Neither wins outright: Mistral: Ministral 3 8B 2512 (batch) is the pick when cost matters at scale, OpenAI: GPT-5.1-Codex-Mini when you need to fit long inputs in one request.
| Spec | Mistral: Ministral 3 8B 2512 (batch) | OpenAI: GPT-5.1-Codex-Mini |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Input price (per 1M tokens) | $0.07 | $0.25 |
| Output price (per 1M tokens) | $0.07 | $2.00 |
| Blended price (3:1 input/output) | $0.07 | $0.69 |
| Cheaper than … of all models we track | 84% | 47% |
| Context window | 262K tokens (~393 pages) | 400K tokens (~600 pages) |
| Larger context than … of all models | 48% | 63% |
| Max output per response | 210K tokens (~157,300 words) | 128K tokens (~96,000 words) |
| Input types | text, image | image, text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-12-02 | 2025-11-13 |
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: Ministral 3 8B 2512 (batch) | OpenAI: GPT-5.1-Codex-Mini | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $7.13 | $58.75 | Mistral: Ministral 3 8B 2512 (batch) saves $51.63 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $9.75 | $50.00 | Mistral: Ministral 3 8B 2512 (batch) saves $40.25 |
| 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) | $9.90 | $54.00 | Mistral: Ministral 3 8B 2512 (batch) saves $44.10 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $6.45 | $32.00 | Mistral: Ministral 3 8B 2512 (batch) saves $25.55 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $3.82 | $14.50 | Mistral: Ministral 3 8B 2512 (batch) saves $10.68 |
| Capability | Mistral: Ministral 3 8B 2512 (batch) | OpenAI: GPT-5.1-Codex-Mini | 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 | 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 | — | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
| Date | Model | Input / 1M | Output / 1M |
|---|---|---|---|
| 2026-09-10 | Mistral: Ministral 3 8B 2512 (batch) | $0.07 | $0.07 |
Neither wins outright: Mistral: Ministral 3 8B 2512 (batch) is the pick when cost matters at scale, OpenAI: GPT-5.1-Codex-Mini when you need to fit long inputs in one request. In short: Mistral: Ministral 3 8B 2512 (batch) when cost matters at scale, you generate long outputs in one go; OpenAI: GPT-5.1-Codex-Mini when you need to fit long inputs in one request, you need reasoning / thinking mode, you need built-in web search.
Mistral: Ministral 3 8B 2512 (batch) is cheaper: $0.07 vs $0.69 per 1M tokens at a typical 3:1 input/output mix, 89% less. For 50,000 support conversations a month that is $7.13 against $58.75.
Mistral: Ministral 3 8B 2512 (batch) costs $0.07 per 1M input tokens and $0.07 per 1M output tokens; OpenAI: GPT-5.1-Codex-Mini costs $0.25 input and $2.00 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 Mistral: Ministral 3 8B 2512 (batch).
Tool calling — Mistral: Ministral 3 8B 2512 (batch): yes, OpenAI: GPT-5.1-Codex-Mini: yes. JSON-schema structured output — Mistral: Ministral 3 8B 2512 (batch): yes, OpenAI: GPT-5.1-Codex-Mini: yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
Mistral: Ministral 3 8B 2512 (batch) can write up to 210K tokens (about 157,300 words) per response; OpenAI: GPT-5.1-Codex-Mini up to 128K (about 96,000 words).
Mistral: Ministral 3 8B 2512 (batch) was listed on 2025-12-02; OpenAI: GPT-5.1-Codex-Mini on 2025-11-13.
Mistral: Ministral 3 8B 2512 (batch): input price cut 50% ($0.15 → $0.07/1M), output price cut 50% ($0.15 → $0.07/1M) on 2026-09-10. OpenAI: GPT-5.1-Codex-Mini: price unchanged since we started tracking it on 2026-03-10.
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Full Mistral: Ministral 3 8B 2512 (batch) specs →GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
Full OpenAI: GPT-5.1-Codex-Mini specs →