# Mistral Large 3 (Mistral) — API pricing and providers

> Open-weight multimodal MoE flagship. Model id `mistral/mistral-large-3`. Text model by Mistral.

- Page: https://infro.io/models/mistral/mistral-large-3
- Vendor: Mistral (https://infro.io/models/mistral)
- Modality: Text
- Endpoint through INFRO: `POST /v1/chat/completions` at https://api.infro.io/v1
- List rate: $0.50 per 1M input tokens and $1.50 per 1M output tokens
- Rates checked: 2026-10-05

Rates are Mistral's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| Mistral | `mistral-large-2512` |
| OpenRouter | `mistral/mistral-large-3` |

## Questions

### How much does the Mistral Large 3 API cost?

Mistral's published list rate for Mistral Large 3 is $0.50 per 1M input tokens and $1.50 per 1M output tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Mistral Large 3?

In INFRO's provider registry, Mistral Large 3 can be served by Mistral and OpenRouter. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Mistral Large 3 model ID?

Request it from INFRO as "mistral/mistral-large-3". INFRO sends each provider its own id: Mistral "mistral-large-2512", OpenRouter "mistral/mistral-large-3".

### How do I call Mistral Large 3 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "mistral/mistral-large-3" to POST /v1/chat/completions. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Mistral Large 3 usage?

No. Mistral or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.