Kimi
Moonshot's open-weight models, built for long documents and agent runs.
Kimi is Moonshot AI's model family, open-weight and aimed squarely at long-horizon work: big context windows, strong tool use, and a Code variant tuned for software tasks. K3 is a multimodal reasoning model with a million-token context. If you have a large repository or a long agent run and do not want to pay frontier prices, this is the family to price against. The Kimi chat app is listed separately under Chats.
At a glance — Kimi K2.5
- Cost
- $0.45 in · $2.25 out per 1M tokensBudget
- Memory
- 262K tokens — about 400 pages
- Reads
- Text · Images
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 48%
- Reliability
- 99.87% uptime, last 24h
- Released
- Jan 27, 2026
Advanced details
- API model ID
moonshotai/kimi-k2.5- Max output
- 236K tokens
- Cached input
- $0.07 per 1M
- Tokenizer
- Other
- Coding index
- 46.8
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlow · int4 | $0.45 | $2.25 | $0.07 | 236K | 99.87% |
| AtlasCloud · int4 | $0.49 | $2.50 | $0.20 | 236K | 97.83% |
| Venice | $0.532 | $3.325 | $0.209 | 66K | 98.61% |
| Novita | $0.57 | $2.85 | $0.095 | 236K | 98.56% |
| Amazon Bedrock · us-east-2 | $0.60 | $3.00 | — | 131K | 98.60% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Moonshot AI
- Weights
- Open
- Good for
- Long documents and long agent runs