Back to Models
Kimi K2.7 Code Highspeed
moonshotmoonshot/kimi-k2.7-code-highspeed
How TheRouter serves this differently from the vendor
As the vendor operates it
Moonshot presents Highspeed as part of the Kimi K2.7 Code platform family for faster coding-agent inference.
On TheRouter
TheRouter exposes moonshot/kimi-k2.7-code-highspeed as its own text-to-text chat-completions model id with 256K context, 65,536 max completion tokens, and 2× catalog pricing versus moonshot/kimi-k2.7-code.
API guide
Chat completion
Use the dedicated Highspeed model id when latency justifies the higher price.
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshot/kimi-k2.7-code-highspeed","messages":[{"role":"user","content":"Review this patch for release-blocking bugs."}]}'Tool calling
Reserve Highspeed tool calling for turns where a human or orchestrator is waiting on the result.
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshot/kimi-k2.7-code-highspeed","messages":[{"role":"user","content":"Read src/router.ts and identify unsafe fallbacks."}],"tools":[{"type":"function","function":{"name":"read_file","description":"Read a project file","parameters":{"type":"object","properties":{"path":{"type":"string"}},"required":["path"]}}}]}'Fact ledger — every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Model family | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Context window | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Maximum completion | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Catalog pricing | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Training data cutoff | — | — | unknown |
| Kimi Code Bench v2 | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Program Bench | platform.kimi.ai ↗ | 2026-08-14 | verified |
| MCP Mark Verified | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Highspeed throughput target | platform.kimi.ai ↗ | 2026-08-14 | verified |
| Kimi K2.7 Code API: 30% Fewer Thinking Tokens and a HighSpeed Variant Change Your Routing Policy | Kimi Open Platform ↗ | 2026-08-14 | verified |
| When should I choose Highspeed instead of standard K2.7 Code? | platform.kimi.ai ↗ | 2026-08-14 | to verify |
| Does Highspeed change the model's context window or output limit? | platform.kimi.ai ↗ | 2026-08-14 | to verify |
| Is this route multimodal? | platform.kimi.ai ↗ | 2026-08-14 | to verify |