High-volume, cost-sensitive work
Choose GPT-5 Mini
GPT-5 Mini costs 8% less on a typical mix of three input tokens for every output token ($0.69 against $0.75 per million tokens).
GPT-5 Mini vs Mistral Large 4: price, context and capabilities
Choose GPT-5 Mini for high-volume, cost-sensitive work. Choose Mistral Large 4 for writing and code generation, very long inputs, the hardest reasoning tasks, reasoning over long documents, self-hosting and data control and the latest release.
In short
- GPT-5 Mini is 8% cheaper than Mistral Large 4 at the headline price ($0.6875 / 1M tokens vs $0.75 / 1M tokens).
- Mistral Large 4 reads more per request: 1M tokens against 400k.
- Mistral Large 4 is the newer model (October 2026, against Aug 7, 2025).
- Only GPT-5 Mini offers reasoning, prompt caching, batch api.
- Only Mistral Large 4 offers self-hostable.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Writing and code generation
Choose Mistral Large 4
Mistral Large 4 charges $1.50 per million output tokens, against $2.00 for GPT-5 Mini. Output dominates the bill when answers are long.
Very long inputs
Choose Mistral Large 4
Mistral Large 4 reads up to 1M tokens per request, against 400k for GPT-5 Mini.
Hardest reasoning tasks
Choose Mistral Large 4
Mistral Large 4 scores 38.4 on the Artificial Analysis Intelligence Index, against 16.8 for GPT-5 Mini.
Reasoning over long documents
Choose Mistral Large 4
Mistral Large 4 scores 81.3% on Long-context reasoning (AA-LCR), against 72.3% for GPT-5 Mini.
Self-hosting and data control
Choose Mistral Large 4
Mistral Large 4 has open weights, so you can run it on your own servers; GPT-5 Mini is only available through its provider.
Latest release
Choose Mistral Large 4
Mistral Large 4 is the newer release (October 2026, against Aug 7, 2025 for GPT-5 Mini).
Monthly cost at three volumes
| Volume | GPT-5 Mini | Mistral Large 4 | Difference |
|---|---|---|---|
| Prototype: 1M input, 250K output tokens | $0.75 | $0.88 | GPT-5 Mini, $0.13 less |
| Production: 20M input, 5M output tokens | $15.00 | $17.50 | GPT-5 Mini, $2.50 less |
| Scale: 500M input, 100M output tokens | $325.00 | $400.00 | GPT-5 Mini, $75.00 less |
Standard rates, without caching or batch discounts. Volumes are per month.
Specifications side by side
| GPT-5 Mini | Mistral Large 4 | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Category | Language models | Language models |
| Status | Legacy | Preview |
| Headline price | $0.6875 / 1M tokens | $0.75 / 1M tokens |
| Input | $0.25 / 1M tokens | $0.50 / 1M tokens |
| Output | $2.00 / 1M tokens | $1.50 / 1M tokens |
| Cached input | $0.025 / 1M tokens | No data |
| Context window | 400k | 1M |
| Max output | 128k | No data |
| Released | Aug 7, 2025 | October 2026 |
| Knowledge cutoff | May 2024 | No data |
| Licence | Proprietary | Open weights |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API | Vision, Tool calling, Structured output, Self-hostable |
| API model id | gpt-5-mini | mistral-large-4 |
Benchmarks side by side
Leader in bold.
| Benchmark | GPT-5 Mini | Mistral Large 4 |
|---|---|---|
| Intelligence Index | 16.8 | 38.4 |
| SciCode | 39% | 54.2% |
| Humanity's Last Exam | 21.5% | 35% |
| MMMU-Pro (visual reasoning) | 70.1% | 76.4% |
| Long-context reasoning (AA-LCR) | 72.3% | 81.3% |
| Terminal-Bench Hard | 33.3% | No data |
| GPQA Diamond | 82.8% | No data |
| IFBench (instruction following) | 75.4% | No data |
| τ²-Bench (agentic tool use) | 68.4% | No data |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose GPT-5 Mini or Mistral Large 4?
Choose GPT-5 Mini for high-volume, cost-sensitive work. Choose Mistral Large 4 for writing and code generation, very long inputs, the hardest reasoning tasks, reasoning over long documents, self-hosting and data control and the latest release.
Which is cheaper, GPT-5 Mini or Mistral Large 4?
GPT-5 Mini is 8% cheaper than Mistral Large 4 at the headline price ($0.6875 / 1M tokens vs $0.75 / 1M tokens).
Which has the larger context window, GPT-5 Mini or Mistral Large 4?
Mistral Large 4 reads more per request: 1M tokens against 400k.
What is the difference between GPT-5 Mini and Mistral Large 4?
GPT-5 Mini is made by OpenAI and Mistral Large 4 by Mistral AI. GPT-5 Mini is 8% cheaper than Mistral Large 4 at the headline price ($0.6875 / 1M tokens vs $0.75 / 1M tokens). Mistral Large 4 reads more per request: 1M tokens against 400k. Mistral Large 4 is the newer model (October 2026, against Aug 7, 2025). Only GPT-5 Mini offers reasoning, prompt caching, batch api. Only Mistral Large 4 offers self-hostable.
How much do GPT-5 Mini and Mistral Large 4 cost per month?
At 20 million input and 5 million output tokens a month, GPT-5 Mini costs $15.00 and Mistral Large 4 costs $17.50, at standard rates.
Which is newer, GPT-5 Mini or Mistral Large 4?
Mistral Large 4 was released on October 2026 and GPT-5 Mini on Aug 7, 2025.