One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.50 = $0.50
- Output0.1M x $1.50 = $0.15
$0.65per session
OpenAI - Closed weights
GPT-3.5 Turbo is a closed-weights model from OpenAI that costs $0.50 per 1M input tokens and $1.50 per 1M output tokens on the first-party API, with a 16K-token context window.
Last verified from developers.openai.com. All sources
| Item | Price / 1M tokens |
|---|---|
| Input | $0.50 |
| Output | $1.50 |
| Batch inputBatch requests | $0.25 |
| Batch outputBatch requests | $0.75 |
Note: Legacy model. Default snapshot gpt-3.5-turbo-0125; the Batch price is the pricing page's gpt-3.5-turbo-0125 row (the alias itself has no Batch row). gpt-3.5-turbo-1106 is priced separately at $1 / $2. release date blank: the changelog only records the gpt-3.5-turbo-0125 snapshot (2024-02-01), not the original launch.
gpt-3.5-turboopenai/gpt-3.5-turboModel page lists function calling and structured outputs as not supported and shows no cached-input rate. Not stated means the provider's docs do not say either way. It is not the same as No. Checked against provider docs on . Compare capabilities across models.
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
1M input tokens and 100K output tokens, no caching.
$0.65per session
10,000 requests a day at 2K input and 500 output tokens each.
$17.50per day
$525.00 per 30-day month
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GPT-3.5 Turbo (this page) | $0.50 | $1.50 |
| Aya Expanse 32BCohere | $0.50 | $1.50 |
| Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.50 |
| Mistral Large 3Mistral AI | $0.50 | $1.50 |
| Qwen3-Coder-FlashAlibaba Cloud (Qwen) | $0.30 | $1.50 |
| GPT-4.1 MiniOpenAI | $0.40 | $1.60 |
| GPT-5.4 nanoOpenAI | $0.20 | $1.25 |
| GPT-5.6 LunaOpenAI | $0.20 | $1.20 |
| GPT-3.5 Turbo InstructOpenAI | $1.50 | $2 |
| GPT-5 MiniOpenAI | $0.25 | $2 |
| GPT-4o MiniOpenAI | $0.15 | $0.60 |
GPT-3.5 Turbo costs $0.50 per 1M input tokens and $1.50 per 1M output tokens on OpenAI's first-party API, per developers.openai.com on October 17, 2026. Per 1M tokens, the batch rate is $0.25 input and $0.75 output.
GPT-3.5 Turbo has a 16,385-token context window and returns up to 4,096 output tokens per response.
No. GPT-3.5 Turbo is a closed-weights model. You call it through OpenAI's API as gpt-3.5-turbo or through Vercel AI Gateway as openai/gpt-3.5-turbo.
Last verified from developers.openai.com.
Newsletter
One email per week. New model releases, price cuts and what they mean for your bill.