Reasoning models
296 models that reason step by step before they answer, for math, code and multi-step problems.
/
 Doubao Seed CharacterByteDancePrompt cachingJSON+3 | $0.295/1Mvia ZenMux | 256K | $0.118/1M | $0.295/1M | — | — | |
| Doubao-Seed-1.8ByteDancePrompt cachingReasoning+2 | $0.28/1Mvia ZenMux | 256K | $0.11/1M | $0.28/1M | — | — | |
 Ember-1FireworksPrompt cachingJSON+3 | $15/1Mvia Fireworks AI | 1.05M | $3/1M | $15/1M | — | — | |
 ERNIE 5.0BaiduPrompt cachingJSON+3 | $3.29/1Mvia AIHubMix | 183K | $0.822/1M | $3.29/1M | — | — | |
| ERNIE 5.0 Thinking ExpBaiduPrompt cachingReasoning | $3.29/1Mvia AIHubMix | 119K | $0.822/1M | $3.29/1M | — | — | |
| ERNIE X1 TurboBaiduJSONReasoning+1 | $0.544/1Mvia AIHubMix | 51K | $0.136/1M | $0.544/1M | — | — | |
| ERNIE X1.1 PreviewBaiduJSONReasoning+1 | $0.544/1Mvia AIHubMix | 119K | $0.136/1M | $0.544/1M | — | — | |
| RFlint 40B FreeRecursiveJSONReasoning+1 | Free/1Mvia OpenCode | 262K | Free/1M | Free/1M | — | — | |
 Fugu UltraSakana AIPrompt cachingJSON+3 | $30/1Mvia EmpirioLabs AI | 1M | $5/1M | $30/1M | — | — | |
| Fugu Ultra v2.0Sakana AIPrompt cachingJSON+3 | $30/1Mvia EmpirioLabs AI | 1M | $5/1M | $30/1M | — | — | |
 Gemini 2.5 Flash-LiteGooglePrompt cachingJSON+3 | $0.32/1Mvia APIMart | 1.05M | — | $0.40/1M | — | — | |
| Gemini 2.5 Pro Preview 0605GooglePrompt cachingJSON+3 | $3/1Mvia Kie.ai | 1.05M | $0.38/1M | $3/1M | — | — | |
| Gemini 3 Flash PreviewGooglePrompt cachingJSON+3 | $1.50/1Mvia Vertex | 1.05M | — | $3/1M | — | — | |
| Gemini 3 Pro PreviewGooglePrompt cachingJSON+3 | $9.60/1Mvia APIMart | 1.05M | $1.60/1M | $9.60/1M | — | — | |
| Gemini 3.1 Flash LiteGooglePrompt cachingJSON+3 | $1.20/1Mvia CometAPI | 1.05M | — | $1.50/1M | — | — | |
| Gemini 3.1 Flash Lite PreviewGooglePrompt cachingJSON+3 | $1.20/1Mvia APIMart | 1.05M | $0.20/1M | $1.20/1M | 1416 | — | |
| Gemini 3.1 Pro Preview Custom ToolsGooglePrompt cachingJSON+3 | $10.80/1Mvia APIYI | 1.05M | $1.80/1M | $10.80/1M | — | — | |
| Gemini 3.5 FlashGooglePrompt cachingJSON+3 | $2.70/1Mvia Kie.ai | 1.05M | $0.45/1M | $2.70/1M | 1499 | — | |
| Gemini 3.5 Flash LiteGooglePrompt cachingJSON+3 | $2/1Mvia APIMart | 1.05M | — | $2.50/1M | 1435 | — | |
| Gemini 3.6 FlashGooglePrompt cachingJSON+3 | $3/1Mvia CometAPI | 1.05M | $0.75/1M | $3.75/1M | 1538 | — | |
| Gemini 3.7 FlashGooglePrompt cachingJSON+3 | $1.13/1Mvia Kie.ai | 1.05M | $0.225/1M | $1.13/1M | 1591 | — | |
| Gemini Flash LatestGooglePrompt cachingJSON+3 | $3/1Mvia OrcaRouter | — | $0.50/1M | $3/1M | — | — | |
| Gemini Flash Lite LatestGooglePrompt cachingJSON+3 | $1.50/1Mvia OrcaRouter | — | $0.25/1M | $1.50/1M | — | — | |
| Gemini Pro LatestGooglePrompt cachingJSON+3 | $6.90/1Mvia Kenari | 1.05M | $2/1M | $12/1M | 1480 | — | |
| Gemini Robotics-ER 1.6 PreviewGoogleJSONReasoning+2 | $5/1Mvia OrcaRouter | — | $1/1M | $5/1M | — | — | |
 GLM 5 TurboZhipu AIPrompt cachingJSON+2 | $3.19/1Mvia ZenMux | 203K | $0.73/1M | $3.19/1M | — | — | |
| GLM-4.5VZhipu AIMITPrompt caching+4 | $0.822/1Mvia AIHubMix | 66K | $0.60/1M | $1.80/1M | 1333 | — | |
