Kimi K2.7 Code

Open weights

Kimi K2.7 Code is a language model from Moonshot AI with a 256K-token context window. Provider list price is $0.95 per million input tokens and $4 per million output; on Allocate you pay $1.02 and $4.28 with the 7% transaction fee. The weights are open, so you can fine-tune it and own the result.

Route Kimi K2.7 Code Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.95$1.02

Output, per M tokens$4$4.28

Cached input, per M tokens$0.19$0.20

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4$0.60$3.60

Qwen3.5 397B A17b$0.60$3.60

Kimi K2.7 Code$0.95$4

GLM 5 Fp4$1$3.20

Kimi K2.6 Fp4$1.20$4.50

Qwen3.7 Max$1.25$3.75

GLM 5.1 FP4$1.40$4.40

Deepseek V4 Pro$1.74$3.48

InputOutput

Provider list prices per M tokens, Kimi K2.7 Code against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.95 + 350 × $4 = $2,540 a month. Billed on Allocate it is $2,718 with the 7% transaction fee.

Kimi K2.7 Code is an open-weights model; the catalog does not list its license, so check the lab’s model card before commercial fine-tuning.

Example usage

Point a route at moonshotai/kimi-k2.7-code and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "moonshotai/kimi-k2.7-code",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · moonshotai/kimi-k2.7-code · inside your boundary

Common questions

How much does Kimi K2.7 Code cost per million tokens?

Provider list price is $0.95 per million input tokens and $4 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $1.02 in and $4.28 out.

What context window does Kimi K2.7 Code have?

262,144 tokens (256K). At roughly 0.75 words per token, that is about 197k words of English text per request.

What does cached input cost on Kimi K2.7 Code?

$0.19 per million tokens at list ($0.20 billed). Repeated prompt prefixes, such as a stable system prompt or tool definitions, bill at this rate instead of the full input price.

Can I fine-tune Kimi K2.7 Code?

Yes. Kimi K2.7 Code is an open-weights model; check the lab’s model card for the exact license terms. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call Kimi K2.7 Code on Allocate?

Send moonshotai/kimi-k2.7-code in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.