GPT-5 Mini
OpenAI · released Aug 7, 2025
- Type
- Proprietary
- Input
- $0.25
- Output
- $2.00
- Cached
- $0.025
List price · per 1M tokens · OpenAI at 272K context · source ↗
Our take
Written Aug 3, 2026GPT-5 Mini is OpenAI's proprietary small model that can handle up to 400,000 tokens in a single request and accepts text, images and files. It is the cheapest way into the GPT-5 family, with measured coding strength but notably weaker creative writing performance.
Pick this for long-document processing where a very large request limit matters, or for coding assistance where its measured Elo is strongest. Use it for budget-conscious multimodal workflows with text, image and file input, or for Azure deployments that need guaranteed throughput up to 110 tokens per second. Skip it if you need to run models on your own hardware, if creative writing quality is central, or if you want a permissive licence.
The case for it
- Largest context window in its price tier among measured offers, at 400,000 tokens.
- Coding is its strongest measured capability, exceeding its own overall text score by 41 points and its creative writing score by 106 points.
- Lowest-cost access point in the GPT-5 family.
- Throughput can more than double at a higher Azure tier, from 47 to 110 tokens per second.
The case against it
- Creative writing lags all other measured capabilities, sitting 106 points below its own coding score and 65 points below its overall text score.
- Proprietary weights with no permissive licence; you cannot download or self-host it.
- Throughput at the cheapest tier is the slowest measured, at 47 tokens per second.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)82nd of 143 · 1390via High
CodingWriting and fixing code on its own
Arena Coding87th of 143 · 1431via High
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
GPT-5 Mini is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 23rd of 39 with 56.2.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where GPT-5 Mini placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model7 scoresEvery figure we hold, from 7 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.25 in / $2.00 out
- Context served
- 400K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenAIflex tier | $0.13 / $1.00 | 400K | 47 tok/s | No | Yesunknown period | Unknown |
| OpenRouter | $0.25 / $2.00 | 400K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $0.25 / $2.00 | 400K | 82 tok/s | No | No | Confirmed |
| OpenAI | $0.25 / $2.00 | 272K128K out | 68 tok/s | No | Yesunknown period | Unknown |
| Microsoft Azure AIswedencentral | $0.28 / $2.20 | 400K | 110 tok/s | No | No | Confirmed |
Microsoft Azure AIAcross the 5 listings we hold: 4 say they do not train on prompts, 0 say they do and 1 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenAIflex | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
| Microsoft Azure AIswedencentral | ✓ | ✓ | ✓ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 5 of 5 listings say yes.
Models people weigh against GPT-5 Mini
When we formed this view
Dates behind this page
Prices last checked 2d ago
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- openai-gpt-5-mini