Comparison · Google and Mistral
Gemini 3.8 Flash vs Mistral Large 4
Listed API prices of Gemini 3.8 Flash and Mistral Large 4 turned into the cost of the same three standard tasks, with speed from our own test requests in the United States and what each provider’s API documentation says about features that break on a switch. Output quality and answer length are not compared.
Calculated impact cost per task and per month
For an L2 task (deep analysis over a 50,000-token document, 3 steps), Gemini 3.8 Flash costs $0.131 and Mistral Large 4 $0.118 at the prices listed in the United States on , so Gemini 3.8 Flash is 11.0 % more than Mistral Large 4, counting visible output only, without cache discounts or hidden reasoning.
| Task | Gemini 3.8 Flash, per task | Mistral Large 4, per task | Gemini 3.8 Flash, per month | Mistral Large 4, per month | Gemini 3.8 Flash vs Mistral Large 4, per task |
|---|---|---|---|---|---|
| L1Micro-task (classification or strict JSON extraction) | $0.0019per L1 task | $0.0015per L1 task | $27.38per month | $21.46per month | +27.6 % |
| L2Deep analysis over a 50,000-token document | $0.131per L2 task | $0.118per L2 task | $1,905.30per month | $1,716.96per month | +11.0 % |
| L3Agentic coding loop, 15 steps | $1.02per L3 task | $0.940per L3 task | $14,897.47per month | $13,720.35per month | +8.6 % |
Calculated Per month: 20 tasks an hour around the clock, 730 hours.
Prices USD per 1M tokens
| Price | Gemini 3.8 Flash | Mistral Large 4 |
|---|---|---|
| Input, per 1M tokens | $0.750 | $0.700 |
| Output, per 1M tokens | $3.75 | $2.10 |
| Price from | Provider's price list · source page Published | Provider's price list · source page Published |
| Read | · the United States | · the United States |
| Context window | 1,048,576 tokens | 1,048,576 tokens |
What can I use it for? six common tasks, our data checks
Quality on your task: not measured by Measured Lab yet.
| Task | Gemini 3.8 Flash | Mistral Large 4 |
|---|---|---|
| Answer customer messages | Fits on price and context | Fits on price and context |
| Pull data from invoices and documents with strict JSON and page images | Fits on price and context | Fits on price and context |
| Summarize documents and meetings | Fits on price and context | Fits on price and context |
| Translate content | Fits on price and context | Fits on price and context |
| Chat assistant on your website | Fits on price and context | Fits on price and context |
| Write and review code with tool calls | Fits on price and context | Fits on price and context |
| Tasks it fits | 6 of 6 | 6 of 6 |
Checks of our data for six common tasks: a published price, a context window and answer length for the task and, where the task needs them, strict JSON output, page images and tool calls; prices, cost a month and terms for each model on its model card. Compare models for your own task in the model picker.
Speed in the US Observed our test requests
In our test requests from the United States, the median time to the first answer token was 6,955 ms for Gemini 3.8 Flash (Direct API · Google) and 634 ms for Mistral Large 4 (Direct API · Mistral).
| Model and route | Time to first answer token, median | Output speed, median | Answers |
|---|---|---|---|
| Gemini 3.8 FlashDirect API · Google | 6,955 ms range 1,021 ms–10,510 ms | 200 tokens/s range 103 tokens/s–365 tokens/s | 95 answers on 19 dates |
| Mistral Large 4Direct API · Mistral | 634 ms range 489 ms–7,389 ms | 91.3 tokens/s range 12.9 tokens/s–212 tokens/s | 65 answers on 13 dates |
| Mistral Large 4OpenRouter → Mistral | 753 ms range 491 ms–6,018 ms | 82.2 tokens/s range 7.0 tokens/s–222 tokens/s | 65 answers on 13 dates |
The same short request to every model, sent from a measurement point in the United States; medians of successful answers on at least 2 different dates, latest on . How we measure
What breaks when you switch Published provider documentation
Moving from Google to Mistral, 2 of the 5 features may not carry over, by each provider’s documentation:
- Streamed tool arguments — Google: yes; Mistral: not stated. An interface that shows arguments as they are written sees nothing until the whole call is ready.
- Reasoning with tools — Google: yes; Mistral: not stated. Switching reasoning on can rule out some tool settings or output formats, or the other way round.
Moving from Mistral to Google: every feature that Mistral’s documentation lists as supported is also listed as supported by Google.
| Feature of the API | Mistral | |
|---|---|---|
| Strict JSON schemas | Yes | Yes |
| Parallel tool calls | Yes | Yes |
| Streamed tool arguments | Yes | Not stated |
| Reasoning with tools | Yes | Not stated |
| Cache covers tool definitions | Not stated | Not stated |
What each provider’s own API documentation says, read ; “not stated” is not the same as “no”. Quotes and sources: what breaks when you switch AI APIs.
Price changes in the last 30 days
- The listed price of Mistral Large 4 changed on on OpenRouter: input $0.68 → $1.36, output $2.09 → $4.18 per 1M tokens.
- The listed price of Mistral Large 4 changed on on OpenRouter: input $1.36 → $0.70, output $4.18 → $2.10 per 1M tokens.
- The listed price of Mistral Large 4 changed on on the provider's price list: input $1.36 → $0.70, output $4.18 → $2.10 per 1M tokens.