GPT-3.5 Turbo (older v0613) API Pricing
OpenAI · context window 4K · prices updated 2026-09-15
Where GPT-3.5 Turbo (older v0613) sits on price
At $2.00 per million output tokens, GPT-3.5 Turbo (older v0613) is a mid tier model — right at the median output price of $2.08, which puts it cheaper than 53% and pricier than 47% of the models we track. It sits 26th cheapest of the 92 OpenAI models we track. Output is only 2.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
What real workloads cost on GPT-3.5 Turbo (older v0613)
These three workloads are the ones teams actually run on a mid-priced model — a $2.00/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0078 | $117 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.004 | $1200 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0008 | $24.00 |
Model your exact traffic in the API cost calculator — it preloads GPT-3.5 Turbo (older v0613) with caching and batch options.
GPT-3.5 Turbo (older v0613) price history
GPT-3.5 Turbo (older v0613)'s price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 models we track have repriced over the same period, including 9 of OpenAI's own 92 models.
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
GPT-3.5 Turbo (older v0613) vs Qwen3.6 27B
The closest-priced alternative from another vendor is Qwen3.6 27B (Alibaba (Qwen)) — priced within a rounding error on output, with $0.7 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen3.6 27B pricing →Cheaper alternatives
More OpenAI models
Frequently asked questions
› How much does the GPT-3.5 Turbo (older v0613) API cost?
GPT-3.5 Turbo (older v0613) costs $1.00 per million input tokens and $2.00 per million output tokens and no discounted cached-input tier. That works out to roughly 500,000 output tokens per dollar.
› What does the support chatbot workload cost on GPT-3.5 Turbo (older v0613)?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0078 per request and $117 per month on GPT-3.5 Turbo (older v0613). Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill GPT-3.5 Turbo (older v0613)'s 4K context window?
Sending 4K of input in a single request costs $0.0041 at $1.00 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.
› Is GPT-3.5 Turbo (older v0613) worth the price?
GPT-3.5 Turbo (older v0613) sits in the middle of the market (26 of 92 by price within OpenAI). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.