← All models
Balanced — strong quality at a mid priceOpen Weights
Ternary Bonsai 2 27B Pricing
PrismML · prism-ml-ternary-bonsai-2-27b
Input / 1M tokens
$0.075
Output / 1M tokens
$0.500
Context window
262,144 tokens
≈ 350 pages of text
Max output
32,768 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0003
1,000 requests / month$0.29/mo10,000 requests / month$2.90/mo100,000 requests / month$29.00/moEstimate your own workloadOpens the calculator with Ternary Bonsai 2 27B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Handles long-context multimodal inputs such as image-rich documents or extended codebases at low cost, supported by the 256k context window and open weights.
The business tradeoff
Performance consistency and tooling ecosystem depend on self-hosting quality; lacks the optimized inference stack and reliability guarantees of major hosted providers.
Head-to-head
Vendor list rates, as of Sep 18, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.