OpenAI: GPT-4 Turbo (batch)
by OpenAIOpenAI: GPT-4 Turbo (batch) is a large language model from OpenAI. It costs $5.00 per million input tokens and $15.00 per million output tokens. Its context window is 128K tokens.
- Input / 1M tokens
- $5.00
- Output / 1M tokens
- $15.00
- Cached input / 1M
- -
- Context window
- 128K
Not supported
tokens
This model also charges $0.01 per search request
That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.013, so the search fee is 80% on top. Per-token rankings elsewhere ignore this entirely.
Benchmarks
Independent scores published alongside the catalogue.
- Coding index
- 21.5
About GPT-4 Turbo (batch)
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.
Specifications
| Model ID | openai/gpt-4-turbo |
|---|---|
| Provider | OpenAI |
| Context window | 128K tokens |
| Max output | 4K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | 2023-12-31 |
| Open weights | No |
| Released | April 9, 2024 |
Cheaper alternatives
Models that cost less than GPT-4 Turbo (batch) while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does OpenAI: GPT-4 Turbo (batch) cost?
$5.00 per million input tokens and $15.00 per million output tokens.
What is the context window of OpenAI: GPT-4 Turbo (batch)?
128K tokens, with up to 4K tokens of output per request.
Does OpenAI: GPT-4 Turbo (batch) have extra fees beyond per-token pricing?
Yes. OpenAI: GPT-4 Turbo (batch) charges $0.01 per search request - $10.00 per 1,000 requests - on top of $5.00 per million input tokens and $15.00 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 80% on top.
Confirm against the source: OpenAI official pricing.