GPT-4o (2024-08-06) API pricing
As of October 22, 2026, OpenAI GPT-4o (2024-08-06) costs $2.50 per million input tokens and $10.00 per million output tokens on OpenAI's own API, with cached input at $1.25 per million.
GPT-4o (2024-08-06) benchmarks and specs · Every OpenAI model's price
- Input, per million tokens$2.50
- Output, per million tokens$10.00
- Cached input, per million$1.25
- Context window128K tokens
- Max output16K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0075 | $7.50 | Yes |
| Repository review | 50K input + 3K output tokens | $0.155 | $155.00 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.600 | $600.00 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We have read OpenAI's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $2.50 input, $10.00 output
Cheaper models as good as GPT-4o (2024-08-06)
Models within two points of GPT-4o (2024-08-06) or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Phi 4$0.14 Overall 24.7 against 26.3 · 99% cheaper output
- gpt-oss-20b$0.15 Overall 38.5 against 26.3 · 99% cheaper output
- Gemma 3 12B$0.1625 Overall 28.0 against 26.3 · 98% cheaper output
- Qwen3.5-Flash$0.26 Overall 50.1 against 26.3 · 97% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 26.3 · 97% cheaper output
GPT-4o (2024-08-06) pricing questions
- How much does GPT-4o (2024-08-06) cost per million tokens?
- $2.50 per million input tokens and $10.00 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does GPT-4o (2024-08-06) support prompt caching?
- Yes. OpenRouter lists cached input at $1.25 per million tokens, against $2.50 for uncached input.
- Is there a cheaper model as good as GPT-4o (2024-08-06)?
- Phi 4 scores 24.7 on the LLMBenchmark Index, within two points of GPT-4o (2024-08-06) or above it, and costs $0.14 per million output tokens.
- Has the price of GPT-4o (2024-08-06) changed?
- Not since we started recording it daily on October 21, 2026.