Is Mistral Medium or Sonar Large cheaper?

Sonar Large is cheaper at $1.00 / 1M tokens per million output tokens, vs $2.00 / 1M tokens for Mistral Medium.

Which has the larger context window?

Mistral Medium accepts 128K tokens vs 127K for Sonar Large.

Is Mistral Medium or Sonar Large better for coding?

Both Mistral Medium 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?

Neither model ships open weights, both are accessible only via their respective providers' APIs.

When were Mistral Medium and Sonar Large released?

Mistral Medium was released by Mistral on 2024-12-18. Sonar Large was released by Perplexity on 2024-11-19.

Is Mistral Medium or Sonar Large cheaper?

Sonar Large is cheaper at $1.00 / 1M tokens per million output tokens, vs $2.00 / 1M tokens for Mistral Medium.

Which has the larger context window?

Mistral Medium accepts 128K tokens vs 127K for Sonar Large.

Is Mistral Medium or Sonar Large better for coding?

Both Mistral Medium 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?

Neither model ships open weights, both are accessible only via their respective providers' APIs.

When were Mistral Medium and Sonar Large released?

Mistral Medium was released by Mistral on 2024-12-18. Sonar Large was released by Perplexity on 2024-11-19.

Mistral Medium 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.

UpdatedApr 30, 2026

Mistral Medium specs · Sonar Large specs

Verdict by category

PriceSonar Large
Sonar Large is roughly 2.0× cheaper on output tokens ($1.00 vs $2.00 per 1M).
Context windowMistral Medium
Mistral Medium 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.
OpennessTie
Both are closed-weight, API-only.

It's a genuine coin-flip between Mistral Medium and Sonar Large: 1 category wins each, with the rest tied. Sonar Large is roughly 2.0× cheaper on output tokens ($1.00 vs $2.00 per 1M). Mistral Medium 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. Both are closed-weight, API-only.

Both shipped within roughly a month of each other in 2024, so they share the same generation of training data and tooling. Mistral Medium is usually picked for customer support and chatbots 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

Spec	Mistral Medium	Sonar Large
Provider	Mistral	Perplexity
Released	Dec 2024	Nov 2024
Modalities	text	text
Context window	128K tokens	127K tokens
Max output	,	,
Input · 1M	$0.40 / 1M tokens	$1.00 / 1M tokens
Output · 1M	$2.00 / 1M tokens	$1.00 / 1M tokens
Knowledge cutoff	,	,
Open weights	No	No
API available	Yes	Yes

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$4.20 vs $4.50
Heavy usage, 1M in / 500k out per day$42.00 vs $45.00
RAG workload, 5M in / 200k out per day$72.00 vs $156

Light usage, 100k in / 50k out per day: $4.20 vs $4.50 per month, model A comes out ahead. Heavy usage, 1M in / 500k out per day: $42.00 vs $45.00 per month, model A comes out ahead. RAG workload, 5M in / 200k out per day: $72.00 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.

Input tokens / dayOutput tokens / dayHorizon

Mistral Medium$0.140
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 Medium if

Mistral Medium fits when…

Mid-tier balance
EU-friendly

Pick Sonar Large if

Sonar Large fits when…

Web-search grounded
Citation-first output
Cheap
Cost-sensitive workloads, 2.0× cheaper than Mistral Medium on output tokens.

Don't want either?

Consider Mistral Large 2

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

See Mistral Large 2 specs Mistral Medium vs Mistral Large 2 Sonar Large vs Mistral Large 2

Frequently asked

Is Mistral Medium or Sonar Large cheaper?
Sonar Large is cheaper at $1.00 / 1M tokens per million output tokens, vs $2.00 / 1M tokens for Mistral Medium.
Which has the larger context window?
Mistral Medium accepts 128K tokens vs 127K for Sonar Large.
Is Mistral Medium or Sonar Large better for coding?
Both Mistral Medium 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?
Neither model ships open weights, both are accessible only via their respective providers' APIs.
When were Mistral Medium and Sonar Large released?
Mistral Medium was released by Mistral on 2024-12-18. Sonar Large was released by Perplexity on 2024-11-19.

Friday digest

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