OpenAI: GPT-3.5 Turbo
Analysis Summary
OpenAI's GPT-3.5 Turbo was a widely adopted model in 2023, but it now sits well below the capability floor of current-generation alternatives. The intelligence index is low, coding performance is limited, and the 16K context window is modest by today's standards. Tool use and function calling are supported, which gives it some structured task capability, but instruction-following and reasoning quality lag significantly behind modern models.
For businesses, GPT-3.5 Turbo is primarily relevant for legacy integrations. At $0.50/1M input and $1.50/1M output, pricing is reasonable, but models like Qwen3.5-Flash or LiquidAI's smaller models offer comparable or better performance at similar or lower cost. There is little reason to start new projects on this model.
Teams with existing GPT-3.5 Turbo deployments should evaluate migration to a current-generation model. The capability gap has widened significantly since 2023, and the cost savings from staying on this model are unlikely to outweigh the quality improvements available elsewhere.
Assessed June 6, 2026
Editorial notes
GPT-3.5 Turbo is a legacy OpenAI model with limited reasoning and a 16K context window; tool use and function calling are supported, but it is outperformed by many cheaper current-generation models.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How OpenAI: GPT-3.5 Turbo compares
OpenAI: GPT-3.5 Turbo ranks #330 of 377 AI models we track for overall intelligence, #232 of 314 for coding. Its 16K-token context window is larger than 26% of the models we list. At $0.50 per million input tokens it is cheaper than 35% of comparable models.
About OpenAI: GPT-3.5 Turbo
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.
Capabilities
Benchmark Scores
Intelligence
Benchmark data from Artificial Analysis and Hugging Face
How does OpenAI: GPT-3.5 Turbo stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.50 | $0.000500 |
| Output | $1.50 | $0.001500 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
External Resources
Frequently asked questions about OpenAI: GPT-3.5 Turbo
How much does OpenAI: GPT-3.5 Turbo cost?
OpenAI: GPT-3.5 Turbo costs $0.50 per million input tokens and $1.50 per million output tokens.
What is the context window of OpenAI: GPT-3.5 Turbo?
OpenAI: GPT-3.5 Turbo has a context window of 16,385 tokens (16K).
Is OpenAI: GPT-3.5 Turbo good for coding?
On our coding benchmark index, OpenAI: GPT-3.5 Turbo ranks #232 of 314 models, placing it in the broader range of the field for code generation and debugging.
What can OpenAI: GPT-3.5 Turbo do?
OpenAI: GPT-3.5 Turbo supports tool use and function calling.
Who created OpenAI: GPT-3.5 Turbo?
OpenAI: GPT-3.5 Turbo is developed by OpenAI and was released on May 28, 2023.
