Long-context models: 200k to 1M tokens
When the prompt is a repo, a contract, or a huge PDF, context is the product. This collection gathers models with 200k–1M windows on Geek Hub for long analysis and agents with extended memory.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 Claude Fable 5Anthropic | Chat | 1M tokens | $10.9006/M in · $54.503/M out |
| Claude Opus 5Anthropic | Chat | 1M tokens | $5.4503/M in · $27.2515/M out |
| Claude Sonnet 5Anthropic | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 Kimi K3Moonshot (Kimi) | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 Gemini 3.1 Pro (preview)Google | Chat | 2M tokens | $2.1801/M in · $13.0807/M out |
| Gemini 2.5 ProGoogle | Chat | 2M tokens | $1.3626/M in · $10.9006/M out |
| Gemini 2.5 FlashGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
| Kimi K2.7 CodeMoonshot (Kimi) | Chat | 262k tokens | $1.0356/M in · $4.3602/M out |
Why these models
Claude 5 family and Kimi K3 offer 1M; Gemini Pro/Flash cover long context at different prices; Kimi Code adds 262k focused on code.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- Does 1M context cost more?
- You pay for tokens used, not the max. A large window lets you send more input; flagships usually cost more per million.
- When do I really need long context?
- Whole codebases, due diligence, books, long logs, multi-doc RAG without aggressive chunking. If it fits in 32k, do not overpay.
- Is Flash with long context enough?
- Gemini Flash with a large window is great for cost. For dense reasoning over that context, Pro/Sonnet/Opus usually win.