Mistral Medium 3.5 vs Mistral Small 4
Mistral Medium 3.5 vs Mistral Small 4: Mistral Small 4 is cheaper for input-heavy usage ($0.15/M vs $1.50/M input tokens), while Mistral Medium 3.5 is better for long-context tasks (256,000 tokens).
Direct answer: choose Mistral Small 4 for lower token spend and choose Mistral Medium 3.5 when your workload needs longer context.
Compare input and output token pricing, context windows, and monthly cost estimates on one page so you can pick the cheaper model fast.
Cost Comparison (1000 input + 500 output tokens, 100 requests/day)
Mistral Medium 3.5
Mistral Small 4
Cost Differences
Mistral Small 4 costs less than Mistral Medium 3.5
Quick Recommendation
Winner for direct API pricing: Mistral Small 4. At the default workload, Mistral Small 4 saves about $14.40/month ($175.20/year) versus Mistral Medium 3.5.
Feature Comparison
| Feature | Mistral Medium 3.5 | Mistral Small 4 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Input Price | $1.50/1M tokens | $0.15/1M tokens |
| Output Price | $7.50/1M tokens | $0.60/1M tokens |
| Context Window | 256,000 tokens | 128,000 tokens |
| Max Output | 32,768 tokens | 16,384 tokens |
| Category | flagship | efficient |
| Capabilities | textvisioncodereasoning | textvisioncodereasoning |
| Release Date | 4/29/2026 | 3/18/2026 |
Mistral Medium 3.5 vs Mistral Small 4: Which Should You Choose?
Choosing between Mistral Medium 3.5 and Mistral Small 4 depends on your priorities: cost efficiency, context length, or raw capability. Mistral Small 4 is the more affordable option at $0.15/1M input tokens — 90% cheaper than Mistral Medium 3.5. Meanwhile, Mistral Medium 3.5 offers a significantly larger context window at 256,000 tokens vs 128,000 for Mistral Small 4.
These models target different tiers: Mistral Medium 3.5 is a flagship model while Mistral Small 4 is efficient. This means they're optimized for different workloads. Mistral Medium 3.5 is built for complex tasks that require deeper reasoning, while Mistral Small 4 offers better value for routine operations.
Output costs matter too. Mistral Medium 3.5 charges $7.50/1M output tokens vs $0.60 for Mistral Small 4. For generation-heavy workloads (content creation, code generation, summarization), output pricing often dominates your bill. Mistral Small 4 has the edge here at $0.60/1M output tokens.
Multimodal capabilities: Both models support vision (image understanding), so you can send images alongside text prompts with either option.
Best Use Cases
Choose Mistral Medium 3.5 when:
- • You need a larger context window (256,000 tokens)
- • You need longer outputs (up to 32,768 tokens)
- • You're already using Mistral AI's API ecosystem
Choose Mistral Small 4 when:
- • Budget is a primary concern
- • You're already using Mistral AI's API ecosystem
- • You're running high-volume, latency-sensitive workloads
Pros and Caveats at a Glance
Mistral Medium 3.5
- • Input pricing: $1.50/M tokens
- • Output pricing: $7.50/M tokens
- • Context window: 256,000 tokens
- • Max output: 32,768 tokens
Watch out for
- • Higher input cost than Mistral Small 4
- • Higher output cost than Mistral Small 4
Mistral Small 4
- • Input pricing: $0.15/M tokens
- • Output pricing: $0.60/M tokens
- • Context window: 128,000 tokens
- • Max output: 16,384 tokens
Watch out for
- • Smaller context window than Mistral Medium 3.5
Try Different Scenarios
Use the calculator below to see how costs change with different usage patterns
Mistral Medium 3.5 (Mistral AI)
Mistral Small 4 (Mistral AI)
Start using Mistral Medium 3.5 today
Sign Up for Mistral AI →Start using Mistral Small 4 today
Sign Up for Mistral AI →Frequently Asked Questions
Which is cheaper, Mistral Medium 3.5 or Mistral Small 4?▼
What is the context window difference between Mistral Medium 3.5 and Mistral Small 4?▼
Which model is better for AI Agent / Agentic Workflows?▼
Which model has better overall pricing for heavy usage?▼
Related Comparisons
Related Articles
Learn when to pick each model, then compare live pricing scenarios.