[Dagon Inference](https://inference.dagon.so/) / [Pricing](https://inference.dagon.so/abliterated-llm-pricing) / Kimi K3.1 Pro

# Kimi K3.1 Pro API

Published 2026-11-07 · Last updated 2026-11-11

Dagon Inference serves Kimi K3.1 Pro through an OpenAI compatible API at `https://inference.dagon.so/v1` and the Anthropic Messages API at `https://inference.dagon.so/v1/messages`, as model id `kimi-k3.1-pro`. It is a model with standard refusal behavior: it declines many requests that abliterated models answer. It costs $0.275 per million input tokens, $0.165 per million cached input tokens and $2.75 per million output tokens, with a 1,048,576 token context window, up to 65,536 output tokens per request and text and image input. 2 providers serve it: Refuseless and Silk Compute.

## What does Kimi K3.1 Pro cost?

| Tokens | Price per 1M |
| --- | --- |
| Input | $0.275 |
| Cached input | $0.165 |
| Output | $2.75 |

A request with 10,000 input tokens and 1,000 output tokens costs 5,500 µ$, about $0.0055.

Prices are Refuseless's, the provider with the lowest typical cost for this model, plus the 10% markup, at price version 2026-11-11.4. A request that falls back to another provider is billed at that provider's rate plus the markup; its signed receipt names the provider. Every model: [pricing](https://inference.dagon.so/abliterated-llm-pricing), [models.json](https://inference.dagon.so/models.json), live [/v1/models](https://inference.dagon.so/v1/models).

## Which providers serve it, and at what price?

Ranked by typical cost per 1M tokens, weighted 3:1 input to output, as of this build. The live order at [/v1/models](https://inference.dagon.so/v1/models) weighs this model's own traffic when it has enough.

| Provider | Input | Cached | Output | Typical | Quantization | Context | Max output | Endpoints |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Refuseless (cheapest) | $0.275 | $0.165 | $2.75 | $0.8938 | Not published | 1,048,576 | 65,536 | Chat, Responses |
| Silk Compute | $0.55 | $0.33 | $5.50 | $1.7875 | Not published | 1,048,576 | 65,536 | Chat, Responses, Messages |

US dollars per million tokens. Prices include the 10% markup. Each request goes to the cheapest healthy provider for that request's size, so this order is typical, not a guarantee.

## What is it?

Kimi K3.1 Pro on standard weights. It keeps the base model's refusal behavior; for refusals removed, use Kimi K3.1 Pro Abliterated (kimi-k3.1-pro-abliterated). Text and image input, 1M context. Standard refusals

- Model id: `kimi-k3.1-pro`
- Refusals: standard
- Context window: 1,048,576 tokens
- Maximum output: 65,536 tokens per request (default cap 16,384)
- Input: text and image input
- Endpoints: `/v1/chat/completions`, `/v1/responses`, `/v1/messages`
- Providers: Refuseless and Silk Compute

We have not benchmarked it and make no claims about its quality. Individual requests may still be declined or answered poorly.

## How do I call it?

Create a key with `curl -X POST https://inference.dagon.so/v1/keys` or in the [console](https://inference.dagon.so/app/), fund it in USDC, then:

```
curl https://inference.dagon.so/v1/chat/completions \
  -H "Authorization: Bearer $DAGON_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kimi-k3.1-pro", "messages": [{"role": "user", "content": "Hello"}]}'
```

With an OpenAI SDK, set the base URL to `https://inference.dagon.so/v1` and the model to `kimi-k3.1-pro`. With an Anthropic SDK, use `https://inference.dagon.so` as the base URL; the [Anthropic Messages guide](https://inference.dagon.so/anthropic-messages-api-uncensored-models) has the details. The [SDK guide](https://inference.dagon.so/uncensored-llm-openai-sdk) has more examples.

## Other models

- [GLM-5.3 Abliterated](https://inference.dagon.so/models/glm-5.3-abliterated) · Refuseless, Experiential Labs, Silk Compute (`glm-5.3-abliterated`): $1.10 input, $2.20 output per 1M tokens
- [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) · Refuseless, Experiential Labs, Lutheos, Silk Compute (`deepseek-v4.1-flash-abliterated`): $0.11 input, $0.44 output per 1M tokens
- [GLM-5.3 Flash Abliterated](https://inference.dagon.so/models/glm-5.3-flash-abliterated) · Refuseless, Experiential Labs, Silk Compute (`glm-5.3-flash-abliterated`): $0.132 input, $0.55 output per 1M tokens
- [Abliterated Large Flash](https://inference.dagon.so/models/abliterated-model-large-flash) · abliteration.ai (`abliterated-model-large-flash`): $1.10 input, $2.20 output per 1M tokens
- [Abliterated Model](https://inference.dagon.so/models/abliterated-model) · abliteration.ai (`abliterated-model`): $1.10 input, $3.30 output per 1M tokens
- [Abliterated Large v2](https://inference.dagon.so/models/abliterated-model-large-v2) · abliteration.ai (`abliterated-model-large-v2`): $3.30 input, $5.50 output per 1M tokens
- [Kimi K3.1 Pro Abliterated](https://inference.dagon.so/models/kimi-k3.1-pro-abliterated) · Silk Compute (`kimi-k3.1-pro-abliterated`): $5.50 input, $16.50 output per 1M tokens
- [DeepSeek V4.1 Flash Fast](https://inference.dagon.so/models/deepseek-v4.1-flash-fast) · Refuseless (`deepseek-v4.1-flash-fast`): $0.011 input, $0.088 output per 1M tokens
- [MiniMax M3.1 Flash](https://inference.dagon.so/models/minimax-m3.1-flash) · Refuseless (`minimax-m3.1-flash`): $0.022 input, $0.088 output per 1M tokens
- [DeepSeek V4.1 Flash](https://inference.dagon.so/models/deepseek-v4.1-flash) · Silk Compute (`deepseek-v4.1-flash`): $0.022 input, $0.176 output per 1M tokens
- [GLM-5.3 Flash](https://inference.dagon.so/models/glm-5.3-flash) · Lutheos, Cheaper Inference (`glm-5.3-flash`): $0.088 input, $0.462 output per 1M tokens
- [Hy4](https://inference.dagon.so/models/hy4) · Silk Compute (`hy4`): $1.76 input, $3.52 output per 1M tokens

## Common questions

### Which API serves Kimi K3.1 Pro?

Dagon Inference serves it as `kimi-k3.1-pro` at the OpenAI compatible base URL `https://inference.dagon.so/v1` (Anthropic SDKs: `https://inference.dagon.so`), routing each request to the cheapest healthy one of Refuseless and Silk Compute. It costs $0.275 per million input tokens, $0.165 per million cached input tokens and $2.75 per million output tokens, paid in USDC from a prepaid key or per request with x402.

### What does Kimi K3.1 Pro cost per million tokens?

$0.275 per million input tokens, $0.165 per million cached input tokens and $2.75 per million output tokens (model id kimi-k3.1-pro), including the 10% markup, at price version 2026-11-11.4.

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

1,048,576 tokens, with up to 65,536 output tokens per request through Dagon Inference.

### Which providers serve kimi-k3.1-pro?

Refuseless and Silk Compute. Each request goes to the cheapest healthy one for that request's size, with fallback to the next cheapest if it fails before any output.

## Create a key in a minute.

[Get a key](https://inference.dagon.so/app/)