GPT-4o (2024-08-06)
OpenAI · released Aug 6, 2024
- Type
- Closed
- Input
- $2.50
- Output
- $10.00
- Cached
- $1.25
List price · per 1M tokens · OpenAI at 128K context · machine-readable source ↗
Our take
Written Sep 17, 2026GPT-4o (2024-08-06) is a hosted-only model: we list no download for it, so using it means choosing a host. All three listed offers carry the same rate, so the bill does not change with the host you pick. It takes text, images and files, and its request capacity keeps a long report in one go.
Use it for hosted chat, document and image work where you want one rate across every host we list, or for tasks that need long inputs kept in a single request. Its coding evidence comes from set-piece competitive exercises, so trial it on your own codebase before committing. Skip it if you need to run the model on your own machine, or if you need measured correctness rather than preference ratings.
The case for it
- Every host we list charges the same rate, so the bill does not change with the host you pick.
- 128,000 tokens of request capacity, so a long report or a stack of documents need not be split up first.
- Text, images and files go into the same request, so a screenshot or a document does not have to be described in words first.
The case against it
- Coding evidence is set-piece competitive exercises, not fixing issues in an existing project, so real codebase work needs a trial on your own tasks.
- The Arena boards record which answer people preferred, not whether it was right, so nothing here measures correctness.
- We list no download for it and no parameter count is published, so running it yourself is not a route we can point you to.
How good is it?
A general chat model for everyday questions and coding, though it trails most models on both.
- getting answers to everyday questionsArena Text (overall) · 132nd of 168
- writing and completing codeArena Coding · 138th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)132nd of 168 · 1336
CodingWriting and fixing code on its own
Arena Coding138th of 168 · 1360
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing113th of 168 · 1327
Arena Creative Writing is the only board that has scored it for this.
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.
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.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
OpenAI, direct
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts OpenAI on 128K of context.
- per 1M tokens
- $2.50 in / $10.00 out
- Context served
- 128K
- Throughput
- ~17 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.50 / $10.00checked 2 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $2.50 / $10.00checked 2 hours ago | 128K16K max reply | 52 tok/s | No | No | Confirmed |
| OpenAIDirect | $2.50 / $10.00checked 2 hours ago | 128K16K max reply | 17 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Microsoft Azure AIAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against GPT-4o (2024-08-06)
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
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
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- openai-gpt-4o-2024-08-06