Kimi K3.1 Pro API
6x cheaperMoonshot AI's 1M-context model for long-horizon coding and agent work, with tools, images and structured outputs. $0.30 input, $0.20 cached input and $9.00 output per 1M tokens, with a 1,048,576 tokens context.
- Input / 1M
- $0.30market $2.00
- Cached input / 1M
- $0.20market $0.20
- Output / 1M
- $9.00market $10.00
- Context
- 1Mtokens
Kimi K3.1 Pro price per 1M tokens
| Mode | Input | Cached input | Output |
|---|---|---|---|
| Standard | $0.30 | $0.20 | $9.00 |
Market price is $2.00 input, $0.20 cached input and $10.00 output per 1M tokens.
Prices are USD per 1M tokens. Cached input is a prompt prefix the model has seen before, which agents resend on every turn. You pay only for the tokens you use. Compare it with every model on OpenScale.
Specs
| Spec | Value |
|---|---|
| Model id | moonshotai/kimi-k3.1-pro |
| Developer | Moonshot AI |
| Context length | 1,048,576 tokens |
| Max output | 943,718 tokens per request |
| Rate limit | 100 requests and 10M tokens per minute per account |
- Text and image input, text output.
- Tool calling.
- Structured outputs with a JSON schema, and JSON mode.
- Reasoning you can turn on or off; the reasoning is returned as reasoning. Reasoning effort: low, medium, high.
Versions
moonshotai/kimi-k3.1-pro always serves the latest version we have tested, now 1023. Pinned ids never change. Every version has the same price.
| Model id | Version | Released | Behavior |
|---|---|---|---|
| moonshotai/kimi-k3.1-pro | 1023 | 23 Oct 2026 | Moves to each new version |
Call Kimi K3.1 Pro from your code
Use any OpenAI SDK with the base URL https://api.openscale.so/v1, or any Anthropic SDK with https://api.openscale.so/anthropic. Set your API key as OPENSCALE_API_KEY.
curl https://api.openscale.so/v1/chat/completions \
-H "Authorization: Bearer $OPENSCALE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k3.1-pro",
"messages": [{"role": "user", "content": "Explain what a token is in one sentence."}]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openscale.so/v1",
api_key=os.environ["OPENSCALE_API_KEY"],
)
response = client.chat.completions.create(
model="moonshotai/kimi-k3.1-pro",
messages=[{"role": "user", "content": "Explain what a token is in one sentence."}],
)
print(response.choices[0].message.content)
import os
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.openscale.so/anthropic",
api_key=os.environ["OPENSCALE_API_KEY"],
)
message = client.messages.create(
model="moonshotai/kimi-k3.1-pro",
max_tokens=1024,
messages=[{"role": "user", "content": "Explain what a token is in one sentence."}],
)
print(next(block.text for block in message.content if block.type == "text"))
Every parameter, streaming and errors are in the API reference.
Use Kimi K3.1 Pro in your coding agent
Each guide is a tested setup that keeps your existing configuration. Select moonshotai/kimi-k3.1-pro as the model.
- Claude Code
- Codex
- OpenCode
- OpenClaw
- Cline
- GitHub Copilot
- DeepSeek Harness
- Hermes
- Kilo Code
- Pi
- Zed
- Factory Droid
Or pick your agent and copy one setup prompt on the agent setup page.
FAQs
How much does the Kimi K3.1 Pro API cost?
$0.30 per 1M input tokens, $0.20 per 1M cached input tokens and $9.00 per 1M output tokens. That is 6x cheaper than the market price of $2.00 input and $10.00 output. You pay only for the tokens you use, from prepaid credit.
Is the Kimi K3.1 Pro API OpenAI compatible?
Yes. Point any OpenAI SDK at https://api.openscale.so/v1 and use the model id moonshotai/kimi-k3.1-pro, with Chat Completions or Responses. Anthropic SDKs work too, at https://api.openscale.so/anthropic.
What is the context length of Kimi K3.1 Pro?
1,048,576 tokens in total, input and output together, with up to 943,718 tokens of output per request.
Can I use Kimi K3.1 Pro in a coding agent?
Yes. OpenScale has a tested setup for 12 coding agents, including Claude Code, Codex, OpenCode, OpenClaw. One API key works for every agent.
What are the rate limits for Kimi K3.1 Pro?
100 requests and 10,000,000 tokens per minute per model on each account, shared by its API keys. Need more? Email hello@openscale.so.
How do I start?
Create an account, add credit and create an API key. New accounts get free credit to try it.
Create an account to get an API key. Plain Markdown version of this page: /models/kimi-k3.1-pro.md.