GPT-4 Turbo (batch)
by OpenAI · openai/gpt-4-turbo:batch · #384 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:22 PM UTC · refreshed hourly
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.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$5.00
per 1M tokens
Output
$15.00
per 1M tokens
Blended (3:1)
$7.50
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-4 Turbo (batch) (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $7.50 | $0.525 | — |
| 50% | $7.50 | $0.525 | −0% |
| 90% | $7.50 | $0.525 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.007 | $7.00 |
| Document summary | 8,000 | 1,000 | $0.055 | $55.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.18 | $180.00 |
| Long-context analysis | 150,000 | 5,000 | $0.825 | $825.00 |
Performance
Intelligence Index
7
AA composite quality
Coding Index
21.5
Math Index
—
Agentic Index
—
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 69.4% |
| Humanity's Last Exam | 3.1% |
| LiveCodeBench | 29.1% |
| MATH-500 | 73.7% |
| AIME | 15.0% |
Specs
Context window
128K
tokens
Max output
4K
tokens
Input modalities
text, image
Tokenizer
GPT