PrismML: Ternary Bonsai 2 27B
by PrismMLPrismML: Ternary Bonsai 2 27B is a large language model from PrismML. It costs $0.075 per million input tokens and $0.500 per million output tokens. Its context window is 262K tokens.
- Input / 1M tokens
- $0.075
- Output / 1M tokens
- $0.500
- Cached input / 1M
- $0.037
- Context window
- 262K
On repeated prefixes
tokens
Who serves it cheapest
1 hosts serve Ternary Bonsai 2 27B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| DarkbloomCheapestint4 | $0.075 | $0.500 | 262K | - | 100.0% |
About 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...
Specifications
| Model ID | prism-ml/ternary-bonsai-2-27b |
|---|---|
| Provider | PrismML |
| Context window | 262K tokens |
| Max output | 33K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | Yes - prism-ml/Ternary-Bonsai-2-27B-gguf |
| Released | September 18, 2026 |
Cheaper alternatives
Models that cost less than Ternary Bonsai 2 27B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does PrismML: Ternary Bonsai 2 27B cost?
$0.075 per million input tokens and $0.500 per million output tokens. Cached input reads cost $0.037 per million tokens.
What is the context window of PrismML: Ternary Bonsai 2 27B?
262K tokens, with up to 33K tokens of output per request.