GPT-3.5-Turbo-Instruct
Poe
GPT-3.5-Turbo-Instruct by Poe costs $1.40 per 1M input tokens and $1.80 per 1M output tokens, with a 4K-token context window.
Pricing
Input (per 1M tokens)
$1.40
Output (per 1M tokens)
$1.80
Cached input (per 1M)
—
Specifications
- Provider
- Poe
- Context window
- 4K tokens
- Parameters
- 20B
- Released
- Sep 2023
- Open weights
- No
- Frontier model
- No
Compare GPT-3.5-Turbo-Instruct with…
GPT-3.5-Turbo-Instruct vs GLM 4.5V$1.80/1MGPT-3.5-Turbo-Instruct vs Llama-3.1-Nemotron-Ultra-253B-v1$1.80/1MGPT-3.5-Turbo-Instruct vs Qwen3 VL 235B A22B Instruct$1.90/1MGPT-3.5-Turbo-Instruct vs DeepSeek V4 Pro 0423$1.91/1MGPT-3.5-Turbo-Instruct vs Qwen3.6 Plus$1.95/1MGPT-3.5-Turbo-Instruct vs GLM 4.7$1.98/1M
FAQ
How much does GPT-3.5-Turbo-Instruct cost?
GPT-3.5-Turbo-Instruct is priced at $1.40 per 1M input tokens and $1.80 per 1M output tokens. Output tokens cost more than input.
What is GPT-3.5-Turbo-Instruct's context window?
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 GPT-3.5-Turbo-Instruct open weight?
No — GPT-3.5-Turbo-Instruct is a closed/proprietary model accessed via API.
Data as of 2026-10-30. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.