Long-context guide
Best Long-Context Models
For giant documents, repos, transcripts, and agent memory buffers, context window only helps when it is paired with retrieval discipline and pricing you can actually afford.
| Model | Context | Best for | Input $/M |
|---|---|---|---|
| GPT-5.2-Codex OpenAI | 400K | Coding-focused tasks | $1.75 |
| GPT-5.2 OpenAI | 400K | General-purpose | $1.75 |
| Qwen 3 Max Alibaba | 262K | Multilingual | $1.2 |
| Kimi K2.5 Moonshot AI | 256K | Visual coding | $0.6 |
| GLM-5 Zhipu AI | 205K | Bilingual (CN/EN) | $0.5 |
| MiniMax M2.5 MiniMax | 196K | Real-world productivity | $0.3 |
| Llama 4 (405B) Meta | 128K | Self-hosted | $2 |
| DeepSeek V3 DeepSeek | 128K | Budget coding | $0.27 |
| Mistral Large 3 Mistral | 128K | European compliance | $2 |
| GPT-OSS-120B OpenAI | 128K | Self-hosted | $0 |
| Grok 4.1 Fast xAI | 2M | Long context | $0.2 |
| GPT-5.5 OpenAI | 1M | Complex reasoning | $5 |
| Claude Opus 4.7 Anthropic | 1M | Complex reasoning | $5 |
| GPT-5.4 OpenAI | 1M | Coding | $2.5 |
| Gemini 3.1 Pro Preview | 1M | Multimodal tasks | $2 |
| Claude Sonnet 4.6 Anthropic | 1M | Balanced performance | $3 |
Fast picks
- Grok 4.1 Fast for raw context size and low-cost giant workloads
- GPT-5.5 for hard reasoning over large inputs
- GPT-5.4 for stronger coding + tools in long-context workflows
- Gemini 3.1 Pro Preview for multimodal long-context setups
- Kimi K2.5 for long-context coding and agent use cases where provider validation is acceptable