Skip to content
ShilpBot
AI Models

Mistral Large 4: Pricing, Specs and Limits

Mistral Large 4: frontier multimodal model for reasoning, coding and agentic workloads, 1M context, 0.70 in / 2.10 out per 1M tokens. Specs, limits and...

By ShilpBot Team · Published · 3 min read

Mistral Large 4 is a frontier multimodal model from Mistral AI, built for reasoning, coding and agentic workloads. It accepts text and image input and offers a 1M-token context window.

At $0.70 per million input tokens and $2.10 per million output tokens it is a lower-cost frontier option than most. Mistral is a European company, which matters to some teams for data-residency reasons.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Mistral Large 4 quick facts

DetailValue
DeveloperMistral AI
Model IDmistralai/mistral-large-4-0
Added to the catalogue2026-10-06
TypeFrontier multimodal model for reasoning, coding and agentic workloads
ParametersNot listed
Context windowabout 1M tokens (1,048,576)
Maximum output262,144 tokens
Input typestext, image
Price0.70 in / 2.10 out per 1M tokens (cached input 0.070)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What Mistral Large 4 is good for

  • General reasoning, coding and agent tasks at lower cost than most frontier models.
  • Teams that prefer a European provider.
  • Long documents with up to 262,144 output tokens.

Limits of Mistral Large 4

  • No audio or video input.
  • Data location depends on the provider you use, so check terms.
  • Compare with Sonnet 5.5 or Gemini 4 Carbon on your own tasks.

How Mistral Large 4 compares

  • Cohere Command A+: It has a larger context window (1,048,576 against 192,000 tokens); its output cap is 262,144 tokens against 64,000; it costs 0.70 input and 2.10 output per million tokens against 0.30 and 1.50.
  • Anthropic Claude Sonnet 5.5: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 262,144 tokens against 128,000; it does not accept file input; it costs 0.70 input and 2.10 output per million tokens against 2.00 and 10.00.
  • Google Gemini 4 Carbon: Both have a 1,048,576-token context window; its output cap is 262,144 tokens against 943,718; it does not accept audio or file or video input; it costs 0.70 input and 2.10 output per million tokens against 2.00 and 10.00.

Calling Mistral Large 4 from code

Use the model ID mistralai/mistral-large-4-0 with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/mistral-large-4-0", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Mistral Large 4 can do

  1. Ask it to draft a technical design document from a rough outline.
  2. Upload a diagram and ask for risks in the architecture.
  3. Compare cost and quality with Command A+ for an enterprise-style task.

What Mistral Large 4 costs

The catalogue lists 0.70 per million input tokens and 2.10 per million output tokens, with cached input at 0.070 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.91. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.13 before caching. If your client reuses the same prompt prefix, cached input at 0.070 per million tokens can cut the input side of that bill by about 90 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

How much does Mistral Large 4 cost?

The catalogue lists $0.70 per million input tokens, $2.10 per million output tokens and $0.07 per million cached input tokens.

What are the cost and limits of Mistral Large 4?

As of 2026-11-16 the catalogue lists 0.70 per million input tokens and 2.10 per million output tokens. About 1M tokens (1,048,576) context window, up to 262,144 output tokens, model ID mistralai/mistral-large-4-0. Prices can change, so check the live model page.

#Mistral Large 4#Mistral AI model#AI model pricing#AI API pricing#AI chat model#frontier model#OpenRouter