GPT-4 Turbo
OpenAI's extended GPT-4 variant adding vision input.
Key Specifications
- Context window
- 128K tokens
- Max output
- 4K tokens
- Knowledge cutoff
- Released
- Inputs
- Text, image
- Capabilities Show details
- Function calling Connect to external tools, APIs, and systems.
Hosted API pricing
| Provider | Input /1M tokens | Output /1M tokens | Cost at 10M in + 2M out | |
|---|---|---|---|---|
|
OpenAI
Creator
|
$10.00 | $30.00 | $160.00 | View |
Azure
|
$10.00 | $30.00 | $160.00 | View |
Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.
Similarly priced models
The models nearest GPT-4 Turbo by blended rate, each at its own cheapest provider.
| Model | Blended /1M | Input /1M | Output /1M | Context | Cutoff | vs GPT-4 Turbo |
|---|---|---|---|---|---|---|
Claude Opus 4.6
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | May 2025 | −37% |
|
Claude Opus 4.7
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | Jan 2026 | −37% |
|
Claude Opus 4.8
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | Jan 2026 | −37% |
|
Claude Opus 5
Anthropic
|
$8.3333 | $5.00 | $25.00 | 1M | May 2026 | −37% |
|
GPT-5.5
OpenAI
|
$9.1667 | $5.00 | $30.00 | 1M | Dec 2025 | −31% |
|
GPT-4 Turbo
This model
OpenAI
|
$13.3333 | $10.00 | $30.00 | 128K | Dec 2023 | |
|
Claude Fable 5
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jan 2026 | +25% |
|
Claude Fable 5.1
Anthropic
|
$16.6667 | $10.00 | $50.00 | 1M | Jun 2026 | +25% |
|
GPT-6 Astra
OpenAI
|
$16.6667 | $10.00 | $50.00 | 1M | Apr 2026 | +25% |
|
o1
OpenAI
|
$22.50 | $15.00 | $60.00 | 200K | Oct 2023 | +69% |
|
o3-pro
OpenAI
|
$30.00 | $20.00 | $80.00 | 200K | Jun 2024 | +125% |
Prices are USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.
Frequently Asked Questions
What is GPT-4 Turbo good for?
Apps built on the GPT-4 generation that need more context than the original GPT-4, with image input and tool calling. OpenAI now recommends newer models such as GPT-4o.
When is GPT-4 Turbo not a good fit?
Long single responses, since its maximum output is short, and structured output or hosted tools, which it lacks. It sits high in OpenAI's price range, and OpenAI plans to shut down the API model in October 2026.
What is the cheapest way to run GPT-4 Turbo?
The cheapest hosted rate is $10.00 / $30.00 per 1M tokens via OpenAI.
How does GPT-4 Turbo compare with GPT-4?
OpenAI calls GPT-4 Turbo the next generation of GPT-4, designed as a cheaper, more capable version of that model. GPT-4 Turbo lists at 67% less per 1M input tokens and 50% less per 1M output tokens than GPT-4. It came out 13 months later, has a larger context (128K against 8K tokens) and a smaller max output (4K against 8K tokens) and takes image input, which GPT-4 does not.
Can I self-host GPT-4 Turbo?
No. OpenAI does not publish the weights; GPT-4 Turbo is available only through hosted APIs.
More from OpenAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
o3-deep-research
|
200K | $10.00 | $40.00 |
|
GPT-6 Astra
|
1M | $10.00 | $50.00 |
|
GPT-5.5
|
1M | $5.00 | $30.00 |
|
o1
|
200K | $15.00 | $60.00 |
|
o3-pro
|
200K | $20.00 | $80.00 |
|
GPT-5 Pro
|
400K | $15.00 | $120.00 |
|
GPT-4
|
8K | $30.00 | $60.00 |
|
GPT-5.4
|
1M | $2.50 | $15.00 |