MiniMax M3 vs Mistral Medium 3.5
API pricing, context window and capabilities for MiniMax M3 and Mistral Medium 3.5, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersMiniMax M3 wins on price, on Terminal-Bench, on intelligence and on context window.
Price
MiniMax M3
Terminal-Bench
MiniMax M3
Intelligence
MiniMax M3
Context window
MiniMax M3
Key takeaways
who wins on what, from the published numbersMiniMax M3 wins
- Cheaper input ($0.23 vs $1.50 /1M)
- Cheaper output ($0.96 vs $7.50 /1M)
- Larger context window (1M vs 262K)
- Higher max output (1M vs 262K)
- More serving providers (11 vs 4)
- Supports prompt caching
Mistral Medium 3.5 wins
No clear edge on the tracked metrics.
Cheaper overall
MiniMax M3
$0.23 + $0.96 /1M
Larger context
MiniMax M3
1M
More providers
MiniMax M3
11 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| MiniMax M3 | Mistral Medium 3.5 | |
|---|---|---|
| Input $/1M | $0.23via Wandb best | $1.50via Mistral |
| Output $/1M | $0.96via Wandb best | $7.50via Mistral |
| Context window | 1M best | 262K |
| Max output | 1M best | 262K |
| Serving providers | 11 best | 4 |
| Date | Released Jun 1, 2026 | Released Apr 30, 2026 |
Benchmarks
Benchmark scores, side by side| MiniMax M3 | Mistral Medium 3.5 | |
|---|---|---|
| Intelligence | 29.2 best | 14.2 |
| Terminal-Bench | 65% best | 51% |
| GPQA Diamond | 93% best | 75% |
| Output speed | 107 t/s | 167 t/s best |
| Latency (TTFT) | 1.21s best | 2.21s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
MiniMax M3
via Wandb
$2.11
Mistral Medium 3.5
via OpenRouter
$15
Capabilities
feature support, side by side| Feature | MiniMax M3 | Mistral Medium 3.5 |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | ✓ | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | — |
| Structured output | ✓ | ✓ |
| Web search | — | — |
Related comparisons
Frequently asked questions
Which is cheaper, MiniMax M3 or Mistral Medium 3.5?
MiniMax M3 is cheaper for input ($0.23 vs $1.50 per 1M tokens) from Wandb. MiniMax M3 is cheaper for output ($0.96 vs $7.50 per 1M tokens) from Wandb.
What is the context window difference between MiniMax M3 and Mistral Medium 3.5?
MiniMax M3 has a 1M-token context window and Mistral Medium 3.5 has 262K tokens, so MiniMax M3 can take a larger prompt.
How do MiniMax M3 and Mistral Medium 3.5 compare on benchmarks?
On the tracked benchmarks, MiniMax M3 leads on Terminal-Bench, and MiniMax M3 leads on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI