LLM Reference

Mistral Medium vs Nemotron 4 340B

Mistral Medium (2023) and Nemotron 4 340B (2025) are compact production models from MistralAI and NVIDIA AI. Mistral Medium ships a 32k-token context window, while Nemotron 4 340B ships a 4k-token context window. On pricing, Mistral Medium costs $0.40/1M input tokens versus $4.20/1M 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 Medium is ~950% cheaper at $0.40/1M; pay for Nemotron 4 340B only for provider fit.

Decision scorecard

Local evidence first
SignalMistral MediumNemotron 4 340B
Best forprovider-routed productionprovider-routed production
Decision fitCoding, Classification, and JSON / Tool useClassification and JSON / Tool use
Context window32k4k
Cheapest output$2/1M tokens$4.20/1M tokens
Provider routes2 tracked2 tracked
Shared benchmarks0 rows0 rows

Decision tradeoffs

Choose Mistral Medium when...
  • Mistral Medium has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Mistral Medium has the lower cheapest tracked output price at $2/1M tokens.
  • Local decision data tags Mistral Medium for Coding, Classification, and JSON / Tool use.
Choose Nemotron 4 340B when...
  • Local decision data tags Nemotron 4 340B for Classification and JSON / Tool use.

Monthly cost at traffic

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

Lower estimate Mistral Medium

Mistral Medium

$820

Cheapest tracked route/tier: OpenRouter

Nemotron 4 340B

$4,410

Cheapest tracked route/tier: DeepInfra

Estimated monthly gap: $3,590. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Medium -> Nemotron 4 340B
  • No overlapping tracked provider route is sourced for Mistral Medium and Nemotron 4 340B; plan for SDK, billing, or endpoint changes.
  • Nemotron 4 340B is $2.20/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
Nemotron 4 340B -> Mistral Medium
  • No overlapping tracked provider route is sourced for Nemotron 4 340B and Mistral Medium; plan for SDK, billing, or endpoint changes.
  • Mistral Medium is $2.20/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.

Specs

Specification
Released2023-12-112025-02-27
Context window32k4k
Parameters340B
Architecturedecoder onlydecoder only
LicenseProprietaryNVIDIA Open Model
OpennessProprietaryOpen weights
Commercial useCommercial use with conditionsCommercial use allowed
Knowledge cutoff--

Pricing and availability

Pricing attributeMistral MediumNemotron 4 340B
Input price$0.40/1M tokens$4.20/1M tokens
Output price$2/1M tokens$4.20/1M tokens
Providers

Capabilities

CapabilityMistral MediumNemotron 4 340B
VisionNoNo
MultimodalNoNo
ReasoningNoNo
Function callingNoNo
Tool useNoNo
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark rows are currently sourced for this pair.

Deep dive

The capability footprint is close: both models cover structured outputs. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.

For cost, Mistral Medium lists $0.40/1M input and $2/1M output tokens on the cheapest tracked provider, while Nemotron 4 340B lists $4.20/1M input and $4.20/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Mistral Medium lower by about $3.32 per million blended tokens. Availability is 2 providers versus 2, so concentration risk also matters.

Choose Mistral Medium when long-context analysis, larger context windows, and lower input-token cost are central to the workload. Choose Nemotron 4 340B when provider fit 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 Medium or Nemotron 4 340B?

Mistral Medium supports 32k tokens, while Nemotron 4 340B supports 4k 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 Medium or Nemotron 4 340B?

Mistral Medium is cheaper on tracked token pricing. Mistral Medium costs $0.40/1M input and $2/1M output tokens. Nemotron 4 340B costs $4.20/1M input and $4.20/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Mistral Medium or Nemotron 4 340B open source?

Mistral Medium is listed under Proprietary. Nemotron 4 340B is listed under NVIDIA Open Model. 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 structured outputs, Mistral Medium or Nemotron 4 340B?

Both Mistral Medium and Nemotron 4 340B expose structured outputs. 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 Medium and Nemotron 4 340B?

Mistral Medium is available on Mistral AI Studio and OpenRouter. Nemotron 4 340B is available on NVIDIA NIM and DeepInfra. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

When should I pick Mistral Medium over Nemotron 4 340B?

Mistral Medium is ~950% cheaper at $0.40/1M; pay for Nemotron 4 340B only for provider fit. If your workload also depends on long-context analysis, start with Mistral Medium; if it depends on provider fit, run the same evaluation with Nemotron 4 340B.

Continue comparing

Last reviewed: 2026-05-19. Data sourced from public model cards and provider documentation.