GPT-4o (2024-08-06) API Pricing
OpenAI · released Aug 6, 2024 · 128K context · API model ID gpt-4o-2024-08-06
GPT-4o (2024-08-06) by OpenAI API pricing: $2.50 per 1M input tokens and $10.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $2.50 |
| Output | $10.00 |
| Cache read | $1.25 |
| Cache write | Not published |
OpenAI's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$2,250
per month
- per day
- $75.00
- per request
- $0.0075
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $2,250/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $3,750/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $2,850/mo |
Context and capabilities
- Context
- 128,000 tokens
- Max output
- 16,384 tokens
- Input
- text, image
- Output
- text
- Knowledge cutoff
- September 2023
- Open weights
- No
- Tool calling
- Yes
- Reasoning
- No
- Structured outputs
- Yes
Capabilities and limits as listed by models.dev.
Similarly priced models
- Gemini 3.1 Pro Preview · $2.00 in / $12.00 out
- Claude Sonnet 5.5 · $2.00 in / $10.00 out
- GPT-6.1 Sol · $2.00 in / $10.00 out
- Kimi K3 · $3.00 in / $15.00 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does GPT-4o (2024-08-06) cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, GPT-4o (2024-08-06) costs about $2,250 per month at OpenAI's list prices ($2.50 per 1M input tokens, $10.00 per 1M output tokens).
- Does GPT-4o (2024-08-06) support prompt caching?
- Yes. Cached input costs $1.25 per 1M tokens, compared with $2.50 for regular input.
- How long is GPT-4o (2024-08-06)'s context window?
- GPT-4o (2024-08-06) accepts up to 128,000 tokens (128K) of context and returns up to 16,384 tokens per response.