GPT-4o (batch)
by OpenAI · openai/gpt-4o:batch · #307 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$1.25
per 1M tokens
Output
$5.00
per 1M tokens
Blended (3:1)
$2.19
3 input : 1 output
Cache read
$0.625
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-4o (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.19 | $0.1325 | — |
| 50% | $1.95 | $0.1013 | −24% |
| 90% | $1.77 | $0.0762 | −42% |
*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 | $0.002125 | $2.12 |
| Document summary | 8,000 | 1,000 | $0.015 | $15.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0475 | $47.50 |
| Long-context analysis | 150,000 | 5,000 | $0.2125 | $212.50 |
Performance
Intelligence Index
8.4
AA composite quality
Coding Index
—
Math Index
6
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 | 74.8% |
| GPQA Diamond | 54.3% |
| Humanity's Last Exam | 2.4% |
| LiveCodeBench | 30.9% |
| MATH-500 | 75.9% |
| AIME | 15.0% |
| AIME 2025 | 6.0% |
| IFBench | 34.3% |
| AA-LCR (Long Context Reasoning) | 49.3% |
| Terminal-Bench Hard | 8.3% |
| τ²-Bench (Telecom) | 25.1% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 843 |
| UI components | 900 |
| Data viz | 870 |
| 3D | 897 |
| Game dev | 930 |
| Code categories | 876 |
Specs
Context window
128K
tokens
Max output
16K
tokens
Input modalities
text, image, file
Tokenizer
GPT