gpt-3.5-turbo API Pricing
gpt-3.5-turbo on OpenAI costs $0.50 per 1M input tokens and $1.50 per 1M output tokens (as of ).
| Input | $0.50 / 1M tokens |
|---|---|
| Output | $1.50 / 1M tokens |
| Cached input (read) | — |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 16K tokens |
| Max output | 4K tokens |
| Supports | tool calling, prompt caching |
| Deprecation date | |
| API model id | gpt-3.5-turbo |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $1.75 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $2.65 |
| 1 million classification calls (300 in, 5 out each) | $157.50 |
Try your own numbers in the LLM API cost calculator.
Price history
No price change recorded since .
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| gpt-4.1-mini | OpenAI | $0.40 | $1.60 | $0.10 | 1.04758M |
| gpt-5-mini | OpenAI | $0.25 | $2.00 | $0.03 | 272K |
| gpt-5.4-nano | OpenAI | $0.20 | $1.25 | $0.02 | 272K |
| gpt-audio-mini | OpenAI | $0.60 | $2.40 | — | 128K |
| gpt-5.6-luna | OpenAI | $0.20 | $1.20 | $0.02 | 922K |
| gpt-4o-mini | OpenAI | $0.15 | $0.60 | $0.07 | 128K |
| gpt-4o-mini-audio-preview- | OpenAI | $0.15 | $0.60 | — | 128K |
| gpt-4o-mini-search-preview | OpenAI | $0.15 | $0.60 | $0.07 | 128K |