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 K2.7 Code
- Cost
- $0.656 in · $3.30 out per 1M tokensMid-range
- Memory
- 262K tokens — about 400 pages
- Reads
- Text · Images
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 69% · Agentic work: better than 54% · Overall: better than 52%
- Reliability
- 100.00% uptime, last 24h
- Released
- Jun 12, 2026
Advanced details
- API model ID
moonshotai/kimi-k2.7-code- Max output
- 236K tokens
- Max input
- 229K tokens
- Cached input
- $0.18 per 1M
- Tokenizer
- Other
- Coding index
- 60.8
- Agentic work index
- 21.0
- Overall index
- 25.8
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 |
|---|---|---|---|---|---|
| Inceptron · int4 | $0.656 | $3.30 | $0.18 | 236K | 99.68% |
| DeepInfra · fp4 | $0.68 | $3.40 | $0.136 | 16K | 97.93% |
| CoreWeave · int4 | $0.71 | $3.50 | $0.15 | 236K | 99.98% |
| StreamLake | $0.712 | $3.00 | $0.143 | 32K | 99.81% |
| Venice · int4 | $0.75 | $3.50 | $0.16 | 66K | 63.32% |
| ModelRun · fp4 | $0.85 | $3.75 | $0.16 | 236K | 99.55% |
| SiliconFlow · fp8 | $0.859 | $3.80 | $0.18 | 236K | 99.91% |
| Novita · int4 | $0.912 | $3.84 | $0.182 | 236K | 99.75% |
| Fireworks | $0.95 | $4.00 | $0.19 | 236K | 89.91% |
| Nebius · fp4 | $0.95 | $4.00 | — | 236K | 99.27% |
| BaseTen · fp4 | $0.95 | $4.00 | $0.16 | 236K | 99.92% |
| GMICloud · fp8 | $0.95 | $4.00 | $0.19 | 236K | 99.75% |
| Alibaba · fp8 | $0.95 | $4.00 | $0.19 | 16K | 97.50% |
| Cloudflare | $0.95 | $4.00 | $0.19 | 236K | 100.00% |
| Moonshot AI · int4 | $0.95 | $4.00 | $0.19 | 236K | 100.00% |
| Moonshot AI · highspeed | $1.90 | $8.00 | $0.38 | 236K | 99.74% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- parallel_tool_calls
- 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