kimi-k3.1-pro
By Moonshot AI
Reads images: a question can carry pictures.
Model name for the API
kimi-k3.1-pro- Uptime, last 3 days
- 3 calls so far
- Too few to give a percentage
- Reference price per million output tokens
- $20.00
- Reference per million tokens: input $4.00, output $20.00, cache reads $0.40
Your chats and training
Not used for training.
The company that answers for this model states in its own terms that it does not use prompts or replies to train its models.
Which company answers for a model is not published here, so this says what the policy is, not whose it is. Checked against their terms on Sep 28, 2026.
Model facts
- Context length
- 1M tokens
- Longest reply
- 128K tokens
- Calls tools
- Yes
- Knowledge cutoff
- Not published
- Released
- 23 Oct 2026
- Open weights
- No
Context, reply length, tool calling, knowledge cutoff, release date and open weights come from the models.dev open dataset, read once a day.
Call it through the API
Any OpenAI-compatible client works: use the address in the sample and this model name.
import requests response = requests.post( "https://onomeo.com/v1/chat/completions", headers={"Authorization": "Bearer YOUR_API_KEY"}, json={"model": "kimi-k3.1-pro", "messages": [ {"role": "user", "content": "Hello!"} ]} ) print(response.json())
Similar price
- gemini-4-argon$20.00Reference price per million output tokensToo few calls yet
- claude-sonnet-5.5$20.00Reference price per million output tokens72% up, last 3 days
- qwen3.8-max$12.00Reference price per million output tokensToo few calls yet
- grok-4.7$12.00Reference price per million output tokensToo few calls yet
- gpt-6.1-terra$10.00Reference price per million output tokens100% up, last 3 days
- glm-5.3$8.80Reference price per million output tokensToo few calls yet
Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.