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.
- Input / output price
- $0.075 / $0.50 per 1M
- Context
- 262K tokens
- Released
- Sep 17, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
OpenRouter openrouter/ternary-bonsai-2-27b | $0.075/M | $0.50/M |
Is a provider down? OpenRouter status
Pricing
USD per 1M tokens on OpenRouter, after gateway discounts.
- Input
- $0.075 per 1M
- Output
- $0.50 per 1M
- Cache read
- $0.0375 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better18tokens/sacross providers
Response latency
Lower is better0.2sacross providers
Benchmarks
6 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchhuggingface.co | 90.1% | huggingface.co | Sep 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 74.9% | huggingface.co | Sep 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2025huggingface.co | 95% | huggingface.co | Sep 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalhuggingface.co | 91.3% | huggingface.co | Sep 17, 2026 |
| MMLU-Reduxhuggingface.co | 89.1% | huggingface.co | Sep 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMMU-Prohuggingface.co | 75.5% | huggingface.co | Sep 17, 2026 |
Apps
Use Ternary Bonsai 2 27B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Ternary Bonsai 2 27B FAQ
Short answers, built from the data on this page.
Ternary Bonsai 2 27B is a model from Prism, released on Sep 17, 2026. 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.
On the Respan gateway, Ternary Bonsai 2 27B costs $0.075 per 1M input tokens and $0.50 per 1M output tokens on OpenRouter, after gateway discounts.
Ternary Bonsai 2 27B is served by OpenRouter.
Ternary Bonsai 2 27B accepts up to 262K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "ternary-bonsai-2-27b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Ternary Bonsai 2 27B has 6 published benchmark scores, including LiveCodeBench 90.1%, BFCL-v3 74.9%, and AIME 2025 95%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.