GPT-3.5 Turbo (older v0613)
OpenAI · Released Jan 2024
GPT-3.5 Turbo (June 2023 snapshot) is OpenAI's lightweight language model for chat and code tasks, with a 4K token context window.
- Strengths
- Fast inference and lower computational overhead relative to larger models like GPT-4, with reasonable performance on routine text generation and code completion tasks.
- Best for
- Applications requiring quick responses and low latency where a smaller context window is sufficient, or cost-sensitive workloads that don't need advanced reasoning or extended document processing.
- Limitations
- The 4K context window significantly limits handling of longer documents or conversation histories; this snapshot is older than subsequently released GPT-3.5 Turbo variants and superseded by GPT-4o and lighter alternatives like GPT-4o-mini.
Input / 1M
$1.00
Output / 1M
$2.00
Cached input / 1M
—
Context window
4K
Price history
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 11 Jun 2026 | $1.00 | $2.00 | — | Imported from OpenRouter | openrouter.ai |