Neither wins outright: Mistral: Codestral 2508 (batch) is the pick when cost matters at scale, OpenAI: GPT-5 Mini (batch) when you need to fit long inputs in one request.
| Spec | Mistral: Codestral 2508 (batch) | OpenAI: GPT-5 Mini (batch) |
|---|---|---|
| Provider | Mistral AI | OpenAI |
| Input price (per 1M tokens) | $0.15 | $0.13 |
| Output price (per 1M tokens) | $0.45 | $1.00 |
| Blended price (3:1 input/output) | $0.22 | $0.34 |
| Cheaper than … of all models we track | 68% | 62% |
| Context window | 256K tokens (~384 pages) | 400K tokens (~600 pages) |
| Larger context than … of all models | 45% | 63% |
| Max output per response | 205K tokens (~153,600 words) | 128K tokens (~96,000 words) |
| Input types | text, file | text, image, file |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-08-01 | 2025-08-07 |
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: Codestral 2508 (batch) | OpenAI: GPT-5 Mini (batch) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $20.25 | $29.38 | Mistral: Codestral 2508 (batch) saves $9.13 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $22.50 | $25.00 | Mistral: Codestral 2508 (batch) saves $2.50 |
| 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) | $23.40 | $27.00 | Mistral: Codestral 2508 (batch) saves $3.60 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $14.70 | $16.00 | Mistral: Codestral 2508 (batch) saves $1.30 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $7.95 | $7.25 | OpenAI: GPT-5 Mini (batch) saves $0.70 |
| Capability | Mistral: Codestral 2508 (batch) | OpenAI: GPT-5 Mini (batch) | 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 | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | ✓ Yes | ✓ Yes | 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: Codestral 2508 (batch) | $0.15 | $0.45 |
Neither wins outright: Mistral: Codestral 2508 (batch) is the pick when cost matters at scale, OpenAI: GPT-5 Mini (batch) when you need to fit long inputs in one request. In short: Mistral: Codestral 2508 (batch) when cost matters at scale, you generate long outputs in one go; OpenAI: GPT-5 Mini (batch) when you need to fit long inputs in one request, you need reasoning / thinking mode, you need image input, you need built-in web search.
Mistral: Codestral 2508 (batch) is cheaper: $0.22 vs $0.34 per 1M tokens at a typical 3:1 input/output mix, 35% less. For 50,000 support conversations a month that is $20.25 against $29.38.
Mistral: Codestral 2508 (batch) costs $0.15 per 1M input tokens and $0.45 per 1M output tokens; OpenAI: GPT-5 Mini (batch) costs $0.13 input and $1.00 output. Output tokens are billed separately, so long answers shift the gap.
OpenAI: GPT-5 Mini (batch): 400K tokens, about 600 pages, against 256K (about 384 pages) for Mistral: Codestral 2508 (batch).
Tool calling — Mistral: Codestral 2508 (batch): yes, OpenAI: GPT-5 Mini (batch): yes. JSON-schema structured output — Mistral: Codestral 2508 (batch): yes, OpenAI: GPT-5 Mini (batch): yes.
Only OpenAI: GPT-5 Mini (batch) accepts image input; Mistral: Codestral 2508 (batch) is text-only for input.
No free variant is listed for either; both are pay-per-token.
Mistral: Codestral 2508 (batch) can write up to 205K tokens (about 153,600 words) per response; OpenAI: GPT-5 Mini (batch) up to 128K (about 96,000 words).
Mistral: Codestral 2508 (batch) was listed on 2025-08-01; OpenAI: GPT-5 Mini (batch) on 2025-08-07.
Mistral: Codestral 2508 (batch): input price cut 50% ($0.30 → $0.15/1M), output price cut 50% ($0.90 → $0.45/1M) on 2026-09-10. OpenAI: GPT-5 Mini (batch): price unchanged since we started tracking it on 2026-08-07.
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Full Mistral: Codestral 2508 (batch) specs →GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Full OpenAI: GPT-5 Mini (batch) specs →