GPT-4 Turbo

OpenAIopenai/gpt-4-turboProviders: 1
Inputi$10per 1M tokens
Outputi$30per 1M tokens
Contexti128K128,000 tokens
ReleasedApr 9, 2024Max output: 4K

Where it stands

Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.

100110120130140150160170$0.01$0.03$0.1$0.3$1$3$10$30$100Overall indexPrice per million tokens, log scale (3 parts input to 1 part output)↖ Cheaper and smarterGPT-4 Turbo
Scores: Epoch AI (CC BY 4.0). Prices: OpenRouter. View as a table

About this model

GPT-4 Turbo is an AI model from OpenAI, made available through the API on April 9, 2024. It can read up to 128,000 tokens in one request, roughly 240 pages of text, and write up to 4,096 tokens in a single answer. Besides text, it accepts images as input.

Through the API it costs $10 per million input tokens and $30 per million output tokens. It is among the more expensive models we track, a price usually reserved for the most capable, flagship-class models.

It can call tools and functions, so developers can connect it to search, databases or other software.

Quality scores

Rankings →
127.3Overall index · #119 of 136
  • GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.46.6%#102 of 116
  • AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.6.7%#101 of 112
  • FrontierMathOriginal, unpublished math problems written by professional mathematicians, from advanced to research level. Share solved.0.7%#71 of 73

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
OpenAIOfficial
$10$30128K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call GPT-4 Turbo through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4-turbo", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $14.00
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.53
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $6,600

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
$10$501MCompare with ⇄
Fugu Ultra v2Sakana AI
$5$301MCompare with ⇄
$4.35$8.701MCompare with ⇄
Qwen3.8 Max PrimeAlibaba Qwen
$4$121MCompare with ⇄
Ember-1Fireworks AI
$3$151MCompare with ⇄
Aion 3.5Aion Labs
$3$6256KCompare with ⇄

News about OpenAI

See all →

Frequently asked questions

How much does GPT-4 Turbo cost?
GPT-4 Turbo costs $10 per million input tokens and $30 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $14.00.
What is the context window of GPT-4 Turbo?
GPT-4 Turbo can read up to 128,000 tokens in one request, about 240 pages of text. It can write up to 4,096 tokens in a single answer.
Is GPT-4 Turbo open source?
No. GPT-4 Turbo is a closed model: its weights are not published, so you use it through OpenAI’s own apps and API, or through cloud providers.
Who makes GPT-4 Turbo?
GPT-4 Turbo is made by OpenAI. It became available through the API on April 9, 2024.
How good is GPT-4 Turbo?
GPT-4 Turbo has an overall index of 127.3 in Epoch AI’s independent tests, ranking #119 of 136 models we track.
Can GPT-4 Turbo read images?
Yes. Besides text, it accepts images as input.
What are the alternatives to GPT-4 Turbo?
Models with a similar price from other companies include Claude Fable 5.1, Fugu Ultra v2 and MiMo-V2.6-Pro-UltraSpeed. You can compare them side by side on this page.