Ternary Bonsai 2 27B
by PrismMLChat
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...
- Context
- 262K tokens
- Max output
- 32,768 tokens
- Released
- 2026-09-18
- Weights
- Closed
prism-ml/ternary-bonsai-2-27b · also seen as prism-ml/ternary-bonsai-2-27b-20260918
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-09-18
- Weights
- Closed
- Input
- Text, Image
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 32,768
- Providers
- 1 + 3 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.075 in · $0.50 out per 1M tokens · from its one provider
More details
- Last updated
- 2026-09-18
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
No change since 19 Oct 2026. The cheapest direct price has been $0.075 in / $0.50 out per 1M tokens at Darkbloom on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Ternary Bonsai 2 27B |
|---|---|---|---|---|---|
| GLM-4.5-AirZ.ai (Zhipu AI) | $0.146 | $0.117 | $0.291 | 131K | −0% cheaper |
| Llama Guard 4 12BMeta | $0.144 | $0.144 | $0.144 | 164K | −1% cheaper |
| Gemma 4 26B A4B CybersecurityGoogle | $0.144 | $0.106 | $0.334 | 262K | −1% cheaper |
| Qwen PlusAlibaba (Qwen) | $0.144 | $0.115 | $0.287 | 1M | −1% cheaper |
| Mistral Small 3.1Mistral AI | $0.148 | $0.111 | $0.334 | 128K | +2% |
| doubao-seed-1-8-251215ByteDance Seed | $0.143 | $0.114 | $0.286 | 224K | −2% cheaper |
| Qwen3 4B BaseAlibaba (Qwen) | $0.15 | $0.15 | $0.15 | 32.8K | +3% |
| Seed 2.0 MiniByteDance Seed | $0.15 | $0.10 | $0.40 | 131K | +3% |
More from PrismML
Newest PrismML models in the catalogue. All PrismML models
| Model | Released | Context | Listed price |
|---|---|---|---|
| ternary-bonsai-27b | — | 262K | unpriced |