GOOGLE VS MISTRAL

Gemini 3.1 Pro Preview vs Magistral Medium

Magistral Medium is about 1.6x cheaper than Gemini 3.1 Pro Preview on a blended 3:1 input:output rate — the same 10K-in/2K-out request costs $0.03 vs $0.044. Gemini 3.1 Pro Preview has the larger context window (1,048,576 vs 128,000 tokens).

Pricing verified

API pricing per 1M tokens

ModelInput / 1M tokensOutput / 1M tokensBlended (3:1 mix)
Gemini 3.1 Pro Preview$2.00$12.00$4.50
Magistral Medium$2.00$5.00$2.75

Rates from official Google pricing and official Mistral pricing, checked 2026-08-11.

What a real workload costs

Example: one request with 10,000 input tokens and 2,000 output tokens, then that request at 100,000 runs per month.

ModelPer request (10K in / 2K out)Per month (100K requests)Monthly delta
Gemini 3.1 Pro Preview$0.044$4,400+$1,400
Magistral Medium$0.03$3,000—

Model your own prompt sizes and volumes in the token cost analyzer, or check caching savings with the prompt caching calculator.

Specs side by side

SpecGemini 3.1 Pro PreviewMagistral Medium
ProviderGoogleMistral
Context window1,048,576 tokens128,000 tokens
Model classReasoningReasoning
TokenizerProprietary (counts estimated)Proprietary (counts estimated)

Count tokens for each model on its own page: Gemini 3.1 Pro Preview token counter and Magistral Medium token counter. All Google models are on the Gemini Token Counter. All Mistral models are on the Mistral Token Counter.

FAQ

Gemini 3.1 Pro Preview vs Magistral Medium FAQ

Which is cheaper, Gemini 3.1 Pro Preview or Magistral Medium?

Magistral Medium is cheaper. At rates checked 2026-08-11, Gemini 3.1 Pro Preview costs $2.00 input / $12.00 output per 1M tokens, while Magistral Medium costs $2.00 input / $5.00 output — about a 1.6x difference on a typical 3:1 input-heavy workload.

How much does a real request cost on Gemini 3.1 Pro Preview vs Magistral Medium?

A request with 10,000 input tokens and 2,000 output tokens costs about $0.044 on Gemini 3.1 Pro Preview and $0.03 on Magistral Medium. At 100,000 such requests per month that is $4,400 vs $3,000 — a difference of $1,400 per month.

Which has the bigger context window, Gemini 3.1 Pro Preview or Magistral Medium?

Gemini 3.1 Pro Preview. It supports 1,048,576 tokens of context versus 128,000 tokens — roughly 786,000 English words in one request.

Do Gemini 3.1 Pro Preview and Magistral Medium count tokens the same way?

Not exactly. Gemini 3.1 Pro Preview uses a proprietary tokenizer (counts are estimates) and Magistral Medium uses a proprietary tokenizer (counts are estimates). The same prompt will tokenize differently, which shifts effective cost per word.