OpenAIGPT-3.5 Turbo (older v0613) pricing
$1.00 per 1M input tokens and $2.00 per 1M output tokens. In real work that is 0.24¢ per chat answer and 1.4¢ to summarize a 20-page PDF.
What GPT-3.5 Turbo (older v0613) costs per task
Token counts estimated from a measured model of the same lab (GPT-6 Luna), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.24¢$2.40 / 1,000 | 45 in · 540 out · 639 reasoning | 170 of 336 | estimated |
| Reply to a customer email | 0.04¢$0.45 / 1,000 | 258 in · 94 out | 100 of 336 | estimated |
| Write a 1,500-word blog post | 0.48¢$4.78 / 1,000 | 59 in · 2,217 out · 143 reasoning | 126 of 336 | estimated |
| Write 10 product descriptions | 0.23¢$2.32 / 1,000 | 283 in · 987 out · 34 reasoning | 85 of 336 | estimated |
| Translate 1,000 words | 0.41¢$4.12 / 1,000 | 1,330 in · 1,328 out · 67 reasoning | 134 of 336 | estimated |
| Proofread one page (500 words) | 0.22¢$2.23 / 1,000 | 718 in · 664 out · 91 reasoning | 162 of 336 | estimated |
| Summarize a 20-page PDF | 1.4¢$14.05 / 1,000 | 12,987 in · 449 out · 84 reasoning | 219 of 336 | estimated |
| Extract data from an invoice | 0.15¢$1.50 / 1,000 | 373 in · 422 out · 140 reasoning | 133 of 336 | estimated |
| Analyze a 200-row spreadsheet | 1.0¢$10.37 / 1,000 | 4,779 in · 456 out · 2,338 reasoning | 108 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.44¢$4.37 / 1,000 | 3,690 in · 234 out · 104 reasoning | 160 of 336 | estimated |
| Classify 100 support tickets | 0.33¢$3.33 / 1,000 | 1,261 in · 445 out · 590 reasoning | 113 of 336 | estimated |
| Review 500 lines of code | 1.5¢$15.07 / 1,000 | 4,557 in · 337 out · 4,921 reasoning | 182 of 336 | estimated |
| Write a SQL query | 0.17¢$1.69 / 1,000 | 126 in · 266 out · 516 reasoning | 138 of 336 | estimated |
| Run a 50-step coding agent | $2.28$2,282 / 1,000 | 2,237,500 in · 15,000 out · 7,000 reasoning | 296 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-3.5 Turbo (older v0613) through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Azureunknown | $1.00 / $2.00 | - | 4K |
Price history
First seen in our price history on Mar 26, 2024 at $1.00 input / $2.00 output. The list price has not changed since.
FAQ
How much does GPT-3.5 Turbo (older v0613) cost?
GPT-3.5 Turbo (older v0613) costs $1.00 per 1 million input tokens and $2.00 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.24¢ and summarizing a 20-page PDF about 1.4¢.
Where is GPT-3.5 Turbo (older v0613) cheapest?
Among 1 providers we track, the lowest list price today is at Azure: $1.00 input and $2.00 output per 1M tokens.
Is the GPT-3.5 Turbo (older v0613) cost per task measured or estimated?
Estimated: GPT-3.5 Turbo (older v0613) was not run directly. Tokens come from GPT-6 Luna and are rescaled by the tokenizer of OpenAI. Real usage can differ.