GPT-3.5 Turbo token cost

Legacy OpenAI chat model kept for migration cost checks against Mini and Nano tiers. Prefer GPT-4.1 Mini or GPT-5 Mini for new production apps.

Privacy first counting

TokenCALC counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.

Pricing snapshot

USD per 1 million tokens. Verify against the provider source before you lock budget.

RateUSD
Input / 1M$0.500
Output / 1M$1.50
Batch input / 1M$0.250
Batch output / 1M$0.750

Model details

DetailValue
ProviderOpenAI
Context window16.4K
TokenizerExact (cl100k_base)
Last verified2026-08-02
API model idgpt-3.5-turbo

Notes

Legacy; verify availability on OpenAI docs.