GPT-3.5 Turbo Instruct

OpenAI · openai/gpt-3.5-turbo-instruct

← Back to leaderboard

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

GPT-3.5 Turbo Instruct ranks #246 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $1.75 blended per million tokens, it is cheaper than 37% of models with published API pricing. Its 4,095-token context window is 64.0× smaller than the catalog median (262,144 tokens).

texttext->text

Context

Max context: 4095
Max output: 3685

Pricing

Input / 1M: 1.50
Output / 1M: 2.00
Blend / 1M: 1.75

Quality

Quality index:

Provider

Provider: OpenAI
Moderated: yes

Monthly cost at this blended rate

Estimated API spend if every token is billed at $1.75per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$1.75
10,000,000$17.50
100,000,000$175.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from OpenAI

Closest API price