Very long inputs
Choose Grok 4.3
Grok 4.3 reads up to 1M tokens per request, against 256k for Mistral Medium 3.5.
Grok 4.3 vs Mistral Medium 3.5: price, context and capabilities
Choose Grok 4.3 for very long inputs, the hardest reasoning tasks, agentic coding, tool use and support agents and reasoning over long documents. Choose Mistral Medium 3.5 for self-hosting and data control.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Grok 4.3 reads more per request: 1M tokens against 256k.
- Only Grok 4.3 offers reasoning, prompt caching, batch api.
- Only Mistral Medium 3.5 offers self-hostable.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Hardest reasoning tasks
Choose Grok 4.3
Grok 4.3 scores 24.9 on the Artificial Analysis Intelligence Index, against 14.2 for Mistral Medium 3.5.
Agentic coding
Choose Grok 4.3
Grok 4.3 scores 37.9% on Terminal-Bench Hard, against 33.3% for Mistral Medium 3.5.
Tool use and support agents
Choose Grok 4.3
Grok 4.3 scores 97.7% on τ²-Bench (agentic tool use), against 94.2% for Mistral Medium 3.5.
Reasoning over long documents
Choose Grok 4.3
Grok 4.3 scores 73% on Long-context reasoning (AA-LCR), against 69.3% for Mistral Medium 3.5.
Self-hosting and data control
Choose Mistral Medium 3.5
Mistral Medium 3.5 has open weights, so you can run it on your own servers; Grok 4.3 is only available through its provider.
Specifications side by side
| Grok 4.3 | Mistral Medium 3.5 | |
|---|---|---|
| Provider | xAI | Mistral AI |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | $1.56 / 1M tokens | No data |
| Input | $1.25 / 1M tokens | No data |
| Output | $2.50 / 1M tokens | No data |
| Cached input | $0.20 / 1M tokens | No data |
| Context window | 1M | 256k |
| Max output | No data | No data |
| Released | Apr 30, 2026 | April 2026 |
| Knowledge cutoff | No data | 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 | grok-4.3 | mistral-medium-3-5 |
Benchmarks side by side
Leader in bold.
| Benchmark | Grok 4.3 | Mistral Medium 3.5 |
|---|---|---|
| Intelligence Index | 24.9 | 14.2 |
| Terminal-Bench Hard | 37.9% | 33.3% |
| SciCode | 48.3% | 40.2% |
| GPQA Diamond | 90.1% | 74.8% |
| Humanity's Last Exam | 37.2% | 13.8% |
| IFBench (instruction following) | 81.3% | 68.8% |
| τ²-Bench (agentic tool use) | 97.7% | 94.2% |
| MMMU-Pro (visual reasoning) | 78.1% | 64.9% |
| Long-context reasoning (AA-LCR) | 73% | 69.3% |
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 Grok 4.3 or Mistral Medium 3.5?
Choose Grok 4.3 for very long inputs, the hardest reasoning tasks, agentic coding, tool use and support agents and reasoning over long documents. Choose Mistral Medium 3.5 for self-hosting and data control.
Which is cheaper, Grok 4.3 or Mistral Medium 3.5?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Grok 4.3 or Mistral Medium 3.5?
Grok 4.3 reads more per request: 1M tokens against 256k.
What is the difference between Grok 4.3 and Mistral Medium 3.5?
Grok 4.3 is made by xAI and Mistral Medium 3.5 by Mistral AI. A price comparison is not possible: one of them has no comparable published price. Grok 4.3 reads more per request: 1M tokens against 256k. Only Grok 4.3 offers reasoning, prompt caching, batch api. Only Mistral Medium 3.5 offers self-hostable.
Which is better for coding, Grok 4.3 or Mistral Medium 3.5?
Grok 4.3 scores 37.9% on Terminal-Bench Hard, against 33.3% for Mistral Medium 3.5.