Choose Mistral: Mistral Small 4 (batch) if…
- you generate long outputs in one go — up to 210K tokens (about 157,300 words) per response
Mistral: Mistral Small 4 (batch) vs PrismML: Ternary Bonsai 2 9B
Neither wins outright: Mistral: Mistral Small 4 (batch) is the pick when you generate long outputs in one go, PrismML: Ternary Bonsai 2 9B when cost matters at scale.
Key numbers
| Spec | Mistral: Mistral Small 4 (batch) | PrismML: Ternary Bonsai 2 9B |
|---|---|---|
| Provider | Mistral AI | Prism ML |
| Input price (per 1M tokens) | $0.07 | $0.08 |
| Output price (per 1M tokens) | $0.30 | $0.13 |
| Blended price (3:1 input/output) | $0.13 | $0.09 |
| Cheaper than … of all models we track | 76% | 82% |
| Context window | 262K tokens (~393 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 47% | 47% |
| Max output per response | 210K tokens (~157,300 words) | 66K tokens (~49,200 words) |
| Input types | text, image | text, image |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2026-03-16 | 2026-10-16 |
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) | Mistral: Mistral Small 4 (batch) | PrismML: Ternary Bonsai 2 9B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $11.63 | $8.60 | PrismML: Ternary Bonsai 2 9B saves $3.03 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $12.00 | $10.90 | PrismML: Ternary Bonsai 2 9B saves $1.10 |
| 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) | $12.60 | $11.16 | PrismML: Ternary Bonsai 2 9B saves $1.44 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $7.80 | $7.18 | PrismML: Ternary Bonsai 2 9B saves $0.62 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $4.05 | $4.13 | Mistral: Mistral Small 4 (batch) saves $0.08 |
Capabilities side by side
| Capability | Mistral: Mistral Small 4 (batch) | PrismML: Ternary Bonsai 2 9B | 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 | 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
- Mistral: Mistral Small 4 (batch): input price cut 50% ($0.15 → $0.07/1M), output price cut 50% ($0.60 → $0.30/1M) on 2026-09-10.
- PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-09-10 | Mistral: Mistral Small 4 (batch) | $0.07 | $0.30 |
Which should you choose?
Choose PrismML: Ternary Bonsai 2 9B if…
- cost matters at scale — it is 30% cheaper on a typical 3:1 input/output mix ($8.60 vs $11.63 a month for 50,000 support chats)
- you need log-probabilities — to read token confidence for classification and scoring; Mistral: Mistral Small 4 (batch) does not advertise it
- you want the newer model — released 2026-10-16, 7 months after the other
Frequently asked questions
Is Mistral: Mistral Small 4 (batch) better than PrismML: Ternary Bonsai 2 9B?
Neither wins outright: Mistral: Mistral Small 4 (batch) is the pick when you generate long outputs in one go, PrismML: Ternary Bonsai 2 9B when cost matters at scale. In short: Mistral: Mistral Small 4 (batch) when you generate long outputs in one go; PrismML: Ternary Bonsai 2 9B when cost matters at scale, you need log-probabilities, you want the newer model.
Which is cheaper, Mistral: Mistral Small 4 (batch) or PrismML: Ternary Bonsai 2 9B?
PrismML: Ternary Bonsai 2 9B is cheaper: $0.09 vs $0.13 per 1M tokens at a typical 3:1 input/output mix, 30% less. For 50,000 support conversations a month that is $8.60 against $11.63.
How much do Mistral: Mistral Small 4 (batch) and PrismML: Ternary Bonsai 2 9B cost per million tokens?
Mistral: Mistral Small 4 (batch) costs $0.07 per 1M input tokens and $0.30 per 1M output tokens; PrismML: Ternary Bonsai 2 9B costs $0.08 input and $0.13 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, Mistral: Mistral Small 4 (batch) or PrismML: Ternary Bonsai 2 9B?
Both take 262K tokens per request — roughly 393 pages of text.
Do Mistral: Mistral Small 4 (batch) and PrismML: Ternary Bonsai 2 9B support function calling and JSON output?
Tool calling — Mistral: Mistral Small 4 (batch): yes, PrismML: Ternary Bonsai 2 9B: yes. JSON-schema structured output — Mistral: Mistral Small 4 (batch): yes, PrismML: Ternary Bonsai 2 9B: yes.
Can Mistral: Mistral Small 4 (batch) or PrismML: Ternary Bonsai 2 9B read images?
Yes, both accept image input.
Is Mistral: Mistral Small 4 (batch) or PrismML: Ternary Bonsai 2 9B free to use?
No free variant is listed for either; both are pay-per-token.
What is the maximum output length of Mistral: Mistral Small 4 (batch) and PrismML: Ternary Bonsai 2 9B?
Mistral: Mistral Small 4 (batch) can write up to 210K tokens (about 157,300 words) per response; PrismML: Ternary Bonsai 2 9B up to 66K (about 49,200 words).
When were Mistral: Mistral Small 4 (batch) and PrismML: Ternary Bonsai 2 9B released?
Mistral: Mistral Small 4 (batch) was listed on 2026-03-16; PrismML: Ternary Bonsai 2 9B on 2026-10-16.
Has the price of Mistral: Mistral Small 4 (batch) or PrismML: Ternary Bonsai 2 9B changed?
Mistral: Mistral Small 4 (batch): input price cut 50% ($0.15 → $0.07/1M), output price cut 50% ($0.60 → $0.30/1M) on 2026-09-10. PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28.
About the two models
Mistral: Mistral Small 4 (batch)
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Full Mistral: Mistral Small 4 (batch) specs →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 →