gpt-oss-120b vs Bonsai 8B
At a Glance
| Compare |  gpt-oss-120bOpenAI |  Bonsai 8BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.037Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $0.17Deepinfra ↗ · Sep 23, 2026 | Not reported |
| Context windowMaximum documented tokens | 131K | 66K |
| Model facts checked | Aug 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
Side-by-Side Facts
| Field | gpt-oss-120b | Bonsai 8B |
|---|---|---|
| Developer | OpenAI | PrismML |
| Family | Gpt Oss 120b | Bonsai 8b |
| Model | gpt-oss-120b | Bonsai 8B |
| Version | gpt-oss-120b | Bonsai 8B |
| Lifecycle | active | active |
| Released | Unknown | 2026-03-18 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
| Context window | 131K | 66K |
| Total parameters | 116.8B | 8.2B |
| Active parameters | 5.1B | Unknown |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | No |
| Self-hostable | Yes | Yes |
| Provider access | Cerebras (Standard), Deepinfra (Standard), Fireworks Ai (Serverless, Standard), Groq (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Serverless, Standard) | Unknown |
| Capabilities | chat, generation, reasoning, tools | chat, generation |
| Effective bit width | Unknown | 1 bit per weight |
| Weight size | Unknown | 1.16 GB |
| Weight format | Unknown | Binary Q1_0 |
gpt-oss-120b Capabilities
Bonsai 8B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
GPT-6 AstraOpenAI | vs | gpt-oss-120bOpenAI | family variantstext |
Claude Fable 5.1Anthropic | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
 Gemini 3.1 ProGoogle DeepMind | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
gpt-oss-120bOpenAI | vs | Grok 4.6xAI | cross-developer peerstext |
gpt-oss-120bOpenAI | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
 Kimi-K3Moonshot AI | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
gpt-oss-120bOpenAI | vs |  GLM-5.3Z.ai | cross-developer peerstext |
gpt-oss-120bOpenAI | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
 Mistral Large 3Mistral AI | vs | gpt-oss-120bOpenAI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
gpt-oss-120b vs Bonsai 8B FAQs
Is gpt-oss-120b or Bonsai 8B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both gpt-oss-120b and Bonsai 8B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, gpt-oss-120b or Bonsai 8B?+
Only gpt-oss-120b has a directly sourced input price: $0.037 per million tokens. Only gpt-oss-120b has a directly sourced output price: $0.17 per million tokens.
Which has a larger context window, gpt-oss-120b or Bonsai 8B?+
gpt-oss-120b has the larger sourced context window. gpt-oss-120b supports 131K and Bonsai 8B supports 66K.
Which performs better in benchmarks, gpt-oss-120b or Bonsai 8B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can gpt-oss-120b or Bonsai 8B be self-hosted?+
Both models have the same recorded self-hosting status: supported. gpt-oss-120b is open weight; Bonsai 8B is open weight.
Can gpt-oss-120b and Bonsai 8B understand images?+
gpt-oss-120b is not documented with image input; Bonsai 8B is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, gpt-oss-120b or Bonsai 8B?+
Neither has a larger sourced maximum output. gpt-oss-120b is — and Bonsai 8B is —.
Do gpt-oss-120b and Bonsai 8B support reasoning and tool use?+
gpt-oss-120b: reasoning and tool calling. Bonsai 8B: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, gpt-oss-120b or Bonsai 8B?+
gpt-oss-120b has 7 sourced provider routes; Bonsai 8B has 0, so gpt-oss-120b has broader tracked availability.
Which offers better value, gpt-oss-120b or Bonsai 8B?+
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.