Mistral Large vs Mistral Small 4
Mistral Large (2024) and Mistral Small 4 (2026) are compact production models from MistralAI. Mistral Large ships a 32k-token context window, while Mistral Small 4 ships a 256K-token context window. On pricing, Mistral Small 4 costs $0.15/1M input tokens versus $0.32/1M for the alternative. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit. It focuses on practical selection signals rather than broad model-family marketing.
Mistral Small 4 is ~113% cheaper at $0.15/1M; pay for Mistral Large only for vision-heavy evaluation.
Decision scorecard
Local evidence first| Signal | Mistral Large | Mistral Small 4 |
|---|---|---|
| Decision fit | Agents, Vision, and Classification | RAG, Agents, and Long context |
| Context window | 32k | 256K |
| Cheapest output | $0.96/1M tokens | $0.6/1M tokens |
| Provider routes | 8 tracked | 3 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Mistral Large has broader tracked provider coverage for fallback and procurement flexibility.
- Mistral Large uniquely exposes Structured outputs in local model data.
- Local decision data tags Mistral Large for Agents, Vision, and Classification.
- Mistral Small 4 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Mistral Small 4 has the lower cheapest tracked output price at $0.6/1M tokens.
- Mistral Small 4 uniquely exposes Multimodal in local model data.
- Local decision data tags Mistral Small 4 for RAG, Agents, and Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Mistral Large
$496
Cheapest tracked route: GCP Vertex AI
Mistral Small 4
$270
Cheapest tracked route: OpenRouter
Estimated monthly gap: $226. Batch, cache, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter, NVIDIA NIM, and Mistral AI Studio; start route-level A/B tests there.
- Mistral Small 4 is $0.36/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Structured outputs before moving production traffic.
- Mistral Small 4 adds Multimodal in local capability data.
- Provider overlap exists on NVIDIA NIM, Mistral AI Studio, and OpenRouter; start route-level A/B tests there.
- Mistral Large is $0.36/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Check replacement coverage for Multimodal before moving production traffic.
- Mistral Large adds Structured outputs in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2024-02-08 | 2026-03-16 |
| Context window | 32k | 256K |
| Parameters | — | 119B (6.5B active) |
| Architecture | - | moe |
| License | Proprietary | Apache 2.0 |
| Knowledge cutoff | 2024-03 | 2025-06 |
Pricing and availability
| Pricing attribute | Mistral Large | Mistral Small 4 |
|---|---|---|
| Input price | $0.32/1M tokens | $0.15/1M tokens |
| Output price | $0.96/1M tokens | $0.6/1M tokens |
| Providers |
Capabilities
| Capability | Mistral Large | Mistral Small 4 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | No | Yes |
| Reasoning | No | No |
| Function calling | Yes | Yes |
| Tool use | Yes | Yes |
| Structured outputs | Yes | No |
| Code execution | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on multimodal input: Mistral Small 4 and structured outputs: Mistral Large. Both models share vision, 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 lists $0.32/1M input and $0.96/1M output tokens, while Mistral Small 4 lists $0.15/1M input and $0.6/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Small 4 lower by about $0.23 per million blended tokens. Availability is 8 providers versus 3, so concentration risk also matters.
Choose Mistral Large when vision-heavy evaluation and broader provider choice are central to the workload. Choose Mistral Small 4 when long-context analysis, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency.
FAQ
Which has a larger context window, Mistral Large or Mistral Small 4?
Mistral Small 4 supports 256K tokens, while Mistral Large supports 32k 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 or Mistral Small 4?
Mistral Small 4 is cheaper on tracked token pricing. Mistral Large costs $0.32/1M input and $0.96/1M output tokens. Mistral Small 4 costs $0.15/1M input and $0.6/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Mistral Large or Mistral Small 4 open source?
Mistral Large is listed under Proprietary. Mistral Small 4 is listed under Apache 2.0. 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 or Mistral Small 4?
Both Mistral Large and Mistral Small 4 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Mistral Large or Mistral Small 4?
Mistral Small 4 has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Mistral Large and Mistral Small 4?
Mistral Large is available on NVIDIA NIM, Microsoft Foundry, AWS Bedrock, Mistral AI Studio, and IBM watsonx. Mistral Small 4 is available on OpenRouter, NVIDIA NIM, and Mistral AI Studio. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-05-19. Data sourced from public model cards and provider documentation.