Kimi K2.7 Code
New$0.95
$4.00
2026-06
- Positioning
- Balanced. The vendor doesn't give one, so it's placed by price among text models.
- Price
- Level 2 of 4 among text models ($ is the cheapest), by output price per 1M tokens: $1 to under $5.
- Vendor-stated speed
- Not shown: the vendor doesn't compare this model's speed.
Three separate signals, not a quality score.
Kimi's coding specialist — long-horizon software engineering with leaner thinking tokens. Kimi K2.7 Code is a Moonshot (Kimi) text model on ATP Token, billed per 1M input and output tokens, with a lower cached-input rate.
Pricing
Moonshot (Kimi) · Family · USD / 1M tokens
Cost per 1,000 typical requests
| Workload | USD / 1,000 |
|---|---|
| Short chat turn800 / 400 | $2.36 |
| RAG answer4,000 / 500 | $5.80 |
| Agent step with tools20,000 / 1,500 | $25.00 |
Benchmarks
- Kimi Code Bench v262.0
Moonshot in-house benchmark; thinking mode via Kimi Code CLI, temperature 1.0, top-p 0.95, 262,144-token context
Moonshot AI - Program Bench53.6
thinking mode via Kimi Code CLI
Moonshot AI - MCP Atlas76.0%
official config, 100 tool-call budget, 32k max tokens per step; avg of 3 runs
Moonshot AI
| Benchmark | Score | Source |
|---|---|---|
| Kimi Code Bench v2Moonshot in-house benchmark; thinking mode via Kimi Code CLI, temperature 1.0, top-p 0.95, 262,144-token context | 62.0 | Moonshot AI |
| Program Benchthinking mode via Kimi Code CLI | 53.6 | Moonshot AI |
| MCP Atlasofficial config, 100 tool-call budget, 32k max tokens per step; avg of 3 runs | 76.0% | Moonshot AI |
Scores as published by each vendor, not measured by ATP. Test conditions vary, so they are not directly comparable across vendors.
Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization
Cost estimator
- Input$9.50
- Output$8.00
$17.50 USD / month · 1,750 credits / month
Quickstart
from openai import OpenAI
client = OpenAI(
base_url="https://api.atptoken.ai/v1",
api_key="atp-•••"
)
r = client.chat.completions.create(
model="kimi-k2.7-code",
messages=[{"role":"user","content":"hi"}],
)Compare with similar models
- GLM-5Z.aiPositioning: Balanced. Price level 2 of 4 among text models.$1.00 / $3.20In / out · per 1M tokens
- DeepSeek V3.2DeepSeekPositioning: Balanced. Price level 2 of 4 among text models.$0.57 / $1.71In / out · per 1M tokens
- Qwen 3.6 PlusQwen (Alibaba)Positioning: Balanced. Price level 2 of 4 among text models.$0.276 / $1.651In / out · per 1M tokens
FAQ
- Can Kimi K2.7 Code use tools, read images, or think before answering?
- Kimi K2.7 Code supports tool calling, vision input and extended thinking, but not audio.
- Is cached input cheaper on Kimi K2.7 Code?
- You pay per 1M input tokens and per 1M output tokens. Cached input costs 20% of the normal input price. You only pay when a request succeeds. $1 = 100 credits. See pricing
- Is there a newer Moonshot (Kimi) model than Kimi K2.7 Code on ATP?
- Yes. Kimi K3 (kimi-k3) came out on Jul 16, 2026, after Kimi K2.7 Code (Jun 2026), and is the newer Moonshot (Kimi) text option on ATP. Both stay available: compare family prices on this page, then turn on the id you want for your project.
- How do I call Kimi K2.7 Code on ATP?
- Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "kimi-k2.7-code" (the API id, not the display name). Make sure the model is turned on for your project.
Start with $5. Credits never expire.
Create a project key, turn this model on, and pay only for what you use.