gpt-oss-20b vs Ternary Bonsai 27B

At a Glance

Compare
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.030Deepinfra · Sep 21, 2026Not reported
Output priceFrom · USD / 1M tokens$0.13Openrouter · Sep 22, 2026Not reported
Context windowMaximum documented tokens131K262K
Model facts checkedAug 28, 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

Fieldgpt-oss-20bTernary Bonsai 27B
DeveloperOpenAIPrismML
FamilyGpt OssBonsai 27b
Modelgpt-oss-20bTernary Bonsai 27B
Versiongpt-oss-20bTernary Bonsai 27B
Lifecycleactiveactive
ReleasedUnknown2026-07-04
Knowledge cutoffUnknownUnknown
Input modalitiesTextText, Image
Output modalitiesTextText
Context window131K262K
Total parameters20.9B27B
Active parameters3.6BUnknown
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableYesYes
Self-hostableYesYes
Provider accessDeepinfra (Standard), Groq (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Serverless, Standard)Together Ai (Standard)
Capabilitieschat, generation, reasoning, toolschat, generation, reasoning, tools, vision
Base modelUnknownQwen3.6 27B
Effective bit widthUnknown1.58 bits per weight
Language model sizeUnknown6.66 GiB
Weight formatUnknownTernary Q2_0

gpt-oss-20b Capabilities

chatgenerationreasoningtools
Serving providers5
Canonical IDopenai/gpt-oss-20b

Ternary Bonsai 27B Capabilities

chatgenerationreasoningtoolsvision
Serving providers1
Canonical IDprism-ml/Ternary-Bonsai-27B

Primary Evidence

Sources and Freshness

Questions

gpt-oss-20b vs Ternary Bonsai 27B FAQs

Is gpt-oss-20b or Ternary Bonsai 27B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both gpt-oss-20b and Ternary Bonsai 27B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, gpt-oss-20b or Ternary Bonsai 27B?+

Only gpt-oss-20b has a directly sourced input price: $0.030 per million tokens. Only gpt-oss-20b has a directly sourced output price: $0.13 per million tokens.

Which has a larger context window, gpt-oss-20b or Ternary Bonsai 27B?+

Ternary Bonsai 27B has the larger sourced context window. gpt-oss-20b supports 131K and Ternary Bonsai 27B supports 262K.

Which performs better in benchmarks, gpt-oss-20b or Ternary Bonsai 27B?+

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

Can gpt-oss-20b or Ternary Bonsai 27B be self-hosted?+

Both models have the same recorded self-hosting status: supported. gpt-oss-20b is open weight; Ternary Bonsai 27B is open weight.

Can gpt-oss-20b and Ternary Bonsai 27B understand images?+

gpt-oss-20b is not documented with image input; Ternary Bonsai 27B is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, gpt-oss-20b or Ternary Bonsai 27B?+

Neither has a larger sourced maximum output. gpt-oss-20b is — and Ternary Bonsai 27B is —.

Do gpt-oss-20b and Ternary Bonsai 27B support reasoning and tool use?+

gpt-oss-20b: reasoning and tool calling. Ternary Bonsai 27B: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, gpt-oss-20b or Ternary Bonsai 27B?+

gpt-oss-20b has 5 sourced provider routes; Ternary Bonsai 27B has 1, so gpt-oss-20b has broader tracked availability.

Which offers better value, gpt-oss-20b or Ternary Bonsai 27B?+

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