Choose PrismML: Ternary Bonsai 2 9B if…
- cost matters at scale — it is 87% cheaper on a typical 3:1 input/output mix ($8.60 vs $61.10 a month for 50,000 support chats)
- you want the newer model — released 2026-10-16, 8 months after the other
PrismML: Ternary Bonsai 2 9B vs Qwen: Qwen3.5-122B-A10B
PrismML: Ternary Bonsai 2 9B comes out ahead on the data we track: 2 advantages and none for Qwen: Qwen3.5-122B-A10B.
Key numbers
| Spec | PrismML: Ternary Bonsai 2 9B | Qwen: Qwen3.5-122B-A10B |
|---|---|---|
| Provider | Prism ML | Qwen |
| Input price (per 1M tokens) | $0.08 | $0.26 |
| Output price (per 1M tokens) | $0.13 | $2.08 |
| Blended price (3:1 input/output) | $0.09 | $0.72 |
| Cheaper than … of all models we track | 82% | 47% |
| Context window | 262K tokens (~393 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 47% | 47% |
| Max output per response | 66K tokens (~49,200 words) | 66K tokens (~49,200 words) |
| Input types | text, image | text, image, video |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2026-10-16 | 2026-02-25 |
Advertisement
What it costs for real workloads
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | PrismML: Ternary Bonsai 2 9B | Qwen: Qwen3.5-122B-A10B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $8.60 | $61.10 | PrismML: Ternary Bonsai 2 9B saves $52.50 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $10.90 | $52.00 | PrismML: Ternary Bonsai 2 9B saves $41.10 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $11.16 | $56.16 | PrismML: Ternary Bonsai 2 9B saves $45.00 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $7.18 | $33.28 | PrismML: Ternary Bonsai 2 9B saves $26.10 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $4.13 | $15.08 | PrismML: Ternary Bonsai 2 9B saves $10.95 |
Capabilities side by side
| Capability | PrismML: Ternary Bonsai 2 9B | Qwen: Qwen3.5-122B-A10B | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | ✓ Yes | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | ✓ Yes | ✓ Yes | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
- PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28.
- Qwen: Qwen3.5-122B-A10B: input price cut 35% ($0.40 → $0.26/1M), output price cut 35% ($3.20 → $2.08/1M) on 2026-10-26 (6 price changes since 2026-03-10).
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-10-26 | Qwen: Qwen3.5-122B-A10B | $0.26 | $2.08 |
| 2026-10-22 | Qwen: Qwen3.5-122B-A10B | $0.40 | $3.20 |
| 2026-09-10 | Qwen: Qwen3.5-122B-A10B | $0.26 | $2.08 |
| 2026-08-29 | Qwen: Qwen3.5-122B-A10B | $0.29 | $2.40 |
| 2026-08-18 | Qwen: Qwen3.5-122B-A10B | $0.26 | $2.08 |
| 2026-08-07 | Qwen: Qwen3.5-122B-A10B | $0.29 | $2.40 |
Which should you choose?
Choose Qwen: Qwen3.5-122B-A10B if…
No advantage on the data we track — pick it for provider preference or output quality on your own prompts.
Frequently asked questions
Is PrismML: Ternary Bonsai 2 9B better than Qwen: Qwen3.5-122B-A10B?
PrismML: Ternary Bonsai 2 9B comes out ahead on the data we track: 2 advantages and none for Qwen: Qwen3.5-122B-A10B.
Which is cheaper, PrismML: Ternary Bonsai 2 9B or Qwen: Qwen3.5-122B-A10B?
PrismML: Ternary Bonsai 2 9B is cheaper: $0.09 vs $0.72 per 1M tokens at a typical 3:1 input/output mix, 87% less. For 50,000 support conversations a month that is $8.60 against $61.10.
How much do PrismML: Ternary Bonsai 2 9B and Qwen: Qwen3.5-122B-A10B cost per million tokens?
PrismML: Ternary Bonsai 2 9B costs $0.08 per 1M input tokens and $0.13 per 1M output tokens; Qwen: Qwen3.5-122B-A10B costs $0.26 input and $2.08 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, PrismML: Ternary Bonsai 2 9B or Qwen: Qwen3.5-122B-A10B?
Both take 262K tokens per request — roughly 393 pages of text.
Do PrismML: Ternary Bonsai 2 9B and Qwen: Qwen3.5-122B-A10B support function calling and JSON output?
Tool calling — PrismML: Ternary Bonsai 2 9B: yes, Qwen: Qwen3.5-122B-A10B: yes. JSON-schema structured output — PrismML: Ternary Bonsai 2 9B: yes, Qwen: Qwen3.5-122B-A10B: yes.
Can PrismML: Ternary Bonsai 2 9B or Qwen: Qwen3.5-122B-A10B read images?
Yes, both accept image input.
Is PrismML: Ternary Bonsai 2 9B or Qwen: Qwen3.5-122B-A10B free to use?
No free variant is listed for either; both are pay-per-token.
What is the maximum output length of PrismML: Ternary Bonsai 2 9B and Qwen: Qwen3.5-122B-A10B?
PrismML: Ternary Bonsai 2 9B can write up to 66K tokens (about 49,200 words) per response; Qwen: Qwen3.5-122B-A10B up to 66K (about 49,200 words).
When were PrismML: Ternary Bonsai 2 9B and Qwen: Qwen3.5-122B-A10B released?
PrismML: Ternary Bonsai 2 9B was listed on 2026-10-16; Qwen: Qwen3.5-122B-A10B on 2026-02-25.
Has the price of PrismML: Ternary Bonsai 2 9B or Qwen: Qwen3.5-122B-A10B changed?
PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28. Qwen: Qwen3.5-122B-A10B: input price cut 35% ($0.40 → $0.26/1M), output price cut 35% ($3.20 → $2.08/1M) on 2026-10-26 (6 price changes since 2026-03-10).
About the two models
PrismML: Ternary Bonsai 2 9B
Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...
Full PrismML: Ternary Bonsai 2 9B specs →Qwen: Qwen3.5-122B-A10B
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Full Qwen: Qwen3.5-122B-A10B specs →