Models that expose an explicit `<think>` or chain-of-thought trace — DeepSeek-R1, Qwen-QwQ, GLM-Z1. Best for math-heavy, multi-step, or agentic workloads where the reasoning trace is itself valuable. Includes tool-use / function-calling tuned variants.
| Model | Creator | Context | Open weight | Tags |
|---|---|---|---|---|
| Yi-1.5-34B-Chat | 01.AI | 4K | Yes | text-generation · conversational · instruction-following |
| Yi Lightning | 01.AI | 16K | — | chat · reasoning |
| Qwen VL Max | Alibaba Cloud | 131K | Yes | chat · vision · ocr |
| Qwen 2.5 Max | Alibaba Cloud | 33K | — | chat · reasoning · code |
| Qwen3.5-122B-A10B | Alibaba Cloud | 262K | Yes | chat · vision · tool_calling |
| Qwen3.5 397B A17B | Alibaba Cloud | 262K | Yes | chat · reasoning · code |
| Qwen3 72B Instruct | Alibaba | 131K | Yes | chat · reasoning · multilingual |
| Qwen3.8 Flash | Alibaba Cloud | 1000K | — | code · reasoning · vision |
| Qwen3.8 Flash-Next | Alibaba Cloud | 262K | Yes | code · reasoning · vision |
| Qwen3.8 Max | Alibaba Cloud | 1000K | — | code · reasoning · vision |
| Qwen3.8 Omni Flash | Alibaba Cloud | 1000K | — | reasoning · vision · audio_understanding |
| Qwen3.5-122B-A10B | Qwen | 33K | Yes | image-text-to-text · conversational · reasoning |
| Baichuan 4 Turbo | Baichuan Intelligence | 33K | — | chat · reasoning |
| ERNIE 4.0 | Baidu | 8K | — | chat · reasoning · search_integration |
| ERNIE 4.0 Turbo | Baidu | 128K | — | chat · reasoning · long_context |
| Doubao Pro 32K | ByteDance | 33K | — | chat · reasoning · code |
| DeepSeek V3.1 | DeepSeek | 33K | Yes | chat · reasoning · code |
| R1 | DeepSeek | 64K | Yes | reasoning · math · coding |
| DeepSeek V3 | DeepSeek AI | 66K | Yes | reasoning · coding · tool_use |
| DeepSeek V4.1 Flash | DeepSeek | 1000K | Yes | reasoning · code · vision |
| DeepSeek V4 Pro | DeepSeek | 1000K | Yes | chat · reasoning · code |
| LongCat-2.5-Preview | Meituan | 1000K | — | reasoning · coding · tool_use |
| Llama 3.1 405B Instruct | Meta | 131K | Yes | chat · reasoning · code |
| Llama 3.3 70B Instruct | Meta | 131K | Yes | chat · coding · reasoning |
| MiniMax-M3.1-Flash-Preview | MiniMax | 1000K | — | reasoning · coding · tool_use |
| MiniMax-Text-01 | MiniMax | 1000K | Yes | text-generation · conversational · function-calling |
| Mistral Large 2411 | Mistral AI | 131K | Yes | chat · reasoning · code |
| Kimi K2 0711 | Moonshot AI | 131K | Yes | text generation · instruction following · agentic tasks |
| Kimi K2.5 | Moonshot AI | 262K | Yes | chat · reasoning · code |
| Kimi K2.6 | Moonshot AI | 262K | Yes | chat · reasoning · code |
| Kimi K2.7 Code | Moonshot AI | 262K | Yes | chat · code · reasoning |
| Kimi K2.8 Preview | Moonshot AI | 1049K | — | code · reasoning · vision |
| Kimi K3 | Moonshot AI | 1049K | Yes | chat · code · reasoning |
| Step-2 16K | StepFun | 16K | — | chat · reasoning · code |
| Step 3.5 Flash | StepFun (阶跃星辰) | 262K | Yes | chat · reasoning · code |
| Step 3.7 Flash | StepFun (阶跃星辰) | 256K | Yes | reasoning · code · vision |
| Step 5 Preview | StepFun | 1000K | — | reasoning · code · vision |
| Hunyuan-Large | Tencent | 131K | Yes | instruction-following · reasoning · mathematics |
| Tencent Hy4 Preview | Tencent | 1000K | Yes | code · reasoning · long_context |
| MiMo-V2.6-Distill-Qwen-9B | Xiaomi | 262K | Yes | coding · tool_use · reasoning |
| MiMo-V2.6-Flash | Xiaomi | 1000K | Yes | reasoning · coding · tool_use |
| MiMo-V2.6-Pro | Xiaomi | 1000K | Yes | reasoning · coding · tool_use |
| GLM-4-Air | Zhipu AI | 131K | — | chat · reasoning · code |
| GLM 5 | Zhipu AI | 203K | Yes | reasoning · coding · tool_calling |
| GLM 5.1 | Zhipu AI | 203K | Yes | chat · reasoning · long_context |
| GLM-5.2 | Zhipu AI | 1049K | Yes | chat · code · reasoning |
| GLM 5.3 | Zhipu AI | 1049K | Yes | code · reasoning · tool_calling |
| GLM 5.3 Flash | Z.ai / Zhipu AI | 1000K | Yes | reasoning · code · vision |
| GLM 5.3 FlashX | Z.ai / Zhipu AI | 1000K | — | reasoning · code · vision |
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.