Overview

Model specifications

Context: 262,144 tokens
Maximum output: 65,536 tokens
Architecture: text+image->text
Tokenizer: Qwen
Knowledge cutoff: Not provided
Moderated: No

OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input: $0.08
Output: $0.13
Cache read: $0.04

API

Model configuration

Default parameters

temperature: 1
top_p: 0.95
top_k: 20

Reasoning

Reasoning required: No
Default parameters: Yes

API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"prism-ml/ternary-bonsai-2-9b","messages":[{"role":"user","content":"Hello!"}]}'

Capabilities

Input → Output

Input

textimage

Output

text

Reasoning

Yes

API

Supported API parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Available providers

1 Provider

Checked: October 28, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Darkbloom

int4

Context: 262K
Maximum output: 66K
Input: $0.08
Output: $0.13
Cache read: $0.04
Cache write: Not provided

PrismML: 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...

Context

262K

Input

text · image

Output

text

Input: $0.075Output: $0.5per 1M tokens

View model details →

PrismML: Ternary Bonsai 2 9B