---
title: "Mistral Large 3 API pricing"
canonical: "https://router.xark.io/models/mistral-large-3"
description: "Mistral Large 3 at $1.20/M, 40% below the official rate. Apache 2.0 licensed, OpenAI-compatible."
section: "models"
updated: "2026-09-02"
source: "https://router.xark.io/models/mistral-large-3.md"
---

# Mistral Large 3 API pricing

Mistral Large 3 costs $1.20 per million input tokens and $3.60 per million output tokens, against an official rate of $2.00 and $6.00 — 40% below official pricing. It is a Mistral AI model under the Apache 2.0 licence, with a 256K context window, callable through an OpenAI-compatible endpoint with the model id `mistralai/mistral-large-3`. On an agent or chat workload that resends a fixed prompt prefix, where that prefix is billed at the cached rate of $0.24 per million, the saving reaches 67%. This model is listed for reference and is not currently served by an upstream provider, so requests for it return no available channel.

**Availability:** not currently served. No configured upstream carries Mistral Large 3, so a request naming `mistralai/mistral-large-3` returns `no available channel`. The rate below is what it will cost once an upstream carries it. 7 of the 24 catalogued models are callable today.

## At a glance

| Field | Value |
| --- | --- |
| Model id | `mistralai/mistral-large-3` |
| Publisher | Mistral AI |
| Modality | text |
| Licence | Apache 2.0 — [what it permits](https://router.xark.io/licences/apache-2-0.md) |
| Capacity | 256K tokens |
| Released | Jan 28, 2026 |
| Unit | per 1M tokens |
| Saving vs official | 40% |
| Callable today | No |

## Pricing

| Line item | Applies to | Our rate | Official rate | Saving |
| --- | --- | --- | --- | --- |
| Input tokens | All requests | $1.20/M | $2.00/M | 40% off |
| Output tokens | All requests | $3.60/M | $6.00/M | 40% off |
| Cache read | Prefix already cached | $0.24/M | $0.40/M | 40% off |

## Other providers carrying this model

| Provider | Input | Output |
| --- | --- | --- |
| AI Token Router | $1.20/M | $3.60/M |
| OpenRouter | $1.94/M | $5.82/M |
| DeepInfra | $1.50/M | $4.50/M |
| Together AI | $1.90/M | $5.70/M |
| Publisher (official) | $2.00/M | $6.00/M |

## What it is

EU-developed, Apache 2.0, and the strongest European-language coverage in the catalog. Often the answer when data residency is part of the conversation.

## Good for

- EU-facing products with residency requirements
- French, German, Spanish and Italian workloads
- Enterprise deployments needing permissive licensing

## Calling it

### Python

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://router.xark.io/api/v1"   # ← the only line that changes
)

response = client.chat.completions.create(
    model="mistralai/mistral-large-3",
    messages=[{"role": "user", "content": "Hello"}]
)
```

### Node.js

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ROUTER_API_KEY,
  baseURL: "https://router.xark.io/api/v1"   // ← the only line that changes
});

const response = await client.chat.completions.create({
  model: "mistralai/mistral-large-3",
  messages: [{ role: "user", content: "Hello" }]
});
```

### cURL

```bash
curl https://router.xark.io/api/v1/chat/completions \
  -H "Authorization: Bearer $ROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-large-3",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

## Questions

### What does Mistral Large 3 cost on AI Token Router, and what is the official rate?

Input is $1.20/M here against $2.00/M official, and output is $3.60/M against $6.00/M official — $0.80/M off every million input tokens and $2.40/M off every million output tokens. The headline 40% blends the two, weighted three to one towards output, because real workloads write far more than they read and a flat average of the two percentages would overstate what you actually save. Both figures are printed side by side on this page: the official rate is the only benchmark that makes ours mean anything.

### Can I call Mistral Large 3 right now?

No. Mistral Large 3 is catalogued but not currently servable — no configured upstream provider carries it, so a request naming `mistralai/mistral-large-3` returns `no available channel` instead of a result. The rate on this page is what it will cost once an upstream serves it, not something you can spend today. The text models you can call today are Kimi K2.6, Kimi K3, GLM-5.2, DeepSeek V4 Pro and DeepSeek V4 Flash. 7 of the 24 catalogued models are callable, and every page says which it is.

### Does Mistral Large 3 support prompt caching, and what does a cached token cost?

Yes. A repeated prefix — a fixed system prompt, a tool schema, a document you keep querying — is served from the model's KV cache and billed at $0.24/M instead of the standard $1.20/M, which is 80% below the input rate. Mistral AI's own cached rate is $0.40/M, so the discount applies on top of a rate that is already below official. Nothing has to be set on the request; the prefix is matched automatically. On an agent loop, where most of every request is unchanged from the last one, this is usually the largest single line on the bill.

### How do I call Mistral Large 3 from my code?

Point an OpenAI SDK at `https://router.xark.io/api/v1` and pass `model="mistralai/mistral-large-3"` — the chat completions endpoint is `https://router.xark.io/api/v1/chat/completions`. Request shape, streaming frames, the usage block and the error envelope all match what your OpenAI client already handles, so the base URL and the model id are the only two lines that change. The bare name `mistral-large-3`, without the provider prefix, resolves to the same model. An integration written before the ids were namespaced therefore keeps working.

### How large is Mistral Large 3's context window?

256K — 262,144 tokens in a single request, shared between everything you send and everything the model generates back. For comparison, the widest context in this catalogue is Llama 4 Maverick at 1M. Context is billed like any other input: filling the window costs the input rate on every token in it, every turn, which is why the cached-input rate matters more than the window size on a workload that resends the same prefix.

### What licence is Mistral Large 3 under, and can I use it commercially?

Mistral Large 3 is published by Mistral AI under the Apache 2.0 licence. Apache 2.0 is a standard permissive licence: commercial use, modification and redistribution are allowed, subject to keeping the notices and stating what you changed. It also carries an explicit patent grant from the contributors, which terminates if you bring a patent claim over the work — that grant is usually the reason a legal team prefers it to MIT. No user threshold and no field-of-use restriction apply.

### How does Mistral Large 3 pricing here compare with other providers carrying it?

Of the 3 other providers we track carrying Mistral Large 3, the lowest is DeepInfra at $1.50/M input and $4.50/M output, against our $1.20/M input and $3.60/M output. That is where the rates stood when we last reconciled them, and it can change without notice — we are not claiming to be the cheapest source for this model, only that our rate sits below Mistral AI's official $2.00/M. If you find one of these figures stale, tell us and we will correct it.

### What is Mistral Large 3 actually good at?

EU-developed, Apache 2.0, and the strongest European-language coverage in the catalog. Often the answer when data residency is part of the conversation. In practice that points at eU-facing products with residency requirements, french, German, Spanish and Italian workloads and enterprise deployments needing permissive licensing. The specifics that actually decide a fit — the rate, the licence and what it will and will not serve today — are all on this page rather than behind a sales conversation.

## Related models

| Model | Our rate | Callable | Document |
| --- | --- | --- | --- |
| Kimi K2.6 | $0.55/M | Yes | [read](https://router.xark.io/models/kimi-k2-6.md) |
| Kimi K3 | $1.85/M | Yes | [read](https://router.xark.io/models/kimi-k3.md) |
| GLM-5.2 | $0.82/M | Yes | [read](https://router.xark.io/models/glm-5-2.md) |
| GLM-5.2 Air | $0.17/M | No | [read](https://router.xark.io/models/glm-5-2-air.md) |
| DeepSeek V4 Pro | $0.28/M | Yes | [read](https://router.xark.io/models/deepseek-v4-pro.md) |
| DeepSeek V4 Flash | $0.090/M | Yes | [read](https://router.xark.io/models/deepseek-v4-flash.md) |
| Qwen3 Max Instruct | $0.49/M | No | [read](https://router.xark.io/models/qwen3-max-instruct.md) |
| Qwen3 235B A22B | $0.13/M | No | [read](https://router.xark.io/models/qwen3-235b-a22b.md) |
| MiniMax M2 | $0.19/M | No | [read](https://router.xark.io/models/minimax-m2.md) |
| Llama 4 Maverick | $0.14/M | No | [read](https://router.xark.io/models/llama-4-maverick.md) |
| GPT-OSS 120B | $0.090/M | No | [read](https://router.xark.io/models/gpt-oss-120b.md) |