Mistral Large 3 vs Mistral Medium 2505
Mistral Large 3 (Azure AI Foundry, 256,000-token context) versus Mistral Medium 2505 (Mistral AI, 131,072-token context). Mistral Large 3 is cheaper by 17% on a blended token mix. Mistral Large 3 uniquely supports vision input. Mistral Medium 2505 uniquely supports structured output (json schema). Across 1 public benchmark we tracked, Mistral Large 3 wins 1 and Mistral Medium 2505 wins 0. Use the live calculator below to plug your real usage shape into both, then route the winner via Agent Command Center for shadow A/B without code changes.
Bottom line — Mistral Large 3 vs Mistral Medium 2505
Mistral Large 3 and Mistral Medium 2505 target overlapping workloads but differ sharply on economics. Mistral Large 3 runs roughly 17% cheaper on a blended input-plus-output token mix, The gap compounds at enterprise scale, making the cost axis the first filter most teams apply when deciding between these two models.
Mistral Large 3 ships a 256,000-token context window, 2.0x larger than Mistral Medium 2505's 131,072 tokens. That headroom matters for long-document RAG pipelines, multi-turn agent sessions that accumulate tool-call history, and codebases where the entire repository needs to fit in a single prompt. If your average prompt stays under 131,072 tokens, the extra context on Mistral Large 3 is insurance you may never use — and Mistral Medium 2505 may win on other axes.
On capability surface area, the models diverge: Mistral Large 3 supports vision input where the other does not; Mistral Medium 2505 supports structured output (json schema) where the other does not. These differences are binary — either your workload needs the capability or it does not. Check whether any critical path in your agent pipeline depends on a capability only one model provides before committing to a migration.
For teams evaluating both models, the recommended path is a shadow A/B test: route production traffic through an OpenAI-compatible gateway, mirror a percentage to the candidate model, score both responses with an automated evaluator (faithfulness, tool-call correctness, latency), and compare cohort-level metrics over two weeks. Future AGI Agent Command Center supports this pattern with a single `base_url` change and built-in evaluators from the ai-evaluation SDK.
Live workload comparison
Same workload run through both models. The cheaper one is highlighted.
strategy: cost-optimized
primary:
model: mistral-medium-2505
provider: mistral
fallback:
model: mistral-large-3
provider: azure-ai-foundry
shadow: { sample_rate: 0.05 } # mirror 5% of traffic to compare quality live| Mistral Large 3 | Mistral Medium 2505 | |
|---|---|---|
| Input price | $0.500/M | $0.400/M |
| Output price | $1.50/M | $2.00/M |
| Context window | 256,000 | 131,072 |
| Max output | 8,191 | 8,191 |
| Function calling | ✓ | ✓ |
| Vision | ✓ | — |
| Audio input | — | — |
| Reasoning | — | — |
| Prompt caching | — | — |
| Structured output | — | ✓ |
| Pricing verified | Aug 6, 2026 | Aug 6, 2026 |
Benchmark comparison
Side-by-side public benchmark scores. Greener bar = winner.
Cost at scale: monthly spend at three usage volumes
Estimated monthly cost assuming 1,000 input + 200 output tokens per request — a realistic chat-agent shape. Adjust your own usage in the calculator at the top of this page for an exact number.
| Scale | Mistral Large 3 | Mistral Medium 2505 | Delta |
|---|---|---|---|
| Startup 10K requests/day | $240 /mo | $240 /mo | — |
| Mid-market 100K requests/day | $2,400 /mo | $2,400 /mo | — |
| Enterprise 1M requests/day | $24,000 /mo | $24,000 /mo | — |
At enterprise scale (1M requests/day), a difference of even ~10% in unit price compounds into thousands of dollars per month. Cached input pricing and batch tiers can shift this further — both are surfaced on each model's own page.
When to choose which
Picked from the data above — not vendor marketing. Match the rules to your workload, not the other way around.
You're cost-sensitive at scale — Mistral Large 3 runs ~17% cheaper on a blended in+out token mix, compounding into thousands of dollars per month at production volume.
Your inputs include screenshots, diagrams, or product photos — Mistral Large 3 accepts image input natively, the other doesn't.
On arena-elo, Mistral Large 3 scores 28.0 points higher — if your workload pattern matches that benchmark's task shape, the gap is meaningful.
Capability diff — what you gain and lose on the swap
A specific list of what each model has that the other doesn't. If your workload depends on a row in Only Mistral Large 3, switching to Mistral Medium 2505 means re-architecting that path (and vice versa).
