Choose Google: Gemma 4 31B if…
- you want to prototype at zero cost — a free variant is listed
Google: Gemma 4 31B vs PrismML: Ternary Bonsai 2 9B
Neither wins outright: Google: Gemma 4 31B is the pick when you want to prototype at zero cost, PrismML: Ternary Bonsai 2 9B when cost matters at scale.
Key numbers
| Spec | Google: Gemma 4 31B | PrismML: Ternary Bonsai 2 9B |
|---|---|---|
| Provider | Prism ML | |
| Input price (per 1M tokens) | $0.20 | $0.08 |
| Output price (per 1M tokens) | $0.40 | $0.13 |
| Blended price (3:1 input/output) | $0.25 | $0.09 |
| Cheaper than … of all models we track | 66% | 82% |
| Context window | 262K tokens (~393 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 47% | 47% |
| Max output per response | 16K tokens (~12,300 words) | 66K tokens (~49,200 words) |
| Input types | image, text, video | text, image |
| Output types | text | text |
| Free variant | Yes | No |
| Listed since | 2026-04-02 | 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) | Google: Gemma 4 31B | PrismML: Ternary Bonsai 2 9B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $23.00 | $8.60 | PrismML: Ternary Bonsai 2 9B saves $14.40 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $28.00 | $10.90 | PrismML: Ternary Bonsai 2 9B saves $17.10 |
| 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) | $28.80 | $11.16 | PrismML: Ternary Bonsai 2 9B saves $17.64 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $18.40 | $7.18 | PrismML: Ternary Bonsai 2 9B saves $11.22 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $10.40 | $4.13 | PrismML: Ternary Bonsai 2 9B saves $6.27 |
Capabilities side by side
| Capability | Google: Gemma 4 31B | 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 | ✓ 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
- Google: Gemma 4 31B: input price raised 50% ($0.10 → $0.20/1M), output price raised 15% ($0.34 → $0.40/1M) on 2026-10-27 (6 price changes since 2026-08-06).
- PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-10-27 | Google: Gemma 4 31B | $0.20 | $0.40 |
| 2026-10-26 | Google: Gemma 4 31B | $0.10 | $0.34 |
| 2026-10-15 | Google: Gemma 4 31B | $0.20 | $0.40 |
| 2026-08-27 | Google: Gemma 4 31B | $0.09 | $0.34 |
| 2026-08-21 | Google: Gemma 4 31B | $0.10 | $0.34 |
| 2026-08-19 | Google: Gemma 4 31B | $0.09 | $0.34 |
Which should you choose?
Choose PrismML: Ternary Bonsai 2 9B if…
- cost matters at scale — it is 63% cheaper on a typical 3:1 input/output mix ($8.60 vs $23.00 a month for 50,000 support chats)
- you generate long outputs in one go — up to 66K tokens (about 49,200 words) per response
- you want the newer model — released 2026-10-16, 7 months after the other
Frequently asked questions
Is Google: Gemma 4 31B better than PrismML: Ternary Bonsai 2 9B?
Neither wins outright: Google: Gemma 4 31B is the pick when you want to prototype at zero cost, PrismML: Ternary Bonsai 2 9B when cost matters at scale. In short: Google: Gemma 4 31B when you want to prototype at zero cost; PrismML: Ternary Bonsai 2 9B when cost matters at scale, you generate long outputs in one go, you want the newer model.
Which is cheaper, Google: Gemma 4 31B or PrismML: Ternary Bonsai 2 9B?
PrismML: Ternary Bonsai 2 9B is cheaper: $0.09 vs $0.25 per 1M tokens at a typical 3:1 input/output mix, 63% less. For 50,000 support conversations a month that is $8.60 against $23.00.
How much do Google: Gemma 4 31B and PrismML: Ternary Bonsai 2 9B cost per million tokens?
Google: Gemma 4 31B costs $0.20 per 1M input tokens and $0.40 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, Google: Gemma 4 31B or PrismML: Ternary Bonsai 2 9B?
Both take 262K tokens per request — roughly 393 pages of text.
Do Google: Gemma 4 31B and PrismML: Ternary Bonsai 2 9B support function calling and JSON output?
Tool calling — Google: Gemma 4 31B: yes, PrismML: Ternary Bonsai 2 9B: yes. JSON-schema structured output — Google: Gemma 4 31B: yes, PrismML: Ternary Bonsai 2 9B: yes.
Can Google: Gemma 4 31B or PrismML: Ternary Bonsai 2 9B read images?
Yes, both accept image input.
Is Google: Gemma 4 31B or PrismML: Ternary Bonsai 2 9B free to use?
Google: Gemma 4 31B has a free variant (google/gemma-4-31b-it:free). Free variants usually carry tighter rate limits.
What is the maximum output length of Google: Gemma 4 31B and PrismML: Ternary Bonsai 2 9B?
Google: Gemma 4 31B can write up to 16K tokens (about 12,300 words) per response; PrismML: Ternary Bonsai 2 9B up to 66K (about 49,200 words).
When were Google: Gemma 4 31B and PrismML: Ternary Bonsai 2 9B released?
Google: Gemma 4 31B was listed on 2026-04-02; PrismML: Ternary Bonsai 2 9B on 2026-10-16.
Has the price of Google: Gemma 4 31B or PrismML: Ternary Bonsai 2 9B changed?
Google: Gemma 4 31B: input price raised 50% ($0.10 → $0.20/1M), output price raised 15% ($0.34 → $0.40/1M) on 2026-10-27 (6 price changes since 2026-08-06). PrismML: Ternary Bonsai 2 9B: price unchanged since we started tracking it on 2026-10-28.
About the two models
Google: Gemma 4 31B
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Full Google: Gemma 4 31B 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 →