Kimi K3.1 Pro API
Model ID: kimi-k3.1-pro · Developer: Moonshot AI · Available on 7API: yes, as of 2026-11-20
Accepts images. Doesn't enforce strict JSON-schema response_format, so validate structured output yourself.
Call Kimi K3.1 Pro with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "kimi-k3.1-pro".
Specifications
| Model ID | kimi-k3.1-pro |
| Context window | 1,000,000 tokens |
| Max output | 32,000 tokens |
| Input | Text and images |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning effort | low, high, max (default max) |
| API formats | Chat Completions, Responses, Anthropic Messages |
Pricing
| USD per 1M tokens | |
|---|---|
| Input | $0.30 |
| Output | $0.30 |
| Cached input | $0.05 |
For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0083 on Kimi K3.1 Pro. Billing is pay per token from a prepaid balance. See Pricing and billing.
Benchmarks
Independent scores for Kimi K3.1 Pro, as published by third parties (retrieved 2026-10-24). 7API serves the same model, so these scores apply to it here.
| Benchmark | Result |
|---|---|
| Artificial Analysis Intelligence Index, default | 55 |
Example
from openai import OpenAI
client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)In Claude Code: /model claude-kimi-k3.1-pro. Setup guides: Claude Code, OpenCode, Codex, Cursor.
Related models
- Kimi K3: $0.15/M, $0.03/M cached, 1M context
