GPT-3.5-turbo pricing & specs
OpenAI · released 2023-03-01 · ● verified 2026-10-11 · deprecated
This model is deprecated. Cheapest compatible replacement: Llama 3.2 1B Instruct.
input / 1M$0.50
output / 1M$1.50
context16.4K
max output4.1K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs GPT-3.5-turbo |
|---|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | 131K | −97.3% |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | 16.4K | −96.3% |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | 32.8K | −94.7% |
| Gemma 3 4B IT | $0.04 | $0.08 | 131.1K | −93.3% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −93.3% |
// faq
How much does GPT-3.5-turbo cost?
GPT-3.5-turbo costs $0.50 per million input tokens and $1.50 per million output tokens. At 50M input and 10M output tokens per month that is about $40.00.
What is the context window of GPT-3.5-turbo?
16.4K tokens, with up to 4.1K output tokens per request.
Does GPT-3.5-turbo support prompt caching?
Yes. Cached input tokens cost $0 per million.
What are cheaper alternatives to GPT-3.5-turbo?
Llama 3.2 1B Instruct ($0.02 in / $0.02 out), Llama-3.1-8B-Instruct ($0.02 in / $0.05 out), Voxtral Mini 3B 2507 ($0.04 in / $0.04 out) offer the same input types and capabilities for less.
// spec sheet
- input / 1M
- $0.50
- output / 1M
- $1.50
- cache read / 1M
- $0
- blended (3:1)
- $0.75
- context
- 16.4K
- max output
- 4.1K
- input types
- text
- reasoning
- no
- tool calling
- no
- structured output
- no
- open weights
- no
- knowledge cutoff
- 2021-09-01
- price source
- OpenAI
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Llama-3.1-8B-Instruct | $0.02 | $0.05 | $1.50 |
| Voxtral Mini 3B 2507 | $0.04 | $0.04 | $2.40 |
| GPT-3.5-turbo | $0.50 | $1.50 | $40.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.