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 K3
- Cost
- $3.00 in · $15.00 out per 1M tokensMid-range
- Memory
- 1M tokens — about 1,550 pages
- Reads
- Text · Images · Video
- Can do
- Use tools (agents)
- Structured output
- Thinking mode
- Good at
- Coding: better than 90% · Agentic work: better than 86% · Overall: better than 84%
- Reliability
- 99.95% uptime, last 24h
- Released
- Jul 16, 2026
Advanced details
- API model ID
moonshotai/kimi-k3- Max output
- 944K tokens
- Cached input
- $0.30 per 1M
- Tokenizer
- Other
- Coding index
- 76.2
- Agentic work index
- 50.0
- Overall index
- 43.6
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 |
|---|---|---|---|---|---|
| Sail Research · fp4 | $1.20 | $10.535 | $0.30 | 944K | 96.56% |
| InferenceNet · fp4 | $1.30 | $11.40 | $0.30 | 944K | 99.76% |
| Wafer | $1.99 | $15.00 | $0.30 | 944K | 99.63% |
| Makora | $2.04 | $12.75 | $0.204 | 944K | 98.88% |
| Relace · fp4 | $2.10 | $10.50 | $0.21 | 944K | 99.67% |
| Morph | $2.125 | $11.90 | $0.247 | 944K | 97.82% |
| Phala | $2.55 | $12.75 | $0.255 | 944K | 99.76% |
| DigitalOcean | $2.55 | $12.95 | $0.255 | 944K | 96.45% |
| DeepInfra · bf16 | $2.85 | $14.25 | $0.285 | 16K | 98.70% |
| Chutes · mxfp4 | $3.00 | $15.00 | $0.30 | 66K | 95.65% |
| Parasail · fp4 | $3.00 | $15.00 | $0.30 | 944K | 99.19% |
| Modal · mxfp4 | $3.00 | $15.00 | $0.30 | 944K | 99.81% |
| Together | $3.00 | $15.00 | $0.30 | 944K | 99.57% |
| Fireworks | $3.00 | $15.00 | $0.30 | 944K | 99.95% |
| BaseTen · fp8 | $3.00 | $15.00 | $0.30 | 262K | 99.51% |
| Moonshot AI · mxfp4 | $3.00 | $15.00 | $0.30 | 944K | 99.88% |
| Fireworks · us | $3.30 | $16.50 | $0.33 | 944K | 99.54% |
| Alibaba | $3.45 | $17.25 | $0.345 | 944K | 96.18% |
| Fireworks · fast | $4.50 | $22.50 | $0.45 | 944K | 99.80% |
Supported parameters
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- 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