OpenAI: GPT-3.5 Turbo Instruct
OpenAI
OpenAI: GPT-3.5 Turbo Instruct by OpenAI costs $1.50 per 1M input tokens and $2.00 per 1M output tokens, with a 4K-token context window.
Pricing
Input (per 1M tokens)
$1.50
Output (per 1M tokens)
$2.00
Cached input (per 1M)
—
Specifications
- Provider
- OpenAI
- Context window
- 4K tokens
- Parameters
- 20B
- Released
- Sep 2023
- Open weights
- No
- Frontier model
- No
Compare OpenAI: GPT-3.5 Turbo Instruct with…
OpenAI: GPT-3.5 Turbo Instruct vs Qwen3.5 35B-A3B$2.00/1MOpenAI: GPT-3.5 Turbo Instruct vs GPT-5 Mini$2.00/1MOpenAI: GPT-3.5 Turbo Instruct vs GPT-5.1-Codex-Mini$2.00/1MOpenAI: GPT-3.5 Turbo Instruct vs Qwen3.6 27B$2.00/1MOpenAI: GPT-3.5 Turbo Instruct vs Grok Build 0.1$2.00/1MOpenAI: GPT-3.5 Turbo Instruct vs Qwen3-Next 80B-A3B Instruct$2.00/1M
FAQ
How much does OpenAI: GPT-3.5 Turbo Instruct cost?
OpenAI: GPT-3.5 Turbo Instruct is priced at $1.50 per 1M input tokens and $2.00 per 1M output tokens. Output tokens cost more than input.
What is OpenAI: GPT-3.5 Turbo Instruct's context window?
OpenAI: GPT-3.5 Turbo Instruct supports a context window of 4K tokens — the maximum prompt plus response length it can handle in a single request.
Is OpenAI: GPT-3.5 Turbo Instruct open weight?
No — OpenAI: GPT-3.5 Turbo Instruct is a closed/proprietary model accessed via API.
Data as of 2026-10-23. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.