This model was retired on 2026-10-23. The pricing below is the last-known rate, kept for migration reference.
Context
128K
Max output
4K
Serving providers
4
Cheapest input
$10.00 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
32 t/s
tokens / second
Time to first token
3.27s
latency
Headline indices
Intelligence Index
7.7
of 100
Coding Index
21.5
of 100
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| GPQA Diamond (lab-claimed) | 48% | — | — | |
| Humanity's Last Exam | 3% | default | — | |
| LiveCodeBench | 29% | default | — | |
| MMLU-Pro | 69% | default | — | |
| SciCode | 32% | default | — |
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Azure | $10.00 | $30.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| OpenAI | $10.00 | $30.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Vercel AI Gateway | $10.00 | $30.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| OpenRouter | $10.00 | $30.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$4,400
estimated / month
Model IDs
copy the exact identifier for your platformazure/gpt-4-turbogpt-4-turbovercel_ai_gateway/openai/gpt-4-turboopenai/gpt-4-turbo
Frequently asked questions
GPT-4 Turbo pricing, context and availabilityIs GPT-4 Turbo still available?
GPT-4 Turbo was retired on 2026-10-23. The pricing on this page is the last-known rate, kept for migration reference.
How much did GPT-4 Turbo cost?
GPT-4 Turbo's last-known pricing, before it was retired on 2026-10-23, was $10.00 per 1M input tokens and $30.00 per 1M output tokens.
What was the context window of GPT-4 Turbo?
GPT-4 Turbo had a 128K token context window and could return up to 4K output tokens.
What could GPT-4 Turbo do?
GPT-4 Turbo supported image input (vision), tool use and prompt caching.
Other OpenAI models
compare pricing across the OpenAI lineupPopular comparisons
head-to-head pages featuring GPT-4 Turbo
GPT-4 Turbo vs Claude 3 Opus Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI