Gemini Computer Use vs Bonsai 27B
At a Glance
| Compare |  Gemini Computer UseGoogle DeepMind |  Bonsai 27BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $1.25Google AI ↗ · Aug 29, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $10.00Google AI ↗ · Aug 29, 2026 | Not reported |
| Context windowMaximum documented tokens | 128K | 262K |
| Model facts checked | Aug 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
Side-by-Side Facts
| Field | Gemini Computer Use | Bonsai 27B |
|---|---|---|
| Developer | Google DeepMind | PrismML |
| Family | Gemini Tools | Bonsai 27b |
| Model | Gemini Computer Use | Bonsai 27B |
| Version | Gemini Computer Use | Bonsai 27B |
| Lifecycle | preview | active |
| Released | Unknown | 2026-07-04 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 128K | 262K |
| Total parameters | Unknown | 27B |
| Active parameters | Unknown | Unknown |
| License | Unknown | apache-2.0 |
| Open weights | No | Yes |
| API available | Yes | No |
| Self-hostable | No | Yes |
| Provider access | Google AI (Standard), Google Gemini (Standard) | Unknown |
| Capabilities | generation, reasoning, tools | chat, generation, reasoning, tools, vision |
| Base model | Unknown | Qwen3.6 27B |
| Effective bit width | Unknown | 1 bit per weight |
| Language model size | Unknown | 3.53 GiB |
| Weight format | Unknown | Binary Q1_0 |
Gemini Computer Use Capabilities
Bonsai 27B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Gemini Computer UseGoogle DeepMind | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | Gemini 3.1 ProGoogle DeepMind | family variantstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | Grok 4.6xAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
Gemini Computer Use vs Bonsai 27B FAQs
Is Gemini Computer Use or Bonsai 27B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Gemini Computer Use and Bonsai 27B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Gemini Computer Use or Bonsai 27B?+
Only Gemini Computer Use has a directly sourced input price: $1.25 per million tokens. Only Gemini Computer Use has a directly sourced output price: $10.00 per million tokens.
Which has a larger context window, Gemini Computer Use or Bonsai 27B?+
Bonsai 27B has the larger sourced context window. Gemini Computer Use supports 128K and Bonsai 27B supports 262K.
Which performs better in benchmarks, Gemini Computer Use or Bonsai 27B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Gemini Computer Use or Bonsai 27B be self-hosted?+
Bonsai 27B is the only model in this pair currently marked as self-hostable. Gemini Computer Use is not marked open weight; Bonsai 27B is open weight.
Can Gemini Computer Use and Bonsai 27B understand images?+
Gemini Computer Use is documented with image input; Bonsai 27B is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Gemini Computer Use or Bonsai 27B?+
Neither has a larger sourced maximum output. Gemini Computer Use is 64K and Bonsai 27B is —.
Do Gemini Computer Use and Bonsai 27B support reasoning and tool use?+
Gemini Computer Use: reasoning, tool calling, and image input. Bonsai 27B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Gemini Computer Use or Bonsai 27B?+
Gemini Computer Use has 2 sourced provider routes; Bonsai 27B has 0, so Gemini Computer Use has broader tracked availability.
Which offers better value, Gemini Computer Use or 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.