Mistral Small 4 119B 2603 vs Sonar Pro

At a Glance

Compare
Sonar ProPerplexity
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.15Openrouter · Aug 29, 2026$3.00Openrouter · Sep 22, 2026
Output priceFrom · USD / 1M tokens$0.60Openrouter · Aug 29, 2026$15.00Openrouter · Sep 22, 2026
Context windowMaximum documented tokens1,049K200K
Model facts checkedAug 28, 2026View model evidence →Aug 29, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

FieldMistral-Small-4-119B-2603Sonar Pro
DeveloperMistral AIPerplexity
FamilyMistral Small 4 119b 2603Sonar
ModelMistral-Small-4-119B-2603Sonar Pro
VersionMistral-Small-4-119B-2603Sonar Pro
Lifecycleactiveactive
ReleasedUnknownUnknown
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageText
Output modalitiesTextText
Context window1,049K200K
Total parameters119.4BUnknown
Active parameters6.5BUnknown
Licenseapache-2.0Unknown
Open weightsYesNo
API availableYesYes
Self-hostableYesNo
Provider accessOpenrouter (Standard)Openrouter (Standard), Perplexity (Standard)
Capabilitieschat, generation, reasoning, toolschat, citations, search

Mistral Small 4 119B 2603 Capabilities

chatgenerationreasoningtools
Serving providers1
Canonical IDmistralai/Mistral-Small-4-119B-2603

Sonar Pro Capabilities

chatcitationssearch
Serving providers2
Canonical IDperplexity/sonar-pro

Primary Evidence

Sources and Freshness

Questions

Mistral Small 4 119B 2603 vs Sonar Pro FAQs

Is Mistral Small 4 119B 2603 or Sonar Pro better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Mistral Small 4 119B 2603 and Sonar Pro, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Mistral Small 4 119B 2603 or Sonar Pro?+

Mistral Small 4 119B 2603 is $0.15 and Sonar Pro is $3.00 per million tokens, so Mistral Small 4 119B 2603 is cheaper on this metric. Mistral Small 4 119B 2603 is $0.60 and Sonar Pro is $15.00 per million tokens, so Mistral Small 4 119B 2603 is cheaper on this metric.

Which has a larger context window, Mistral Small 4 119B 2603 or Sonar Pro?+

Mistral Small 4 119B 2603 has the larger sourced context window. Mistral Small 4 119B 2603 supports 1,049K and Sonar Pro supports 200K.

Which performs better in benchmarks, Mistral Small 4 119B 2603 or Sonar Pro?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can Mistral Small 4 119B 2603 or Sonar Pro be self-hosted?+

Mistral Small 4 119B 2603 is the only model in this pair currently marked as self-hostable. Mistral Small 4 119B 2603 is open weight; Sonar Pro is not marked open weight.

Can Mistral Small 4 119B 2603 and Sonar Pro understand images?+

Mistral Small 4 119B 2603 is documented with image input; Sonar Pro is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Mistral Small 4 119B 2603 or Sonar Pro?+

Neither has a larger sourced maximum output. Mistral Small 4 119B 2603 is — and Sonar Pro is —.

Do Mistral Small 4 119B 2603 and Sonar Pro support reasoning and tool use?+

Mistral Small 4 119B 2603: reasoning, tool calling, and image input. Sonar Pro: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Mistral Small 4 119B 2603 or Sonar Pro?+

Mistral Small 4 119B 2603 has 1 sourced provider route; Sonar Pro has 2, so Sonar Pro has broader tracked availability.

Which offers better value, Mistral Small 4 119B 2603 or Sonar Pro?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback