Enter opens the highlighted result. Esc closes.

Ternary Bonsai 2 27B vs Fugu Max

Ternary Bonsai 2 27B costs 12.0x less per output token than Fugu Max ($0.50 vs $6.00 per million). Updated October 23, 2026; no benchmark has tested both models yet.

Replace Ternary Bonsai 2 27B Replace Fugu Max
P Ternary Bonsai 2 27BPrism-ml
Coding
No data
Overall
No data
Output $/M
$0.50
Fugu MaxSakana
Coding
No data
Overall
No data
Output $/M
$6.00
vs $0.50 vs $6.00 per 1M output tokens. Ternary Bonsai 2 27B is 12.0x cheaper.

Ternary Bonsai 2 27B or Fugu Max: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Ternary Bonsai 2 27B for output tokens 12.0x cheaper ($0.50 vs $6.00 per million).

Model ATernary Bonsai 2 27BPrism-mlNot benchmarkedNo coding benchmarkNo cost per solved taskModel BFugu MaxSakanaNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested either model yet, so price and context are the only way to compare them.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Ternary Bonsai 2 27B not benchmarked, Fugu Max not benchmarked.
Widest category
None yet: no category has been tested on both models.
Widest single gap
None yet: no benchmark has tested both models.
Output price
Ternary Bonsai 2 27B $0.50 against Fugu Max $6.00 per million output tokens, 12.0x apart.
Context window
Ternary Bonsai 2 27B takes 262K tokens, Fugu Max 1M.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Ternary Bonsai 2 27B$0.0003Fits in one request
Fugu Max$0.0050Fits in one request

Ternary Bonsai 2 27B costs less

Repository review

50K input + 3K output tokens

Ternary Bonsai 2 27B$0.0053Fits in one request
Fugu Max$0.118Fits in one request

Ternary Bonsai 2 27B costs less

Agent loop

200K input + 10K output tokens

Ternary Bonsai 2 27B$0.020Fits in one request
Fugu Max$0.460Fits in one request

Ternary Bonsai 2 27B costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Ternary Bonsai 2 27B and Fugu Max
SpecificationPrismML Ternary Bonsai 2 27BSakana Fugu Max
MakerPrism-mlSakana
WeightsOpen weightsNo public weights listed
ReleasedSeptember 18, 2026September 11, 2026
Context window262K1M
Input $/Mtok$0.075$2.00
Output $/Mtok$0.50$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Ternary Bonsai 2 27B better than Fugu Max for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Ternary Bonsai 2 27B for output tokens 12.0x cheaper ($0.50 vs $6.00 per million).

Which is cheaper, Ternary Bonsai 2 27B or Fugu Max?

Ternary Bonsai 2 27B costs $0.075 per million input tokens and $0.50 per million output tokens; Fugu Max costs $2.00 and $6.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Ternary Bonsai 2 27B or Fugu Max?

Fugu Max, with 1M tokens against 262K.

Has any benchmark tested both Ternary Bonsai 2 27B and Fugu Max?

No benchmark has tested either model yet, so price and context are the only way to compare them. Data as of October 23, 2026.

Compare next