Kimi K3 is now live. Try it now
Sign Up
moonshotai

kimi-k2.7-code

Open-weight model built for end-to-end coding and multi-step agent workflows.

moonshotai 256K context ★ Featured
Get API Key View Pricing

Value rank

#13 of 19

intelligence per dollar in our catalogue

Context rank

#2 tied

256K token window

Agentic strength

90%

tau2-bench tool-use success

Benchmarks

Independent scores by Artificial Analysis, compared with the strongest models in our catalogue.

Intelligence index

kimi-k3
57
glm-5.2
51.1
deepseek-v4-flash-0731
50
minimax-m3
44.4
kimi-k2.7-code
41.9

Coding index

glm-5.2
68.8
kimi-k2.7-code
60.8
minimax-m3
58.6

Agentic (tau2-bench)

glm-5.2
99.1%
kimi-k2.7-code
90.1%
minimax-m3
88.9%

Best for

Where this model earns its keep.

Agentic pipelines and tool use Coding and engineering Vision and image-aware tasks Prompt-cached workloads

The numbers

Pricing is live from our platform. Prices per 1M tokens, zero data retention on every request.

Input price$1.25
Cache read price$0.31
Output price$4.50
Context window256K tokens
Intelligence / coding index41.9 / 60.8
Agentic: tau2 / terminal-bench90% / 45%
GPQA / MMLU-Pro90% / -

Or consider

Close alternatives in the catalogue.

kimi-k2.6

Intelligence 42.8 · agentic 96%

deepseek-v4-flash

Intelligence 40.3 · agentic 95%

glm-5.1

Intelligence 40.2 · agentic 98%

Quick start

OpenAI-compatible. Switch in one line.

# pip install openai
client = OpenAI(base_url="https://api.tensorx.ai/v1", api_key="tsx-...")
r = client.chat.completions.create(
    model="moonshotai/kimi-k2.7-code",
    messages=[{"role": "user", "content": "Hello"}],
)

Benchmark data from the Artificial Analysis Intelligence Index v4.1, measured independently. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.