Moonshot · Text model · GA
Moonshot: faster output variant of K3.1 Pro at twice the price platform.kimi.ai (opens in a new tab)
Compare with similar models Open the Model Finder
Figures checked 1 Nov 2026. A dash means not published on the sources we checked, so it stays blank rather than estimated.
Moonshot names these settings reasoning_effort. Price per token is the same at every level. Higher levels usually use more output tokens. platform.kimi.ai (opens in a new tab)
| Level | When to use it, per Moonshot | AA index | Tokens/s |
|---|---|---|---|
| low | No per-level advice published | – | – |
| high | No per-level advice published | – | – |
| max default | No per-level advice published | – | – |
Our rule of thumb: Simple or speed-critical work: low. Standard work: the lab's default. Complex work: high. Use xhigh or max only when your own tests show a gain, as OpenAI and Anthropic both advise. developers.openai.com (opens in a new tab)platform.claude.com (opens in a new tab)
US$ per 1M tokens, standard tier, short prompts. Output left blank where not published.
| Model | Input US$/1M | Output US$/1M |
|---|---|---|
| Kimi K3.1 Pro Highspeed | 4 | 20 |
| GPT-5.6 Sol | 4 | 20 |
| GPT-5.5 | 5 | 30 |
| Kimi K3 | 3 | 15 |
| GPT-5.4 | 2.5 | 15 |
| Lab | Moonshot |
|---|---|
| Type | Text |
| Status | GA platform.kimi.ai (opens in a new tab) |
| Released | – |
| API access | Yes platform.kimi.ai (opens in a new tab) |
| API model ID | kimi-k3.1-pro-highspeed platform.kimi.ai (opens in a new tab) |
| API rate limits | – |
| Consumer app plans | – |
| Price at each level | Same per-token price at every level. platform.kimi.ai (opens in a new tab) |
| Input per 1M tokens | US$4 platform.kimi.ai (opens in a new tab) |
| Output per 1M tokens | US$20 platform.kimi.ai (opens in a new tab) |
| Cached input | US$0.2 platform.kimi.ai (opens in a new tab) |
| Batch in / out | – |
| Other pricing | – |
| Context window | 1.05M tokens platform.kimi.ai (opens in a new tab) |
| Max output | – |
| Input types | text, image, video platform.kimi.ai (opens in a new tab) |
| Output types | text |
| Weights | Announced platform.kimi.ai (opens in a new tab)Moonshot says full weights will be released by 4 Nov 2026 |
| Reasoning | Yes platform.kimi.ai (opens in a new tab) |
| Tool use | Yes platform.kimi.ai (opens in a new tab) |
| Artificial Analysis index | – |
| Output speed | – |
| Time to first token | – |
| Reasoning levels | low, high, max (default) platform.kimi.ai (opens in a new tab) |
| Lab benchmark claims | – |
| Limitations | – |
Moonshot: Guide to using K3.1 Pro with MCP platform.kimi.ai (opens in a new tab). These official remote MCP servers fit that rule. We have not tested each server with this model. A server that publishes a client list is left out when this lab is not on it.
Same type, closest on quality index and blended price. A similarity, not a ranking.
Compare Kimi K3.1 Pro Highspeed with GPT-5.6 Sol and GPT-5.5
All 109 AI models · AI agents · How we check sources
Moonshot 
K3.1 Pro has a 1M-token context and costs $2 in and $10 out per 1M tokens on the Kimi API, a third below Kimi K3. Moonshot says full weights follow by 4 November 2026. Its Terminal-Bench 4.0 score of 65.7% is Moonshot's own claim.
Source: Kimi (opens in a new tab)
