GPT-5.1 pricing
$1.25 per 1M input tokens and $10.00 per 1M output tokens. In real work that is 1.2¢ per chat answer and 2.2¢ to summarize a 20-page PDF.
What GPT-5.1 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 | 1.2¢$11.85 / 1,000 | 45 in · 540 out · 639 reasoning | 282 of 336 | estimated |
| Reply to a customer email | 0.13¢$1.26 / 1,000 | 258 in · 94 out | 185 of 336 | estimated |
| Write a 1,500-word blog post | 2.4¢$23.67 / 1,000 | 59 in · 2,217 out · 143 reasoning | 258 of 336 | estimated |
| Write 10 product descriptions | 1.1¢$10.56 / 1,000 | 283 in · 987 out · 34 reasoning | 214 of 336 | estimated |
| Translate 1,000 words | 1.6¢$15.61 / 1,000 | 1,330 in · 1,328 out · 67 reasoning | 220 of 336 | estimated |
| Proofread one page (500 words) | 0.84¢$8.45 / 1,000 | 718 in · 664 out · 91 reasoning | 254 of 336 | estimated |
| Summarize a 20-page PDF | 2.2¢$21.56 / 1,000 | 12,987 in · 449 out · 84 reasoning | 250 of 336 | estimated |
| Extract data from an invoice | 0.61¢$6.09 / 1,000 | 373 in · 422 out · 140 reasoning | 249 of 336 | estimated |
| Analyze a 200-row spreadsheet | 3.4¢$33.91 / 1,000 | 4,779 in · 456 out · 2,338 reasoning | 199 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.80¢$7.99 / 1,000 | 3,690 in · 234 out · 104 reasoning | 218 of 336 | estimated |
| Classify 100 support tickets | 1.2¢$11.93 / 1,000 | 1,261 in · 445 out · 590 reasoning | 221 of 336 | estimated |
| Review 500 lines of code | 5.8¢$58.28 / 1,000 | 4,557 in · 337 out · 4,921 reasoning | 261 of 336 | estimated |
| Write a SQL query | 0.80¢$7.98 / 1,000 | 126 in · 266 out · 516 reasoning | 264 of 336 | estimated |
| Run a 50-step coding agent | 59¢$591 / 1,000 | 2,237,500 in · 15,000 out · 7,000 reasoning | 185 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-5.1 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
OpenAIunknown | $0.62 / $5.00 | $0.062 | 400K | |
Azureunknown | $1.25 / $10.00 | $0.13 | 400K | 100% |
OpenAIunknown | $1.25 / $10.00 | $0.12 | 400K | 100% |
Azureunknown | $1.38 / $11.00 | $0.14 | 400K | |
OpenAIunknown | $2.50 / $20.00 | $0.25 | 400K |
Price history
First seen in our price history on Nov 14, 2025 at $1.25 input / $10.00 output. The list price has not changed since.
FAQ
How much does GPT-5.1 cost?
GPT-5.1 costs $1.25 per 1 million input tokens and $10.00 per 1 million output tokens, with cached input at $0.12 (list price on Oct 18, 2026). In practice one chat answer costs about 1.2¢ and summarizing a 20-page PDF about 2.2¢.
Where is GPT-5.1 cheapest?
Among 5 providers we track, the lowest list price today is at OpenAI: $0.62 input and $5.00 output per 1M tokens.
Does GPT-5.1 charge for reasoning tokens?
Yes. Reasoning (thinking) tokens are billed as output tokens. That is why the cost per task can be much higher than the visible answer suggests - our task costs include them.
Is the GPT-5.1 cost per task measured or estimated?
Estimated: GPT-5.1 was not run directly. Tokens come from GPT-6 Luna and are rescaled by the tokenizer of OpenAI. Real usage can differ.