GPT-3.5 Turbo Pricing
FastOpenAI · 16K tokens context
GPT-3.5 Turbo from OpenAI costs $0.500 per 1 million input tokens and $1.50 per 1 million output tokens as of May 2026 (live OpenRouter data). The model supports a 16,385-token context window (approximately 12,289 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0005 in input charges; a 10,000-token request costs $0.0050.
| Input price | $0.500 / 1M tokens |
|---|---|
| Output price | $1.50 / 1M tokens |
| Output / input ratio | 3.0× |
| Context window | 16,385 tokens (~12,289 words) |
| Maximum output | 4,096 tokens |
| Cost per 1K tokens (input) | $0.0005 |
| Tier | Fast |
| Last verified |
GPT-3.5 Turbo is the previous workhorse model from OpenAI. Cheap and fast, but generally outclassed by GPT-4o mini at similar or lower price points. Still common in legacy integrations.
Input Price
$0.500
per 1 million tokens
Output Price
$1.50
per 1 million tokens
Context Window
16K tokens
max 4K output
Cost Examples
| Request Type | Tokens | Input Cost | Output Cost |
|---|---|---|---|
| 1,000 word article | 1,333 | $0.000666 | $0.0006 |
| 10-page document (2,500 words) | 3,333 | $0.00167 | $0.0015 |
| 1,000 lines of code | 5,000 | $0.0025 | $0.00225 |
| 100K token document | 100,000 | $0.05 | $0.045 |
Output cost estimated at 30% of input token count. Use the calculator for exact figures.
Strengths
- ✓Very low cost
- ✓Fast response time
- ✓Huge ecosystem of tooling and prompts
Limitations
- –Outperformed by GPT-4o mini at lower cost
- –Small 16K context
- –Weaker reasoning
Best Use Cases
Calculate GPT-3.5 Turbo Costs
Use the TokenRate calculator to convert any budget, token count, or text into exact GPT-3.5 Turbo costs — and compare across all models.
Open Calculator →GPT-3.5 Turbo — FAQ
Related Models
Related Guides