GPT-4 Turbo
OpenAI · released Apr 9, 2024
- Type
- Proprietary
- Input
- $10.00
- Output
- $30.00
- Cached
- Not published
List price · per 1M tokens · OpenAI at 128K context · source ↗
Our take
Written Aug 2, 2026GPT-4 Turbo is OpenAI's flagship-class model from April 2024, handling up to 128,000 tokens in a single request with text and image input. It remains a viable legacy option for teams locked to that version, though its two identical-priced offers and measured speed of eight tokens per second on the direct endpoint are clear limitations.
Pick this only when you are locked to the April 2024 OpenAI model version for an existing integration, or when you need 128,000-token context and newer GPT-4o pricing does not apply to your case. Skip it if you want price competition between providers, need faster throughput, or are starting a new project where a current release would serve better.
The case for it
- Broad capability coverage across six Arena categories, with Elo scores ranging from 1296 in maths to 1347 in coding as of July 2026.
- Handles up to 128,000 tokens in one request, useful for long-document work.
- Same pricing on both tracked hosts, so there is no penalty for choosing either provider.
The case against it
- Slow measured throughput on the primary endpoint: eight tokens per second on OpenAI, with no verified figure for the second host.
- No price competition within its own offers: both hosts charge the same rate, so there is no cheaper alternative for this exact model.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)113th of 143 · 1324.2
CodingWriting and fixing code on its own
Arena Coding121st of 143 · 1347.2
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored GPT-4 Turbo for this. We would take the rating from Arena Agent (IPS).
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-4 Turbo 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
- $10.00 in / $30.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $10.00 / $30.00 | 128K | not measured | Unknown | Unknown | Unknown |
| OpenAI | $10.00 / $30.00 | 128K4K out | 35 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 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 | ✓ | ✓ | ✓ |
| OpenAI | ✓ | ✓ | ✓ |
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
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 2 listings do not say whether they train on prompts.
- We hold no cached-input 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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image->text
- Catalogue slug
- openai-gpt-4-turbo