Kimi K2.7 Code
Instantly via the EU router or as a dedicated GPU deployment. Data stays in Europe.
$ curl https://hostyourai.com/api/v1/chat/completions \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/Kimi-K2.7-Code",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
text+image->text · moonshotai · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinkin...
- Router
- Router · warm
- Dedicated
- Dedicated · available
- Input (per 1M tokens)
- €0.86
- Output (per 1M tokens)
- €4.02
Specifications
| Parameters | 1027B |
|---|---|
| Context window | 262,144 tokens |
| Minimum VRAM | 715 GB |
| Architecture | KimiK25ForConditionalGeneration (vLLM) |
| License | other |
| Modality | text+image->text |
| Released | June 2026 |
| Publisher | moonshotai ↗ |
Pricing
Shared router · per token
€0.23 per million cached input tokens
Dedicated GPU · per hour
Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.
Bench index
Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.
Measured by Epoch AI across 11 benchmarks, with a range.
Range 74.0 to 79.1 · Rank 66 of 258 at Epoch AI
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 22-11-2026
LiveBench · 68.4 · Rank 61 of 70
Every benchmark (11)
| OTIS Mock AIME 2024-2025 | 95.6 |
|---|---|
| GPQA diamond | 87.3 |
| FrontierMath-Tiers-1-3-v2-Private | 56.9 |
| WeirdML | 54.1 |
| SimpleBench | 49.5 |
| Surface Evolver Bench | 48.8 |
| APEX-Agents | 37.6 |
| SimpleQA Verified | 36.5 |
| FrontierCode | 30.1 |
| FrontierMath-Tier-4-v2-Private | 12.2 |
| Chess Puzzles | 9.5 |
LiveBench · All tasks
| theory of mind | 69.2 |
|---|---|
| zebra puzzle | 96.0 |
| spatial | 92.0 |
| logic with navigation | 74.0 |
| code generation | 71.8 |
|---|---|
| code completion | 76.1 |
| javascript | 63.6 |
|---|---|
| typescript | 23.3 |
| python | 50.0 |
| AMPS Hard | 97.0 |
|---|---|
| integrals with game | 37.0 |
| math comp | 94.1 |
| olympiad | 90.3 |
| consecutive events | 48.3 |
|---|---|
| tablejoin | 47.5 |
| tablereformat | 92.2 |
| connections | 98.0 |
|---|---|
| plot unscrambling | 55.7 |
| typos | 80.0 |
| paraphrase | 48.5 |
|---|---|
| simplify | 49.8 |
| story generation | 68.6 |
| summarize | 58.3 |
Frequently asked questions
Can I run Kimi K2.7 Code in the EU?
Yes. HostYourAI runs Kimi K2.7 Code on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Is hosting Kimi K2.7 Code GDPR-compliant?
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.
How much does Kimi K2.7 Code cost?
Via the shared EU router you pay €0.86 per million input tokens and €4.02 per million output tokens, with no fixed costs. For high volume or isolation you can also run Kimi K2.7 Code on a dedicated GPU instance, billed per minute.
Is the API OpenAI-compatible?
Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.
More models from Moonshotai
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Try Kimi K2.7 Code for free
Creating an account takes a minute. Test Kimi K2.7 Code straight away in the playground.







