GPT-4o
OpenAI · released May 13, 2024
- Type
- Proprietary
- Input
- $2.50
- Output
- $10.00
- Cached
- $1.25
List price · per 1M tokens · OpenAI at 128K context · source ↗
Our take
Written Aug 3, 2026GPT-4o is OpenAI's flagship multimodal system from May 2024, handling text, images and files in a single request with a 128,000-token limit. It is available only through hosted APIs, with identical rates across every provider we track.
Choose this for general multimodal tasks that need text, image and file understanding in one endpoint, or for 128,000-token workflows where the full window is actively used. Use it when provider flexibility matters, since every host charges the same. Skip it if you need downloadable weights for self-hosting, or if you want measured chat-quality scores or broader benchmark coverage.
The case for it
- Identical pricing across all three tracked providers eliminates arbitrage complexity.
- Fastest measured throughput on direct OpenAI hosting, at 37 tokens per second.
- Broad modality support: handles text, images and files together in one endpoint.
The case against it
- Only one measured benchmark, SWE-bench Verified at 32.6%, with no peer scores for comparison.
- Proprietary weights with no disclosed licence; no self-host option.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored GPT-4o for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
Nobody we watch has scored GPT-4o for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
GPT-4o 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 31st of 39 with 32.6.
WritingWe do not rate this
Nobody we watch has scored this model for writing. 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.
Every published score for this model1 scoreEvery figure we hold, from 1 board, 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
- $2.50 in / $10.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.50 / $10.00 | 128K | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $2.50 / $10.00 | 128K | 49 tok/s | No | No | Confirmed |
| OpenAI | $2.50 / $10.00 | 128K16K out | 57 tok/s | No | Yesunknown period | Unknown |
Microsoft Azure AIAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 1 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 |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
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
When we formed this view
Dates behind this page
Prices last checked 9d 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 3 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-4o