GPT-4 Turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
gpt-4-turboReleased 9 Apr 2024 (Apr 2024)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $10.00 | $30.00 |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$5,250
- RAG over documents2,000 requests a day, 8K in / 0.6K out$5,880
- Coding agent1,000 requests a day, 40K in / 2K out$13,800
- Overnight batch20,000 requests a day, 4K in / 0.4K out$31,200
Where to run it
3 hosts serve GPT-4 Turbo. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-4-turbo | $10.00 / $30.00 | gpt-4-turbo | |
Vercel AI GatewayGateway gpt-4-turbo | $10.00 / $30.00 | gpt-4-turbo | |
Azure OpenAICloud gpt-4-turbo | $11.00 / $33.00 +10% vs headline | gpt-4-turbo |
Show 3 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2024-04-09 gpt-4-turbo-2024-04-09 | $10.00 / $30.00 | gpt-4-turbo-2024-04-09 | |||||
| Azure OpenAI | |||||||
| 2024-04-09 gpt-4-turbo-2024-04-09 | $11.00 / $33.00 +10% vs headline | gpt-4-turbo-2024-04-09 | |||||
| us-gov gpt-4-turbo | $12.50 / $37.50 +25% vs headline | gpt-4-turbo | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImagesPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 68% less
- 73% less
- 87% less
Other frontier labs
- 47% less
- 73% less
- 80% less
- 73% less
Open-weight picks
- 73% less
- 86% less
- 87% less
- 89% less
Model line
Newer and older versions, at each lab's own price.
- Apr 2024GPT-4 TurboThis page$10.00 / $30.00
- Jan 2024GPT-3.5 Turbo$0.50 / $1.50
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-4-turbo", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4-turbo", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-4-turbo",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4 Turbo cost?
On OpenAI, GPT-4 Turbo costs $10.00 per million input tokens and $30.00 per million output tokens.
Which APIs offer GPT-4 Turbo?
GPT-4 Turbo runs on 3 APIs: OpenAI, Vercel AI Gateway and Azure OpenAI.
What is GPT-4 Turbo's context window?
128K tokens, with up to 4K tokens in one reply.
Is GPT-4 Turbo being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to GPT-4 Turbo?
Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (68% less), Claude Opus 5.5 on Anthropic (47% less), Gemini 4 Carbon on Google AI Studio (73% less) and Kimi K3.1 Pro on Databricks (73% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-4 Turbo released?
OpenAI released it on 9 Apr 2024.
What is GPT-4 Turbo's API model id?
Use gpt-4-turbo with OpenAI.
Sources
Raw catalog entry for gpt-4-turbo on OpenAI
{
"deprecation_date": "2026-10-23",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-5.6-sol",
"input_cost_per_token": 0.00001,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00003,
"fedramp_uplift_multiplier": 1.1,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
}