ModelsKimi K3.1 Pro Highspeed
Kimi K3.1 Pro Highspeed
The faster hosted variant of Kimi K3.1 Pro, with separate API pricing and no separately identified independent evaluation in the checked sources.
Model specifications
- Context window
- 1,048,576 tokens
- Maximum output
- 1,048,576 tokens
- Input / output price
- $4.00 / $20.00USD / million tokens · check tiers below
- AA Intelligence Index
- No published resultEvaluator composite, on its own scale
Test coverage
- 165 no result
165 catalogue tests. Each test counts once; evaluator results take precedence where sources overlap.
tests with a result
source-specific results
No separately identified result is catalogued for this release. Scores from related models are not inherited.
Evaluation results
Filter the observations. Expand a row to inspect its run conditions.
0 results
No published results match.
Try another source or clear the search. Missing results are not zero.
API, pricing & runtime
Published prompt tiers, configuration notes, and endpoint measurements.
| Prompt tier | Input | Output | Cache read | Write 5m | Write 1h |
|---|---|---|---|---|---|
| All prompt lengths | $4.00 | $20.00 | $0.20 | $4.00 | $8.00 |
Release, availability and weights
Released 23 October 2026 across Kimi web/mobile, Kimi Work, Kimi Code and the API. Full weights are promised by 4 November 2026 and were not public in the sources checked on 24 October; the licence is not yet published. Enterprise administrators must opt in at launch. Kimi Work requires version 3.1.0 or later.
Read source ↗API identity and Highspeed
API identifier kimi-k3.1-pro-highspeed. Moonshot describes the same capabilities at 2–3× the speed of the base model; this is a publisher claim. No Highspeed-specific independent score, measured speed or latency was found, and the base model’s scores are not copied here.
Read source ↗Context and completion limits
The official K3 API supports a 1,048,576-token shared context window. max_completion_tokens defaults to 131,072 and can be set up to 1,048,576, subject to the combined input/output budget; this is a request upper bound, not an additional output window. OpenRouter’s completion cap is recorded separately under Hosted runtime.
Read source ↗Architecture and modalities
Moonshot calls this a 3T-class post-trained Kimi K3 model with native visual understanding. Artificial Analysis lists 2.8T total parameters and 104B active; these exact counts are evaluator metadata, not a new official architecture disclosure. The API guide supports text, image and video input with text output; no audio input/output is documented.
Read source ↗Thinking and sampling
Always-on thinking with reasoning_effort low, high or max (default max). Temperature 1.0, top_p 0.95, n=1, presence_penalty=0 and frequency_penalty=0 are fixed and should be omitted. Return complete assistant messages unchanged in multi-turn and tool workflows.
Read source ↗Capabilities and integration
Streaming, tool calling, forced tool choice, dynamic tool loading, JSON/strict JSON Schema and partial/prefix completion are documented. Chat Completions, Responses and Anthropic Messages-compatible APIs are available. Vision uses base64 or ms:// file identifiers; public image URLs are unsupported. Built-in web search is being updated and is not currently recommended for production. Zero Data Retention is available to API customers.
Read source ↗USD pricing and caching
USD per million tokens, excluding tax: input $4.00, output $20.00, cached input $0.20, cache writes $4.00 for 5m and $8.00 for 1h. The official table explicitly gives the same $0.20 cache-read rate as the base model. Flat rates across context lengths; automatic repeated-prefix caching defaults to a 5m TTL.
Read source ↗Documentation read 24 October 2026.
No separate hosted-runtime record was checked for this release.