Google: Gemini 2.5 Pro vs Mistral: Mistral Large 4
Head-to-head API pricing and cost comparison between Google’s Google: Gemini 2.5 Pro and Mistral’s Mistral: Mistral Large 4. Prices auto-refresh daily from OpenRouter.
Mistral: Mistral Large 4 is 46% cheaper for input tokens; Mistral: Mistral Large 4 also wins on output tokens.
Side-by-side comparison
| Spec | Google: Gemini 2.5 Pro | Mistral: Mistral Large 4 |
|---|---|---|
| Input price (per 1M) | $1.25 | $0.68 |
| Cached input (per 1M) | $0.13 | $0.07 |
| Output price (per 1M) | $10.00 | $2.09 |
| Batch input (per 1M) | — | — |
| Batch output (per 1M) | — | — |
| Reasoning price (per 1M) | $10.00 | — |
| Context window | 1049K | 524K |
| Vision support | Yes | Yes |
| Caching support | Yes | Yes |
| Batch API | No | No |
| Reasoning capability | Yes | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | Google: Gemini 2.5 Pro | Mistral: Mistral Large 4 | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $78.75 | $22.74 | $56.01 Mistral: Mistral Large 4 wins |
10K req/day 1500in / 500out tokens | $2,063 | $619.50 | $1,443 Mistral: Mistral Large 4 wins |
100K req/day 3000in / 800out tokens | $35,250 | $11,136 | $24,114 Mistral: Mistral Large 4 wins |
1M req/day 8000in / 2000out tokens | $900,000 | $288,600 | $611,400 Mistral: Mistral Large 4 wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
Frequently asked questions
Which is cheaper, Google: Gemini 2.5 Pro or Mistral: Mistral Large 4?
For input tokens, Mistral: Mistral Large 4 is roughly 46% cheaper at $0.68/1M vs $1.25/1M. For output tokens, Mistral: Mistral Large 4 wins at $2.09/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
Google: Gemini 2.5 Pro has a context window of 1049K tokens. Mistral: Mistral Large 4 offers 524K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.
Should I use Google: Gemini 2.5 Pro or Mistral: Mistral Large 4?
Choose Google: Gemini 2.5 Pro if you’re already on the Google stack, want reasoning capabilities, or prefer its feature set. Choose Mistral: Mistral Large 4 for Mistral’s ecosystem, native vision input, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.
How are these prices kept current?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: Oct 7, 2026.