Neither wins outright: OpenAI: GPT-5.1-Codex-Mini is the pick when you need to fit long inputs in one request, PrismML: Ternary Bonsai 2 9B when cost matters at scale.
| Spec | OpenAI: GPT-5.1-Codex-Mini | PrismML: Ternary Bonsai 2 9B |
|---|---|---|
| Provider | OpenAI | Prism ML |
| Input price (per 1M tokens) | $0.25 | $0.08 |
| Output price (per 1M tokens) | $2.00 | $0.13 |
| Blended price (3:1 input/output) | $0.69 | $0.09 |
| Cheaper than … of all models we track | 47% | 82% |
| Context window | 400K tokens (~600 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 62% | 47% |
| Max output per response | 128K tokens (~96,000 words) | 66K tokens (~49,200 words) |
| Input types | image, text | text, image |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-11-13 | 2026-10-16 |
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) | OpenAI: GPT-5.1-Codex-Mini | PrismML: Ternary Bonsai 2 9B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $58.75 | $8.60 | PrismML: Ternary Bonsai 2 9B saves $50.15 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $50.00 | $10.90 | PrismML: Ternary Bonsai 2 9B saves $39.10 |
| 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) | $54.00 | $11.16 | PrismML: Ternary Bonsai 2 9B saves $42.84 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $32.00 | $7.18 | PrismML: Ternary Bonsai 2 9B saves $24.82 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $14.50 | $4.13 | PrismML: Ternary Bonsai 2 9B saves $10.37 |
| Capability | OpenAI: GPT-5.1-Codex-Mini | 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 | ✓ Yes | — | 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.
Neither wins outright: OpenAI: GPT-5.1-Codex-Mini is the pick when you need to fit long inputs in one request, PrismML: Ternary Bonsai 2 9B when cost matters at scale. In short: OpenAI: GPT-5.1-Codex-Mini when you need to fit long inputs in one request, you need built-in web search, 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.
PrismML: Ternary Bonsai 2 9B is cheaper: $0.09 vs $0.69 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 $58.75.
OpenAI: GPT-5.1-Codex-Mini costs $0.25 per 1M input tokens and $2.00 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.
OpenAI: GPT-5.1-Codex-Mini: 400K tokens, about 600 pages, against 262K (about 393 pages) for PrismML: Ternary Bonsai 2 9B.
Tool calling — OpenAI: GPT-5.1-Codex-Mini: yes, PrismML: Ternary Bonsai 2 9B: yes. JSON-schema structured output — OpenAI: GPT-5.1-Codex-Mini: yes, PrismML: Ternary Bonsai 2 9B: yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
OpenAI: GPT-5.1-Codex-Mini can write up to 128K tokens (about 96,000 words) per response; PrismML: Ternary Bonsai 2 9B up to 66K (about 49,200 words).
OpenAI: GPT-5.1-Codex-Mini was listed on 2025-11-13; PrismML: Ternary Bonsai 2 9B on 2026-10-16.
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
Full OpenAI: GPT-5.1-Codex-Mini specs →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 →