Mistral Large 2 vs Mistral Medium 3.5

Name: Mistral Large 2
Author: MistralAI

Mistral Large 2 (2025) and Mistral Medium 3.5 (2026) are frontier reasoning models from MistralAI. Mistral Large 2 ships a 128k-token context window, while Mistral Medium 3.5 ships a 256k-token context window. On MMLU PRO, Mistral Medium 3.5 leads by 10.1 pts. On pricing, Mistral Large 2 costs $0.48/1M input tokens versus $1.50/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Mistral Large 2 is ~213% cheaper at $0.48/1M; pay for Mistral Medium 3.5 only for reasoning depth.

Decision scorecard

Local evidence first

Signal	Mistral Large 2	Mistral Medium 3.5	How to read it
Best for	multimodal apps, tool-calling agents, and provider-routed production	reasoning-heavy apps, multimodal apps, and tool-calling agents	Use-case synthesis from product type, capability flags, context, and provider data.
Decision fit	Coding, RAG, and Agents	Coding, RAG, and Agents	Primary workload tags from local decision data.
Context window	128k	256k	Higher is better when prompts, retrieval chunks, or transcripts are large.
Cheapest output	$2.40/1M tokens	$7.50/1M tokens	Cheapest tracked provider route; verify your exact region and tier.
Provider routes	4 tracked	3 tracked	Broader coverage can reduce vendor lock-in and fallback risk.
Shared benchmarks	1 rows	MMLU PRO leader	Visible benchmark lead is 10.1 points on MMLU PRO.

Decision tradeoffs

Choose Mistral Large 2 when...

Mistral Large 2 has the lower cheapest tracked output price at $2.40/1M tokens.
Mistral Large 2 has broader tracked provider coverage for fallback and procurement flexibility.
Local decision data tags Mistral Large 2 for Coding, RAG, and Agents.

Choose Mistral Medium 3.5 when...

Mistral Medium 3.5 holds a shared-benchmark lead on MMLU PRO, ahead by 10.1 points.
Mistral Medium 3.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
Mistral Medium 3.5 uniquely exposes Reasoning in local model data.
Local decision data tags Mistral Medium 3.5 for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Mistral Large 2

Requests / monthInput tokens / requestOutput tokens / request

Mistral Large 2

$984

Cheapest tracked route/tier: AWS Bedrock

Mistral Medium 3.5

$3,075

Cheapest tracked route/tier: Mistral AI Studio

Estimated monthly gap: $2,091. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Large 2 -> Mistral Medium 3.5

Provider overlap exists on Mistral AI Studio and OpenRouter; start route-level A/B tests there.
Mistral Medium 3.5 is $5.10/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
Mistral Medium 3.5 adds Reasoning in local capability data.

Mistral Medium 3.5 -> Mistral Large 2

Provider overlap exists on OpenRouter and Mistral AI Studio; start route-level A/B tests there.
Mistral Large 2 is $5.10/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
Check replacement coverage for Reasoning before moving production traffic.

Specs

Specification	Mistral Large 2 MistralAI	Mistral Medium 3.5 MistralAI
Released	2025-11-25	2026-04-29
Context window	128k	256k
Parameters	123B	128B
Architecture	decoder only	decoder only
License	Mistral License	Proprietary
Openness	Open weights	Proprietary
Commercial use	Non-commercial only	Commercial use with conditions
Knowledge cutoff	2025-07	-

Pricing and availability

Pricing attribute	Mistral Large 2	Mistral Medium 3.5
Input price	$0.48/1M tokens	$1.50/1M tokens
Output price	$2.40/1M tokens	$7.50/1M tokens
Providers	OpenRouter IBM watsonx AWS Bedrock Mistral AI Studio	Mistral AI Studio OpenRouter Vercel AI Gateway

Capabilities

Capability	Mistral Large 2	Mistral Medium 3.5
Vision	Yes	Yes
Multimodal	Yes	Yes
Reasoning	No	Yes
Function calling	Yes	Yes
Tool use	Yes	Yes
Structured outputs	Yes	Yes
Code execution	No	No
IDE integration	No	No
Computer use	No	No
Parallel agents	No	No

Benchmarks

Benchmark	Mistral Large 2	Mistral Medium 3.5
MMLU PRO	69.7	79.8

Deep dive

On shared benchmark coverage, MMLU PRO has Mistral Large 2 at 69.7 and Mistral Medium 3.5 at 79.8, with Mistral Medium 3.5 ahead by 10.1 points. The largest visible gap is 10.1 points on MMLU PRO, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.

The capability footprint differs most on reasoning mode: Mistral Medium 3.5. Both models share vision, multimodal input, function calling, and tool use, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

For cost, Mistral Large 2 lists $0.48/1M input and $2.40/1M output tokens on the cheapest tracked provider, while Mistral Medium 3.5 lists $1.50/1M input and $7.50/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Large 2 lower by about $2.24 per million blended tokens. Availability is 4 providers versus 3, so concentration risk also matters.

Choose Mistral Large 2 when vision-heavy evaluation, lower input-token cost, and broader provider choice are central to the workload. Choose Mistral Medium 3.5 when reasoning depth and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.

FAQ

Which has a larger context window, Mistral Large 2 or Mistral Medium 3.5?

Mistral Medium 3.5 supports 256k tokens, while Mistral Large 2 supports 128k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, Mistral Large 2 or Mistral Medium 3.5?

Mistral Large 2 is cheaper on tracked token pricing. Mistral Large 2 costs $0.48/1M input and $2.40/1M output tokens. Mistral Medium 3.5 costs $1.50/1M input and $7.50/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Mistral Large 2 or Mistral Medium 3.5 open source?

Mistral Large 2 is listed under Mistral License. Mistral Medium 3.5 is listed under Proprietary. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for vision, Mistral Large 2 or Mistral Medium 3.5?

Both Mistral Large 2 and Mistral Medium 3.5 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Which is better for multimodal input, Mistral Large 2 or Mistral Medium 3.5?

Both Mistral Large 2 and Mistral Medium 3.5 expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run Mistral Large 2 and Mistral Medium 3.5?

Mistral Large 2 is available on OpenRouter, IBM watsonx, AWS Bedrock, and Mistral AI Studio. Mistral Medium 3.5 is available on Mistral AI Studio, OpenRouter, and Vercel AI Gateway. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Model pages

Labs and families

Related comparisons

Last reviewed: 2026-05-22. Data sourced from public model cards and provider documentation.

Both models

Mistral Large 2 Mistral Medium 3.5