GPT-4o pricing & specs
OpenAI · released 2024-05-13 · ● verified 2026-10-11
input / 1M$2.50
output / 1M$10.00
context128K
max output16.4K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs GPT-4o |
|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | 1.05M | −96% |
| Claude Haiku 5.5 | $0.10 | $0.50 | 1M | −95.4% |
| GPT-6 Luna | $0.10 | $0.50 | 1.05M | −95.4% |
| GLM-5.3-Flash | $0.15 | $0.50 | 1M | −94.6% |
| GPT-4o mini | $0.15 | $0.60 | 128K | −94% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Azure | $2.50 | $10.00 |
// faq
How much does GPT-4o cost?
GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens. At 50M input and 10M output tokens per month that is about $225.
What is the context window of GPT-4o?
128K tokens, with up to 16.4K output tokens per request.
Does GPT-4o support prompt caching?
Yes. Cached input tokens cost $1.25 per million.
What are cheaper alternatives to GPT-4o?
Gemini 2.5 Flash-Lite ($0.10 in / $0.40 out), Claude Haiku 5.5 ($0.10 in / $0.50 out), GPT-6 Luna ($0.10 in / $0.50 out) offer the same input types and capabilities for less.
// spec sheet
- input / 1M
- $2.50
- output / 1M
- $10.00
- cache read / 1M
- $1.25
- blended (3:1)
- $4.375
- context
- 128K
- max output
- 16.4K
- input types
- text · image · pdf
- reasoning
- no
- tool calling
- yes
- structured output
- yes
- open weights
- no
- knowledge cutoff
- 2023-09
- price source
- OpenAI
- aliases
- gpt-4o-2024-08-06, gpt-4o-2024-11-20
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $9.00 |
| Claude Haiku 5.5 | $0.10 | $0.50 | $10.00 |
| GPT-6 Luna | $0.10 | $0.50 | $10.00 |
| GPT-4o | $2.50 | $10.00 | $225 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.