| GLM-4.6V-FlashZhipu AIMITPrompt caching+2 | $0.218/1Mvia ZenMux | 200K | $0.022/1M | $0.218/1M | — | — | |
| GLM-4.7-FlashXZhipu AIPrompt cachingReasoning+1 | $0.40/1Mvia DevPass (LLM Gateway) | 200K | $0.07/1M | $0.40/1M | — | — | |
| GLM-5V-TurboZhipu AIPrompt cachingJSON+3 | $3.10/1Mvia AIHubMix | 200K | $0.704/1M | $3.10/1M | 1438 | — | |
| GPT 5.1 Thinking (Fast)OpenAIPrompt cachingJSON+3 | $20/1Mvia Vercel AI Gateway | 400K | $2.50/1M | $20/1M | — | — | |
| GPT-5 CodexOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | — | — | |
| GPT-5 ProOpenAIJSONReasoning+2 | $96/1Mvia APIMart | 400K | $15/1M | $120/1M | — | — | |
| GPT-5.1OpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1.25/1M | $10/1M | 1443 | — | |
| GPT-5.1 CodexOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | 1337 | — | |
| GPT-5.1 Codex MaxOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | — | — | |
| GPT-5.1 Codex miniOpenAIPrompt cachingJSON+3 | $1.60/1Mvia APIMart | 400K | $0.20/1M | $1.60/1M | 1244 | — | |
| GPT-5.2 CodexOpenAIPrompt cachingJSON+3 | $11.20/1Mvia APIMart | 400K | $1.40/1M | $11.20/1M | 1339 | — | |
| GPT-5.5 ProOpenAIJSONReasoning+2 | $144/1Mvia CometAPI | 1.05M | $30/1M | $180/1M | — | — | |
| GPT-5.6 TerraOpenAIPrompt cachingJSON+3 | $9.60/1Mvia APIMart | 1.05M | $2/1M | $12/1M | 1521 | — | |
| GPT-6 Astra (Fast)OpenAIPrompt cachingJSON+3 | $100/1Mvia Vercel AI Gateway | 1.05M | $20/1M | $100/1M | — | — | |
| GPT-6 Astra Pro ($$$$)OpenAIPrompt cachingJSON+3 | $50/1Mvia OpenRouter | 1.05M | $10/1M | $50/1M | — | — | |
| GPT-6 Luna ProOpenAIPrompt cachingJSON+3 | $0.50/1Mvia OpenRouter | 1.05M | $0.10/1M | $0.50/1M | — | — | |
| GPT-6 Sol ProOpenAIPrompt cachingJSON+3 | $10/1Mvia OpenRouter | 1.05M | $2/1M | $10/1M | — | — | |
| GPT-6.1 Sol ProOpenAIPrompt cachingJSON+3 | $10/1Mvia OpenRouter | 1.05M | $2/1M | $10/1M | — | — | |
| Granite 4.2 8BIBMApache 2.0Prompt caching+3 | $0.25/1Mvia Deep Infra | 131K | $0.06/1M | $0.25/1M | 1319 | — | |
| Grok 3 MinixAIPrompt cachingJSON+2 | $0.50/1Mvia Helicone | 131K | $0.30/1M | $0.50/1M | 1369 | — | |
| Grok 4 Fast Non ReasoningxAIPrompt cachingJSON+2 | $0.50/1Mvia Helicone | 2M | $0.20/1M | $0.50/1M | — | — | |
| Grok 4.1 Fast (Reasoning)xAIPrompt cachingJSON+3 | $0.475/1Mvia Jiekou.AI | 2M | $0.19/1M | $0.475/1M | — | — | |
| Grok 4.20 (Reasoning)xAIPrompt cachingJSON+3 | $2/1Mvia APIMart | 1M | $1.25/1M | $2.50/1M | — | — |
Frequently asked questions
A model trained to work through a problem in intermediate steps, often called thinking, before it answers. It does better on math, coding and planning, at the cost of more tokens and slower replies.
The thinking steps are billed as output tokens, so one answer can use many times the tokens of a direct reply. Compare output prices, and check whether the model lets you limit or switch off its reasoning.
For short lookups, classification, extraction or chat, a regular model is faster and cheaper with little loss in quality. Keep reasoning for problems that really need several steps.
Can't find what you're looking for? Contact us