GetMoreToken
This model is currently paused and cannot be called via the API. Specs and prices reflect the last known state.
mistral·chat· vision

Mistral Large 2

mistral/mistral-large-2

Mistral's flagship — EU-hosted, strong on multilingual generation.

At a glance

  • · $2.00 input / $6.00 output per 1M tokens (provider list price, billed in credits)
  • · Context window: 128,000 tokens
  • · OpenAI-compatible — model: "mistral/mistral-large-2" (provider: mistral)
  • · Best for: EU-hosted — GDPR-friendly without US data export

Strengths

  • +EU-hosted — GDPR-friendly without US data export
  • +Strong on European languages (DE, FR, IT, ES)
  • +Solid tool calling and JSON mode

Weaknesses

  • −Code quality behind Sonnet 4.6 and GPT-5.4
  • −No native vision

Use cases

  • →Multilingual generation for European markets
  • →GDPR-strict B2B workloads without US data path
  • →Structured-output tasks with moderate accuracy requirements

Alternatives in the catalog

How to call it

Drop-in OpenAI-compatible. Just swap the `model` string and you're using this model.

curl https://www.getmorecredits.com/v1/chat/completions \
  -H "Authorization: Bearer $GMC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-2",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Good for

Frequently asked questions

How much does Mistral Large 2 cost?⌄

Input is $2.00 per million tokens; output is $6.00 per million tokens — provider list price. On getmorecredits.com you pay in credits, no subscription, no minimum spend.

What's the context window of Mistral Large 2?⌄

Mistral Large 2 accepts up to 128,000 input tokens, with a maximum of 8,192 output tokens per response. That fits long conversations and medium documents into a single call.

What can Mistral Large 2 do?⌄

Mistral Large 2 supports tool calling, native JSON mode, structured output. Mistral's flagship — EU-hosted, strong on multilingual generation.

Is Mistral Large 2 OpenAI-compatible?⌄

Yes. On getmorecredits.com you call Mistral Large 2 with the same request shape as OpenAI: POST /v1/chat/completions with "model": "mistral/mistral-large-2". Existing OpenAI SDKs (Python, Node, etc.) work by changing the base URL and API key.