GPT-4
by OpenAI · openai/gpt-4 · #319 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$30.00
per 1M tokens
Output
$60.00
per 1M tokens
Blended (3:1)
$37.50
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-4 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $37.50 | $3.12 | — |
| 50% | $37.50 | $3.12 | −0% |
| 90% | $37.50 | $3.12 | −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 | $0.033 | $33.00 |
| Document summary | 8,000 | 1,000 | $0.3 | $300.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $1.02 | $1,020 |
| Long-context analysis | 150,000 | 5,000 | $4.80 | $4,800 |
Performance
Intelligence Index
7
AA composite quality
Coding Index
13.1
Math Index
—
Agentic Index
—
Output speed
44 tok/s
median
Time to first token
1.15s
median
Time to first answer
1.15s
after reasoning tokens
Specs
Context window
8K
tokens
Max output
4K
tokens
Input modalities
text
Tokenizer
GPT