Home / Models / Prism Ml / Ternary Bonsai 2 27B
PPrism Mlopen weights

Ternary Bonsai 2 27B pricing

$0.075 per 1M input tokens and $0.50 per 1M output tokens. In real work that is 0.05¢ per chat answer and 0.13¢ to summarize a 20-page PDF.

Input / 1M$0.075
Output / 1M$0.50
Cached input / 1M$0.037
Chat answer0.05¢
Context262K
Quality-

What Ternary Bonsai 2 27B costs per task

Token counts estimated from a measured model of the same lab (Claude Haiku 5.5), rescaled by tokenizer. Reasoning tokens are billed as output.

TaskCostTokens usedPrice rankBasis
Answer a chat question
0.05¢$0.51 / 1,000
44 in · 767 out · 244 reasoning62 of 336estimated
Reply to a customer email
0.03¢$0.30 / 1,000
263 in · 210 out · 346 reasoning77 of 336estimated
Write a 1,500-word blog post
0.14¢$1.40 / 1,000
65 in · 2,589 out · 200 reasoning39 of 336estimated
Write 10 product descriptions
0.19¢$1.85 / 1,000
330 in · 1,311 out · 2,342 reasoning65 of 336estimated
Translate 1,000 words
0.09¢$0.88 / 1,000
1,332 in · 1,565 out59 of 336estimated
Proofread one page (500 words)
0.05¢$0.54 / 1,000
717 in · 664 out · 304 reasoning58 of 336estimated
Summarize a 20-page PDF
0.13¢$1.28 / 1,000
13,093 in · 488 out · 118 reasoning31 of 336estimated
Extract data from an invoice
0.05¢$0.53 / 1,000
397 in · 417 out · 591 reasoning54 of 336estimated
Analyze a 200-row spreadsheet
≥0.82¢$8.22 / 1,000
3,951 in · 411 out · 15,434 reasoning93 of 336estimated
Answer from 5 retrieved documents (RAG)
0.11¢$1.06 / 1,000
3,770 in · 797 out · 753 reasoning59 of 336estimated
Classify 100 support tickets
0.08¢$0.77 / 1,000
1,270 in · 389 out · 961 reasoning20 of 336estimated
Review 500 lines of code
0.58¢$5.84 / 1,000
5,176 in · 2,369 out · 8,532 reasoning99 of 336estimated
Write a SQL query
0.07¢$0.72 / 1,000
132 in · 610 out · 810 reasoning69 of 336estimated
Run a 50-step coding agent
11¢$110 / 1,000
2,255,400 in · 15,120 out · 29,550 reasoning61 of 336modeled

Price at every provider

List prices per 1M tokens (input / output) at each host serving Ternary Bonsai 2 27B through OpenRouter today. Hosts can differ in quantization, context and speed.

ProviderInput / outputCached inputContextUptime
D
Darkbloomint4
$0.075 / $0.50$0.037262K100%

Price history

First seen in our price history on Sep 21, 2026 at $0.075 input / $0.50 output. The list price has not changed since.

$0$0.14$0.29$0.43$0.57Sep 2026Sep 2026Oct 2026Oct 2026Oct 2026
Output per 1MInput per 1M

FAQ

How much does Ternary Bonsai 2 27B cost?

Ternary Bonsai 2 27B costs $0.075 per 1 million input tokens and $0.50 per 1 million output tokens, with cached input at $0.037 (list price on Oct 18, 2026). In practice one chat answer costs about 0.05¢ and summarizing a 20-page PDF about 0.13¢.

Where is Ternary Bonsai 2 27B cheapest?

Among 1 providers we track, the lowest list price today is at Darkbloom: $0.075 input and $0.50 output per 1M tokens.

Does Ternary Bonsai 2 27B charge for reasoning tokens?

Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.

Is the Ternary Bonsai 2 27B cost per task measured or estimated?

Estimated: Ternary Bonsai 2 27B was not run directly. Tokens come from Claude Haiku 5.5 and are rescaled by the tokenizer of Prism Ml. Real usage can differ.