Gemini 2.5 Pro vs Ternary Bonsai 4B

At a Glance

Compare
Gemini 2.5 ProGoogle DeepMind
Pricing and Limits
Input priceFrom · USD / 1M tokens$1.25Google AI · Aug 29, 2026Not reported
Output priceFrom · USD / 1M tokens$10.00Google AI · Aug 29, 2026Not reported
Context windowMaximum documented tokens1,049K33K
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

FieldGemini 2.5 ProTernary Bonsai 4B
DeveloperGoogle DeepMindPrismML
FamilyGemini 2 5Bonsai 4b
ModelGemini 2.5 ProTernary Bonsai 4B
VersionGemini 2.5 ProTernary Bonsai 4B
Lifecycleactiveactive
ReleasedUnknown2026-04-18
Knowledge cutoff2025-01-01Unknown
Input modalitiesText, Image, Video, Audio, DocumentText
Output modalitiesTextText
Context window1,049K33K
Total parametersUnknown4B
Active parametersUnknownUnknown
LicenseUnknownapache-2.0
Open weightsNoYes
API availableYesNo
Self-hostableNoYes
Provider accessGoogle AI (Standard), Google Gemini (Standard)Unknown
Capabilitieschat, generation, reasoning, toolschat, generation
Effective bit widthUnknown1.58 bits per weight
Weight sizeUnknown1.07 GB
Weight formatUnknownTernary Q2_0

Gemini 2.5 Pro Capabilities

chatgenerationreasoningtools
Serving providers2
Canonical IDgoogle-deepmind/gemini-2.5-pro

Ternary Bonsai 4B Capabilities

chatgeneration
Serving providers0
Canonical IDprism-ml/Ternary-Bonsai-4B

Primary Evidence

Sources and Freshness

Questions

Gemini 2.5 Pro vs Ternary Bonsai 4B FAQs

Is Gemini 2.5 Pro or Ternary Bonsai 4B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Gemini 2.5 Pro and Ternary Bonsai 4B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Gemini 2.5 Pro or Ternary Bonsai 4B?+

Only Gemini 2.5 Pro has a directly sourced input price: $1.25 per million tokens. Only Gemini 2.5 Pro has a directly sourced output price: $10.00 per million tokens.

Which has a larger context window, Gemini 2.5 Pro or Ternary Bonsai 4B?+

Gemini 2.5 Pro has the larger sourced context window. Gemini 2.5 Pro supports 1,049K and Ternary Bonsai 4B supports 33K.

Which performs better in benchmarks, Gemini 2.5 Pro or Ternary Bonsai 4B?+

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

Can Gemini 2.5 Pro or Ternary Bonsai 4B be self-hosted?+

Ternary Bonsai 4B is the only model in this pair currently marked as self-hostable. Gemini 2.5 Pro is not marked open weight; Ternary Bonsai 4B is open weight.

Can Gemini 2.5 Pro and Ternary Bonsai 4B understand images?+

Gemini 2.5 Pro is documented with image input; Ternary Bonsai 4B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Gemini 2.5 Pro or Ternary Bonsai 4B?+

Neither has a larger sourced maximum output. Gemini 2.5 Pro is 66K and Ternary Bonsai 4B is —.

Do Gemini 2.5 Pro and Ternary Bonsai 4B support reasoning and tool use?+

Gemini 2.5 Pro: reasoning, tool calling, and image input. Ternary Bonsai 4B: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Gemini 2.5 Pro or Ternary Bonsai 4B?+

Gemini 2.5 Pro has 2 sourced provider routes; Ternary Bonsai 4B has 0, so Gemini 2.5 Pro has broader tracked availability.

Which offers better value, Gemini 2.5 Pro or Ternary Bonsai 4B?+

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