GPT-3.5 Turbo pricing & benchmarks
GPT-3.5 Turbo is available from OpenAI at $0.500 per million input tokens and $1.50 per million output tokens ($0.750 blended at 3:1). It accepts up to 16,385 tokens of context. GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
Pricing
Per million tokens · OpenRouter
Input$0.500
Output$1.50
Blended (3:1)$0.750
Specification
openai/gpt-3.5-turbo
Context window16K
Max output4K
ReleasedMay 2023
LicenceProprietary
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 27.2% ±2.0 | — | 2025-01-27 | Independently run · Epoch AI |
| OTIS Mock AIME | 2.2% ±2.2 | — | 2026-08-07 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| Mistral Nemo | Mistral AI | $0.022 (−97%) | 29.9% | Compare → |
| Mistral Small 3 | Mistral AI | $0.058 (−92%) | 45.3% | Compare → |
| gpt-oss-120b | OpenAI | $0.070 (−91%) | 75.8% | Compare → |
| Phi 4 | Microsoft | $0.088 (−88%) | 56.1% | Compare → |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−85%) | 91.0% | Compare → |
Compare GPT-3.5 Turbo
FAQ
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo costs $0.500 per million input tokens and $1.50 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.750 per million tokens.
What is GPT-3.5 Turbo's context window?
GPT-3.5 Turbo accepts up to 16,385 tokens of context, and can generate up to 4,096 output tokens.
How good is GPT-3.5 Turbo on benchmarks?
GPT-3.5 Turbo scores 27.2% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as GPT-3.5 Turbo?
Yes — 5 models in our catalogue cost less per token than GPT-3.5 Turbo and score at least as high on the same benchmark. The cheapest is Mistral Nemo at $0.022 per million tokens blended.