Models that keep accuracy at 128K+ tokens — Kimi, GLM-Long, Qwen2.5-1M. Useful for long-document Q&A, whole-repo code review, or multi-hour transcripts where chunking would lose the through-line.
| Model | Creator | Context | Open weight | Tags |
|---|---|---|---|---|
| Qwen2.5-32B-Instruct | Alibaba Cloud | 131K | Yes | text-generation · instruction-following · long-context |
| Qwen3 72B Instruct | Alibaba | 131K | Yes | chat · reasoning · multilingual |
| ERNIE 4.0 Turbo | Baidu | 128K | — | chat · reasoning · long_context |
| DeepSeek V3 | DeepSeek AI | 66K | Yes | reasoning · coding · tool_use |
| Llama 3.3 70B Instruct | Meta | 131K | Yes | chat · coding · reasoning |
| MiniMax M2.7 | MiniMax | 205K | Yes | chat · long_context |
| 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 K3 | Moonshot AI | 1049K | Yes | chat · code · reasoning |
| Hunyuan-Large | Tencent | 131K | Yes | instruction-following · reasoning · mathematics |
| Tencent Hy4 Preview | Tencent | 1000K | Yes | code · reasoning · long_context |
| 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 |
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.