← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Ternary Bonsai 2 9B Pricing
PrismML · prism-ml-ternary-bonsai-2-9b
Input / 1M tokens
$0.080
Output / 1M tokens
$0.130
Context window
262,144 tokens
≈ 350 pages of text
Max output
65,536 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.148/mo10,000 requests / month$1.48/mo100,000 requests / month$14.80/moEstimate your own workloadOpens the calculator with Ternary Bonsai 2 9B 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
Suitable for cost-sensitive text and vision workloads where open weights enable local or private deployment. Low per-token pricing supports high-volume inference.
The business tradeoff
9B scale limits complex reasoning and instruction following relative to larger models. Performance consistency depends on user-hosted infrastructure and fine-tuning.
Head-to-head
Vendor list rates, as of Oct 27, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.