Mistral Large 4 vs Mistral Medium 3.5

Mistral Large 4 is the cheaper model at $1.36 per 1M input tokens and $4.18 per 1M output tokens, against $1.50 and $7.50 for Mistral Medium 3.5. That is about 31% less on a workload with 3 input tokens per output token. Mistral Large 4 has the larger context window: 1,000,000 tokens against 262,144. Mistral Large 4 is the newer release (October 6, 2026, against May 1, 2026 for Mistral Medium 3.5).

Mistral Large 4 vs Mistral Medium 3.5: pricing, context window and capabilities

SpecMistral Large 4Mistral Medium 3.5
Input price (per 1M tokens)$1.36$1.50
Output price (per 1M tokens)$4.18$7.50
Cached input price (per 1M tokens)$0.14—
Context window1,000,000 tokens262,144 tokens
Max output——
ReleasedOctober 6, 2026May 1, 2026
Image inputYesYes
Tool callingYesYes
ReasoningNoNo
Strict JSON schema outputYesYes
Native web searchNoNo
ProvidersMistral AIMistral AI

Prices are list prices from the cheapest provider LLM Gateway routes to for each model.

What Mistral Large 4 and Mistral Medium 3.5 cost at volume

Monthly usageMistral Large 4Mistral Medium 3.5
1M input + 250K output tokens$2.41$3.38
10M input + 2.5M output tokens$24.05$33.75
100M input + 25M output tokens$240.50$337.50

When to choose each model

Choose Mistral Large 4 for

  • Lower cost: about 31% cheaper on a typical workload
  • Larger context window: 1,000,000 tokens
  • Newer release: October 6, 2026
Mistral Large 4 pricing and providers

Choose Mistral Medium 3.5 for

No advantage on price, context window, release date or listed capabilities. Test it on your own prompts before ruling it out.

Mistral Medium 3.5 pricing and providers

Both models run on the same OpenAI-compatible endpoint, so you can send the same prompt to each and compare the output. Open this pair in the comparison tool to pin a provider or region.

Mistral Large 4 vs Mistral Medium 3.5: frequently asked questions

Which is cheaper, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 is the cheaper model at $1.36 per 1M input tokens and $4.18 per 1M output tokens, against $1.50 and $7.50 for Mistral Medium 3.5. That is about 31% less on a workload with 3 input tokens per output token.

Which has the larger context window, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 has the larger context window: 1,000,000 tokens against 262,144.

Which is newer, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 is the newer release (October 6, 2026, against May 1, 2026 for Mistral Medium 3.5).

Can I switch between Mistral Large 4 and Mistral Medium 3.5 without changing my code?

Yes. Both models are available through LLM Gateway's OpenAI-compatible API at https://api.llmgateway.io/v1. Change the model field from "mistral-large-4" to "mistral-medium-3-5" and keep the same API key, SDK, and request format.