- • Vision input
- • Structured output (JSON schema)
Capabilities both share (2)
- ✓ Function calling
- ✓ Streaming
Benchmark winners — by the numbers
For each public benchmark that has scores for both models, the higher score and the size of the gap. Benchmarks are noisy — treat anything under a 2-point delta as effectively tied.
| Benchmark | Mistral Large 3 | Mistral Medium 2505 | Winner | Δ |
|---|---|---|---|---|
| arena-elo | 1415.0 | 1387.0 | Mistral Large 3 | +28.0 |
Migration considerations
Concrete differences to wire through your stack before you flip traffic from one to the other.
- Context window changes down 49% when moving from Mistral Large 3 (256,000) to Mistral Medium 2505 (131,072). Re-check any prompt that relies on cramming long history or documents.
- Mistral Large 3 has capabilities Mistral Medium 2505 lacks: Vision input. Switching to Mistral Medium 2505 means re-architecting any flow that depends on these.
- Mistral Medium 2505 has capabilities Mistral Large 3 lacks: Structured output (JSON schema). Worth wiring through the agent design before commit.
- Provider changes from Azure AI Foundry to Mistral AI. API authentication, rate-limit policy, regional availability, and billing all shift. Most teams route through an OpenAI-compatible gateway (e.g., Future AGI Agent Command Center) so the swap is a single `base_url` change instead of an SDK rewrite.
How to A/B test Mistral Large 3 vs Mistral Medium 2505 in production
If you're stuck between the two, run them side-by-side on real traffic. Four steps the Future AGI team uses internally:
- 1. Point your existing OpenAI SDK at
https://gateway.futureagi.com/v1. No code change beyondbase_urland a virtual key. - 2. Mark Mistral Large 3 primary, mirror 20% of traffic to Mistral Medium 2505 in shadow mode. Both responses are logged; only the primary is served to users.
- 3. Score every shadow response with an evaluator — faithfulness, tool-call correctness, response latency, cost. Built-in evaluators in ai-evaluation cover the common axes.
- 4. Compare cohort-level metrics after two weeks. Switch primary when the candidate wins on what matters to your workload — and stays within your latency budget.
Full walkthrough on the Agent Command Center page.
FAQ — Mistral Large 3 vs Mistral Medium 2505
Which is cheaper, Mistral Large 3 or Mistral Medium 2505? ▾
Mistral Large 3 is cheaper by roughly 17% on a blended input + output token mix. Input prices are $0.500/M for Mistral Large 3 versus $0.400/M for Mistral Medium 2505; output prices are $1.50/M versus $2.00/M. The exact savings depend on your input:output ratio — use the live calculator above to plug in your own request shape.
What is the context window of Mistral Large 3 versus Mistral Medium 2505? ▾
Mistral Large 3 supports up to 256,000 tokens of context. Mistral Medium 2505 supports up to 131,072 tokens. Mistral Large 3 has the larger window by a factor of 2.0x, which matters for long-document RAG, multi-turn agent sessions, and tasks that need to keep an entire codebase in working memory.
Do Mistral Large 3 and Mistral Medium 2505 both support tool calling? ▾
Yes — both Mistral Large 3 and Mistral Medium 2505 support native function calling. Both also support structured output via JSON schema, so an agent can be ported between them with the same tool definitions.
Can Mistral Large 3 and Mistral Medium 2505 process images? ▾
Mistral Large 3 accepts native image input. Mistral Medium 2505 does not — you would need to route image-heavy workloads through Mistral Large 3 or add a separate vision model in front of Mistral Medium 2505.
When should I choose Mistral Large 3 over Mistral Medium 2505? ▾
You're cost-sensitive at scale — Mistral Large 3 runs ~17% cheaper on a blended in+out token mix, compounding into thousands of dollars per month at production volume. Your inputs include screenshots, diagrams, or product photos — Mistral Large 3 accepts image input natively, the other doesn't. On arena-elo, Mistral Large 3 scores 28.0 points higher — if your workload pattern matches that benchmark's task shape, the gap is meaningful.
When should I choose Mistral Medium 2505 over Mistral Large 3? ▾
On the data this page surfaces, Mistral Medium 2505 is the right pick when Mistral Large 3's lower price or different capability profile aren't a fit for your workload. Run the live calculator above against your actual usage shape to confirm.
How do I A/B test Mistral Large 3 against Mistral Medium 2505 in production? ▾
Route both through an OpenAI-compatible gateway like Future AGI Agent Command Center with shadow mode enabled. Send 100% of traffic to your primary model, mirror 10–20% to the candidate, score every response with an evaluator (faithfulness, tool-call correctness, response time), and compare cohort-level metrics for two weeks. Switch when the candidate wins on the metrics that matter to your workload and stays within your latency budget.