Alex Getmanearly AI signals
EN

Kimi K2.7 Code

Moonshot

Released Updated
Context window
262K
262,144 tokens
Input / Output
image, text, video → text

API pricing

USD / 1M tokens

InputOutputCached input
  • $0.60
openrouter
  • $3.50
openrouter
  • $0.16
openrouter
Calculate your workload

Timeline

  1. · Weights version · evidence link
Input / output price · USD / 1M tokens
ModelEvidence linksInput / output price
moonshotai/kimi-k2.7-code
standard
openrouter$0.60 / $3.50
moonshotai/kimi-k2.7-code
standard
vercel-gateway$0.95 / $4.00
kimi-k2.7-code
standard · text
opencode-go$0.95 / $4.00
  1. · Evidence links · GitHub search · Moonshot · commits · agentgateway/agentgateway · @github-actions[bot]
    Excerpt
    -json.providers.nebius.models["moonshotai/Kimi-K2.7-Code"] = {};
  2. · Evidence links · GitHub search · Moonshot · pulls · sammasak/nixos-config · @sammasak
  3. · Evidence links · GitHub search · Moonshot · pulls · landfallbox/heimdall · @github-actions[bot]
    Excerpt
    - kimi: keeping retired models: kimi-k2.6, kimi-k2.7-code, kimi-k2.7-code-highspeed
  4. · Evidence links · GitHub search · Moonshot · pulls · kodustech/kodus-ai · @Wellington01
    Excerpt
    template vs this one through `EVAL_TEMPLATES_FILE`, deepseek-v4-flash and kimi-k2.7-code. Local runs: this eval has no model path in CI (`evals/experiment.js` has no custom-agents step).
  5. · Evidence links · GitHub search · Moonshot · pulls · folke/zaly · @zaly-repo-automation[bot]
  6. · Evidence links · GitHub search · Moonshot · pulls · duketopceo/open-computer · @duketopceo
  7. · Evidence links · GitHub search · Moonshot · pulls · anomalyco/models.dev · @KevRojo
  8. · Evidence links · GitHub search · Moonshot · pulls · agentgateway/agentgateway · @github-actions[bot]
    Excerpt
    -json.providers.nebius.models["moonshotai/Kimi-K2.7-Code"] = {};
  9. · Evidence links · GitHub search · Moonshot · pulls · Pinvou/CodeWhale · @asto18089
  10. · Evidence links · GitHub search · Moonshot · pulls · cbc02009/container-images · @mahoro-ai
    Excerpt
    failover. Non-streaming, native `/v1/messages`, and OpenAI-protocol models (`minimax-m3.1-flash`, `kimi-k2.7-code`) all work, which makes it easy to miss. Verified live against `v1.109.0-rc.1`, `v1.109.1`, `v1.110.0-rc.2` and `main`
  11. · Evidence links · GitHub search · Moonshot · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  12. · Evidence links · GitHub search · Moonshot · pulls · anomalyco/models.dev · @models-dev-automation[bot]
  13. · Evidence links · GitHub search · Moonshot · pulls · anomalyco/models.dev · @models-dev-automation[bot]

Signals 1

Specifications

Kimi K2.7 Code is a model from Moonshot with open weights, released on 12 Jun 2026. The context window is 262,144 tokens. Pricing is $0.60 per million input tokens and $3.50 per million output tokens.

Context window
262,144
Input
image · text · video
Output
text
Weights
Open
Input · USD / 1M tokens
$0.60
Output · USD / 1M tokens
$3.50
Cached input · USD / 1M tokens
$0.16

Questions

What is the context window of Kimi K2.7 Code?

The context window is 262,144 tokens.

How much does Kimi K2.7 Code cost?

Pricing is $0.60 per million input tokens and $3.50 per million output tokens. Cached input is $0.16 per million.

Are the weights of Kimi K2.7 Code publicly available?

Yes. Moonshot publishes the weights.

When was Kimi K2.7 Code released?

On 12 Jun 2026.