All models
Prism Ml
Ternary Bonsai 2 27B fastruns locally
prism-ml/ternary-bonsai-2-27b
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...
Input / 1M
$0.075
USD per million tokens
Output / 1M
$0.50
USD per million tokens
Est. cost / token
$0.000000181
$0.18 per 1M, 3:1 mix
Context window
262K
max output 33K
Major features
VisionOpen weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 14.3 GB |
| Q3_K_M | fair | 16.2 GB |
| Q4_K_Mrecommended | good | 19.7 GB |
| Q5_K_M | very good | 22.6 GB |
| Q6_K | excellent | 25.6 GB |
| Q8_0 | near-lossless | 32.5 GB |
| F16 | lossless | 59.1 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.075 | $0.50 | $0.037 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.075
- Output
- $0.50
- Cached input
- $0.037
- Blended (3:1)
- $0.18
Details
- Company
- Prism Ml
- Version
- 2
- Family
- Ternary
- Released
- 2026-09-18
- Parameters
- 27B
- Max output
- 33K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 46 min ago