OpenAI: GPT-3.5 Turbo (older v0613)
Analysis Summary
GPT-3.5 Turbo (v0613) is a legacy OpenAI model from early 2024, representing one of the older variants in the GPT-3.5 family. It supports tool use and function calling, which gave it early agentic utility, but carries no current benchmark data and a 4,095-token context window. At $1.00/$2.00 per million tokens, it is not cheap for what it delivers.
For business use, the model is largely obsolete. The 4K context cap is a hard constraint for most document or code tasks, and without benchmark data, reasoning and instruction-following quality cannot be reliably assessed against current alternatives. Tool use support is its main residual value.
Teams still using this endpoint should migrate to a current-generation model. GPT-4o Mini or comparable models offer substantially better performance, larger context windows, and competitive pricing.
Assessed June 6, 2026
Editorial notes
GPT-3.5 Turbo v0613 is a legacy OpenAI model with tool use and function calling but no current benchmark data, a 4K context cap, and multiple generations of successors now available.
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 (older v0613) compares
Its 4K-token context window is larger than 21% of the models we list. At $1.00 per million input tokens it is cheaper than 25% of comparable models.
About OpenAI: GPT-3.5 Turbo (older v0613)
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
How does OpenAI: GPT-3.5 Turbo (older v0613) stack up?
Compare side-by-side with other legacy models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.00 | $0.001000 |
| Output | $2.00 | $0.002000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about OpenAI: GPT-3.5 Turbo (older v0613)
How much does OpenAI: GPT-3.5 Turbo (older v0613) cost?
OpenAI: GPT-3.5 Turbo (older v0613) costs $1.00 per million input tokens and $2.00 per million output tokens.
What is the context window of OpenAI: GPT-3.5 Turbo (older v0613)?
OpenAI: GPT-3.5 Turbo (older v0613) has a context window of 4,095 tokens (4K).
What can OpenAI: GPT-3.5 Turbo (older v0613) do?
OpenAI: GPT-3.5 Turbo (older v0613) supports tool use and function calling.
Who created OpenAI: GPT-3.5 Turbo (older v0613)?
OpenAI: GPT-3.5 Turbo (older v0613) is developed by OpenAI and was released on January 25, 2024.
