GPT-4 Turbo
OpenAI · released Apr 9, 2024
- Type
- Closed
- Input
- $10.00
- Output
- $30.00
- Cached
- None held
List price · per 1M tokens · OpenAI at 128K context · machine-readable source ↗
Our take
Written Sep 30, 2026GPT-4 Turbo is a hosted-only model: we list no download for it, so using it means choosing a host. Its Arena placings sit in the bottom quarter of the field on every board we hold, so treat it as a legacy option rather than a current pick.
Consider it only where an OpenAI or OpenRouter integration is already in place and the work is undemanding, or where a screenshot needs to go in with the question. Both listed hosts serve it at the same rate, so switching between them does not change the bill. Skip it if you need a model that places well on coding, maths or hard-prompt work, or if you want to run the model yourself.
The case for it
- One integration covers both listed hosts, and both serve it at the same rate, so switching between them does not change the bill.
- Text and images go into the same request, so a screenshot does not have to be described in words first.
- The request capacity takes a long report or a stack of documents beside the question, though reliable recall across all of it is unverified in our data.
The case against it
- Bottom quarter of the field on every board we hold: 135th of 168 on Arena Text (overall) as of 25 Sep 2026, and 145th of 168 on Arena Coding as of 25 Sep 2026.
- Those Arena placings record which answer people preferred, not whether it was correct, so a low placing means answers were liked less often rather than that they were wrong.
- Released 2024-04-09, so it is competing against considerably newer models.
How good is it?
A general-purpose text model for chat and code, though it now trails most models on everyday questions and coding.
- getting answers to everyday questionsArena Text (overall) · 135th of 168
- writing and completing codeArena Coding · 145th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)135th of 168 · 1324
CodingWriting and fixing code on its own
Arena Coding145th of 168 · 1347
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing117th of 168 · 1323
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 4 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
- $10.00 in / $30.00 out
- Context served
- 128K
- Throughput
- ~15 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $10.00 / $30.00checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| OpenAIDirect | $10.00 / $30.00checked 4 hours ago | 128K4K max reply | 15 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear 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 | ✓ | ✓ | ✓ |
| OpenAIDirect | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
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 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- 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 and images in, text out
- Catalogue slug
- openai-gpt-4-turbo