a12b--free | openrouter | 1M | ✅ |
| gemma-4-26b-a4b-it | auriko | 262K | ✅ |
| gemma-4-31b-it | auriko | 262K | ✅ |
| arcee-ai--trinity-large-thinking--free | openrouter | 262K | ✅ |
| google--gemma-4-26b-a4b-it--free | openrouter | 262K | ✅ |
| google--gemma-4-31b-it--free | openrouter | 262K | ✅ |
| nvidia--nemotron-3-nano-omni-30b-a3b-reasoning--free | openrouter | 256K | ✅ |
| minimax--minimax-m2.5--free | openrouter | 204K | ✅ |
| z-ai--glm-5.1 | openrouter | 202K | ✅ |
120 reasoning models you can run locally for full privacy and zero API costs.
| Model | Provider | Context | Tool Call |
|---|---|---|---|
| xiaomi--mimo-v2.5-pro | hpc-ai | 1M | ✅ |
| xiaomi--mimo-v2.5 | hpc-ai | 1M | ✅ |
| deepseek--deepseek-v4-flash | hpc-ai | 1M | ✅ |
| deepseek--deepseek-v4-pro | hpc-ai | 1M | ✅ |
| DeepSeek-V4-Pro | nebius | 1M | ✅ |
| trinity-large-thinking | arcee | 262K | ✅ |
| qwen3-next-80b-a3b-thinking | clarifai | 262K | ✅ |
| gemma-4-26b-a4b-it | cloudflare | 262K | ✅ |
| kimi-k2.5 | cloudflare | 262K | ✅ |
| kimi-k2.6 | cloudflare | 262K | ✅ |
Models with both reasoning and tool calling — the most capable for agentic workflows that need complex planning.
| Model | Provider | Input $/1M | Output $/1M | Context |
|---|---|---|---|---|
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K |
| gpt-oss-120b | inferencenet | $0.05 | $0.45 | 131K |
| Qwen--Qwen3.6-35B-A3B | neuralwatt | $0.05 | $0.1 | ? |
| openai--gpt-oss-120b | novitaai | $0.05 | $0.25 | 131K |
| qwen3-30b-a3b-fp8 | cloudflare | $0.051 | $0.335 | 40K |
| glm-4.7-flash | cloudflare | $0.06 | $0.4 | 131K |
| Nemotron-3-Nano-Omni | nebius | $0.06 | $0.24 | 128K |
| hermes-4-llama-3.1-8b | nousresearch | $0.06 | $0.12 | 131K |
| seed-1.6-flash | bytedance | $0.07 | $0.3 | 262K |
| ring-2.6-1t | inclusionai | $0.07 | $0.62 | 262K |
| zai-org--glm-4.7-flash | novitaai | $0.07 | $0.4 | 200K |
| microsoft-phi-4-mini-reasoning | microsoft | $0.075 | $0.3 | 128K |
| Qwen--Qwen3-32B-TEE | chutes | $0.08 | $0.24 | 40K |
| gpt-oss-120b | clarifai | $0.09 | $0.36 | 131K |
Reasoning models with 128K+ context — for analyzing long documents, large codebases, and complex multi-step problems.
| Model | Provider | Context | Input $/1M | Tool Call |
|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | 262K | $0.01 | |
| qwen3.5-2b | deepinfra | 262K | $0.02 | |
| gpt-oss-20b | deepinfra | 131K | $0.03 | |
| qwen3.5-4b | deepinfra | 262K | $0.03 | |
| qwen--qwen3-4b-fp8 | novitaai | 128K | $0.03 | ✅ |
| gpt-oss-120b | deepinfra | 131K | $0.039 | |
| nvidia-nemotron-nano-9b-v2 | deepinfra | 131K | $0.04 | |
| openai--gpt-oss-20b | novitaai | 131K | $0.04 | |
| nemotron-3-nano-30b-a3b | deepinfra | 262K | $0.05 | |
| gpt-oss-120b | inferencenet | 131K | $0.05 | ✅ |
| openai--gpt-oss-120b | novitaai | 131K | $0.05 | ✅ |
| glm-4.7-flash | cloudflare | 131K | $0.06 | ✅ |
| glm-4.7-flash | deepinfra | 202K | $0.06 | |
| Nemotron-3-Nano-Omni | nebius | 128K | $0.06 | ✅ |
| hermes-4-llama-3.1-8b | nousresearch | 131K | $0.06 | ✅ |
All data is sourced from first-party APIs. Reasoning capability is defined by the provider's own classification — models that use chain-of-thought, extended thinking, or similar techniques. Aggregator providers are excluded from ranking tables to avoid duplicate models.