LLM·Dex

Mistral Small vs Sonar Large

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Verdict by category
  • PriceMistral Small

    Mistral Small is roughly 1.7× cheaper on output tokens ($0.60 vs $1.00 per 1M).

  • Context windowMistral Small

    Mistral Small accepts 128K tokens vs 127K, 1.0× the room for long documents and codebases.

  • BenchmarksTie

    No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.

  • ModalitiesTie

    Both handle text.

  • OpennessMistral Small

    Mistral Small ships open weights (Apache-2.0); Sonar Large is API-only.

On balance Mistral Small edges ahead, winning 3 of 5 categories against Sonar Large's 0. Mistral Small is roughly 1.7× cheaper on output tokens ($0.60 vs $1.00 per 1M). Mistral Small accepts 128K tokens vs 127K, 1.0× the room for long documents and codebases.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. Both target the same set of modalities (text), so the deciding factors are price, context, and raw quality. Mistral Small ships open weights (Apache-2.0); Sonar Large is API-only.

Sonar Large is the newer of the two, released 2 months after Mistral Small, which usually means a more recent knowledge cutoff and updated safety post-training. Mistral Small is usually picked for cheapest llm and fastest llm workloads, while Sonar Large sees more deployments in research agent and rag. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecMistral SmallSonar Large
ProviderMistralPerplexity
ReleasedSep 2024Nov 2024
Modalitiestexttext
Context window128K tokens127K tokens
Max output,,
Input · 1M$0.20 / 1M tokens$1.00 / 1M tokens
Output · 1M$0.60 / 1M tokens$1.00 / 1M tokens
Knowledge cutoff,,
Open weightsYes (Apache-2.0)No
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$1.50 vs $4.50
  • Heavy usage, 1M in / 500k out per day$15.00 vs $45.00
  • RAG workload, 5M in / 200k out per day$33.60 vs $156

Light usage, 100k in / 50k out per day: $1.50 vs $4.50 per month, model A comes out ahead. Heavy usage, 1M in / 500k out per day: $15.00 vs $45.00 per month, model A comes out ahead. RAG workload, 5M in / 200k out per day: $33.60 vs $156 per month, model A comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Mistral Small$0.050
  • Sonar Large$0.150

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.
Pick Mistral Small if

Mistral Small fits when…

  • Apache-2.0 open-weight
  • Fast and cheap
  • Cost-sensitive workloads, 1.7× cheaper than Sonar Large on output tokens.
  • Self-hosting and on-prem requirements, open weights (Apache-2.0).
Pick Sonar Large if

Sonar Large fits when…

  • Web-search grounded
  • Citation-first output
  • Cheap
Don't want either?

Consider Mistral Large 2

Mistral's flagship API model, strong on code and reasoning, EU-friendly hosting.

Frequently asked

  • Is Mistral Small or Sonar Large cheaper?
    Mistral Small is cheaper at $0.60 / 1M tokens per million output tokens, vs $1.00 / 1M tokens for Sonar Large.
  • Which has the larger context window?
    Mistral Small accepts 128K tokens vs 127K for Sonar Large.
  • Is Mistral Small or Sonar Large better for coding?
    Both Mistral Small and Sonar Large are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Mistral Small ships open weights (Apache-2.0). Sonar Large is API-only.
  • When were Mistral Small and Sonar Large released?
    Mistral Small was released by Mistral on 2024-09-18. Sonar Large was released by Perplexity on 2024-11-19.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.