Mistral Large 3 vs Mistral Medium 3 — Price, Context, and Capability Compared
Mistral Large 3 vs Mistral Medium 3: which should I use?
Mistral Large 3 costs 3.8× more per blended million tokens than Mistral Medium 3. Mistral Large 3 has the larger context window (131,072 tokens). Default to Mistral Medium 3 unless you specifically need Mistral Large 3's edge.
Price, speed, and task evidence
Task verdict
Best-fit task signals from the published model strengths; this is not a substitute for a controlled benchmark.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| Best fit | Strong reasoning and coding at a lower cost than the big-lab flagships. | Balanced production workloads that don’t need Mistral Large. |
| Reasoning mode | Unavailable | Unavailable |
Effective workload cost
Modeled for Coding Agent: 20,000 input + 2,000 output tokens per task, 1 turn. This is a workload model, not a provider quote.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| Coding Agent / task | $0.05 (modeled) | $0.01 (modeled) (winner) |
| Input / output rate | $2.00 / $6.00 per M | $0.40 / $2.00 per M |
Speed
Only non-estimated benchmark results are shown as measured.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| Measured throughput | 61 tokens/s | 92 tokens/s (winner) |
| Time to first token | 400 ms | 320 ms |
API compatibility
Provider-level wire-format and SDK facts; model-specific parameter differences may still apply.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| OpenAI SDK | Usable | Usable |
| Request shape | OpenAI-compatible chat/completions endpoint at api.mistral.ai/v1. | OpenAI-compatible chat/completions endpoint at api.mistral.ai/v1. |
| Streaming | SSE (OpenAI delta) | SSE (OpenAI delta) |
Privacy and retention
Provider policy and residency facts from the verified provider registry. A missing retention policy is not treated as a guarantee.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| Provider says API data trains models | No | No |
| Published retention period | Unavailable | Unavailable |
| Data residency | EU-hosted by default | EU-hosted by default |
Migration effort
Direction is from each displayed model to the other. Effort is derived from provider compatibility and published parameter maps.
| Fact | Mistral Large 3 | Mistral Medium 3 |
|---|---|---|
| Move Mistral Large 3 → Mistral Medium 3 | drop-in; 0 breaking parameter differences | Target: Mistral Medium 3 |
| Move Mistral Medium 3 → Mistral Large 3 | Source: Mistral Medium 3 | drop-in; 0 breaking parameter differences |
| Why | Same provider; only the model identifier changes. | Same provider; only the model identifier changes. |
Spec comparison
| Mistral Large 3 | Mistral Medium 3 | |
|---|---|---|
| Price (input) | $2.00/M | $0.40/M ✓ |
| Price (output) | $6.00/M | $2.00/M ✓ |
| Blended price | $3.00/M | $0.80/M ✓ |
| Context window | 131,072 tokens | 131,072 tokens |
| Max output | 32,768 tokens | 32,768 tokens |
| Modalities | text, vision | text, vision |
| Reasoning mode | No | No |
| Released | 2026-01 | 2025-12 |
| Speed | 61 t/s | 92 t/s ✓ |
Cost at scale (3:1 blended)
| Tokens / month | Mistral Large 3 | Mistral Medium 3 | Delta |
|---|---|---|---|
| 1,000,000 | $3.00 | $0.80 | $2.20 (3.8×) |
| 10,000,000 | $30.00 | $8.00 | $22.00 (3.8×) |
| 100,000,000 | $300.00 | $80.00 | $220.00 (3.8×) |
Choose Mistral Large 3 if…
- ✓Mistral’s flagship reasoning and coding model
- ✓Low price relative to other frontier models
- ✓EU-hosted option available
- ✓Strong reasoning and coding at a lower cost than the big-lab flagships.
Choose Mistral Medium 3 if…
- ✓Best quality-to-cost ratio in the Mistral lineup
- ✓Fast enough for interactive use
- ✓Vision input included
- ✓Balanced production workloads that don’t need Mistral Large.
Run this exact matchup right now
Send the same prompt to Mistral Large 3 and Mistral Medium 3 side by side and see the outputs yourself.
Try Mistral Large 3 vs Mistral Medium 3 FreeFAQ
Is Mistral Large 3 cheaper than Mistral Medium 3?
Mistral Medium 3 is cheaper, at $0.80 per million blended tokens vs $3.00 for Mistral Large 3.
Which has the bigger context window, Mistral Large 3 or Mistral Medium 3?
Both models support 131,072 tokens of context.
Can Mistral Large 3 replace Mistral Medium 3 for coding?
Both are viable for coding. Mistral’s flagship reasoning and coding model (Mistral Large 3) vs Best quality-to-cost ratio in the Mistral lineup (Mistral Medium 3) — pick based on which strength matters more for your workload.
Which is faster, Mistral Large 3 or Mistral Medium 3?
Mistral Medium 3 is faster: 92 t/s vs 61 t/s, measured on our speed benchmarks.
Neither of these? See Mistral Large 3 alternatives.
Related
Pricing verified 2026-06-14. Specs verified 2026-08-08.