# Kimi K3.1 Pro API

Kimi K3.1 Pro is Moonshot AI's flagship 3T-class model and the first of its K3.1 series, with thinking always on, image and video input and a 1,048,576-token context window; list price $2.00 in / $10.00 out per 1M tokens, provider list as at 1 November 2026.

- Provider: Moonshot AI
- Model ID: kimi-k3.1-pro
- Type: Chat
- Region: Global (provider global routing)
- Context window: 1,048,576 tokens
- Max output: 1,048,576 tokens
- Modalities: text, vision, tools, reasoning
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 2.00 | 3.06 |
| Output | 10.00 | 15.30 |
| Cached input | 0.20 | 0.31 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=kimi-k3.1-pro

Global: runs on the provider's global routing; no Australian-region option as at 1 November 2026. Input, output and reasoning tokens share the same 1,048,576-token window.

## Strengths

- Thinking always on, with reasoning effort low, high or max (max by default)
- Image and video input
- Output of 131,072 tokens by default, configurable up to the full 1,048,576-token window
- Strict JSON Schema output and partial mode for continuing from an assistant prefix

## Typical use cases

- Coding work from quick fixes in real codebases to full-project builds
- Finance and spreadsheet analysis
- Agents that reason over images and video
- Long outputs such as complete documents

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"kimi-k3.1-pro","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

Global: Served on the provider's global routing.

## Related models

- [Kimi K2.5](https://seedrise.ai/models/kimi-k2.5): US$0.62 input · US$3.09 output per 1M tokens, AU
- [Claude Sonnet 5.5](https://seedrise.ai/models/claude-sonnet-5-5): US$2.00 input · US$10.00 output per 1M tokens, AU
- [GPT-6.1 Sol](https://seedrise.ai/models/gpt-6.1-sol): US$2.00 input · US$10.00 output per 1M tokens, Global
- [Gemini 4 Argon](https://seedrise.ai/models/gemini-4-argon): US$2.00 input · US$10.00 output per 1M tokens, Global

## FAQ

### What is the model ID for Kimi K3.1 Pro?

Use kimi-k3.1-pro as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for Kimi K3.1 Pro compare to the list price?

Moonshot AI's list price as at 1 November 2026 is US$2.00 per 1M input tokens and US$10.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.

### What is the context window and max output of Kimi K3.1 Pro?

Kimi K3.1 Pro has a context window of 1,048,576 tokens and a maximum output of 1,048,576 tokens, per the provider documentation checked on 1 November 2026.

### Can Kimi K3.1 Pro run in Australia?

Not at present. Kimi K3.1 Pro is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### Can I turn thinking off on Kimi K3.1 Pro?

No. K3.1 Pro always thinks. You can lower reasoning_effort to low or high to reduce reasoning; max is the default.

### What is the maximum output on Kimi K3.1 Pro?

131,072 tokens by default, configurable up to 1,048,576. Input and output share the same 1,048,576-token window, and reasoning tokens count toward it.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/kimi-k3.1-pro