Moonshot: Kimi K3
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestkimi-k3-fast | Neuralwatt | $3 | $15 | $0.3 | 1.0M |
| models.devmoonshotai/Kimi-K3-Fast | Pioneer | $4.50 | $22.50 | $0.45 | 1M |
| models.devmoonshotai/kimi-k3-fast | Vercel AI Gateway | $4.50 | $22.50 | $0.45 | 1M |
| models.devaccounts/fireworks/routers/kimi-k3-fast | Fireworks AI | $4.50 | $22.50 | $0.45 | 1.0M |
| models.devkimi-k3-fast | DevPass (LLM Gateway) | $4.50 | $22.50 | $0.45 | 1.0M |
| models.devfireworks/kimi-k3-fast | LLM Gateway | $4.50 | $22.50 | $0.45 | 1.0M |
| LiteLLMaccounts/fireworks/routers/kimi-k3-fast | N/A | $4.50 | $22.50 | $0.45 | N/A |
| LiteLLMkimi-k3-fast | N/A | $4.50 | $22.50 | $0.45 | N/A |
| models.devkimi-k3:fast | Inco | $6 | $30 | $0.6 | 1.0M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence43.6i
- AA coding76.2i
- AA agentic50i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.