Sonar Reasoning Pro vs Ternary Bonsai 1.7B

At a Glance

Compare
Pricing and Limits
Input priceFrom · USD / 1M tokens$2.00Openrouter · Sep 22, 2026Not reported
Output priceFrom · USD / 1M tokens$8.00Openrouter · Sep 22, 2026Not reported
Context windowMaximum documented tokens128K33K
Model facts checkedAug 29, 2026View model evidence →Sep 18, 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

FieldSonar Reasoning ProTernary Bonsai 1.7B
DeveloperPerplexityPrismML
FamilySonarBonsai 1 7b
ModelSonar Reasoning ProTernary Bonsai 1.7B
VersionSonar Reasoning ProTernary Bonsai 1.7B
Lifecycleactiveactive
ReleasedUnknown2026-04-18
Knowledge cutoffUnknownUnknown
Input modalitiesTextText
Output modalitiesTextText
Context window128K33K
Total parametersUnknown1.7B
Active parametersUnknownUnknown
LicenseUnknownapache-2.0
Open weightsNoYes
API availableYesNo
Self-hostableNoYes
Provider accessOpenrouter (Standard), Perplexity (Standard)Unknown
Capabilitieschat, citations, reasoning, searchchat, generation
Effective bit widthUnknown1.58 bits per weight
Weight sizeUnknown0.46 GB
Weight formatUnknownTernary Q2_0

Sonar Reasoning Pro Capabilities

chatcitationsreasoningsearch
Serving providers2
Canonical IDperplexity/sonar-reasoning-pro

Ternary Bonsai 1.7B Capabilities

chatgeneration
Serving providers0
Canonical IDprism-ml/Ternary-Bonsai-1.7B

Primary Evidence

Sources and Freshness

Questions

Sonar Reasoning Pro vs Ternary Bonsai 1.7B FAQs

Is Sonar Reasoning Pro or Ternary Bonsai 1.7B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Sonar Reasoning Pro and Ternary Bonsai 1.7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

Only Sonar Reasoning Pro has a directly sourced input price: $2.00 per million tokens. Only Sonar Reasoning Pro has a directly sourced output price: $8.00 per million tokens.

Which has a larger context window, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

Sonar Reasoning Pro has the larger sourced context window. Sonar Reasoning Pro supports 128K and Ternary Bonsai 1.7B supports 33K.

Which performs better in benchmarks, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

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

Can Sonar Reasoning Pro or Ternary Bonsai 1.7B be self-hosted?+

Ternary Bonsai 1.7B is the only model in this pair currently marked as self-hostable. Sonar Reasoning Pro is not marked open weight; Ternary Bonsai 1.7B is open weight.

Can Sonar Reasoning Pro and Ternary Bonsai 1.7B understand images?+

Sonar Reasoning Pro is not documented with image input; Ternary Bonsai 1.7B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

Neither has a larger sourced maximum output. Sonar Reasoning Pro is — and Ternary Bonsai 1.7B is —.

Do Sonar Reasoning Pro and Ternary Bonsai 1.7B support reasoning and tool use?+

Sonar Reasoning Pro: reasoning. Ternary Bonsai 1.7B: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

Sonar Reasoning Pro has 2 sourced provider routes; Ternary Bonsai 1.7B has 0, so Sonar Reasoning Pro has broader tracked availability.

Which offers better value, Sonar Reasoning Pro or Ternary Bonsai 1.7B?+

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