# Mistral Large 4 API

Mistral Large 4 is Mistral's general-purpose multimodal model, a mixture-of-experts with 1.05T total and 52B active parameters, in public preview since 6 October 2026 with a 1M-token context window; list price $0.70 in / $2.10 out per 1M tokens, provider list as at 1 November 2026.

- Provider: Mistral
- Model ID: mistral-large-4
- Type: Chat
- Region: Global (provider global routing)
- Context window: 1,000,000 tokens
- Max output: not listed
- 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 | 0.70 | 1.07 |
| Output | 2.10 | 3.21 |
| Cached input | 0.070 | 0.107 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=mistral-large-4

Mistral Large 4 is a public preview, so behaviour, limits and the exact API identifier may change before general availability. Global: runs on the provider's global routing; no Australian-region option as at 1 November 2026.

## Strengths

- Text and image input through a 1.6B-parameter vision encoder
- Reasoning modes low and high
- Function calling and structured outputs
- Open weights under the Mistral Ecosystem Open Weight License

## Typical use cases

- General-purpose assistants with image understanding
- Long-context document analysis up to 1M tokens
- Tool-calling agents at a moderate price
- Teams that prefer an open-weight model family

## 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":"mistral-large-4","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="mistral-large-4",
    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

- [Mistral Small 4](https://seedrise.ai/models/mistral-small-4): US$0.15 input · US$0.60 output per 1M tokens, Global
- [Gemini 3.8 Flash](https://seedrise.ai/models/gemini-3.8-flash): US$0.75 input · US$3.75 output per 1M tokens, Global
- [DeepSeek V3.2](https://seedrise.ai/models/deepseek-v3.2): US$0.64 input · US$1.91 output per 1M tokens, AU
- [Kimi K2.5](https://seedrise.ai/models/kimi-k2.5): US$0.62 input · US$3.09 output per 1M tokens, AU

## FAQ

### What is the model ID for Mistral Large 4?

Use mistral-large-4 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 Mistral Large 4 compare to the list price?

Mistral's list price as at 1 November 2026 is US$0.70 per 1M input tokens and US$2.10 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 Mistral Large 4?

Mistral Large 4 has a context window of 1,000,000 tokens, per the provider documentation checked on 1 November 2026. Maximum output is not listed on our rate card; ask us for the current limit.

### Can Mistral Large 4 run in Australia?

Not at present. Mistral Large 4 is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### Is Mistral Large 4 generally available?

Not yet. Mistral lists it as a public preview released on 6 October 2026. If the provider changes its identifier or pricing at general availability, we pass the change on with notice.

### Does Mistral Large 4 accept images?

Yes. Mistral describes it as multimodal, with a 1.6B-parameter vision encoder alongside the language model.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/mistral-large-4