OpenAIreasoningGPT-5.1-Codex pricing
$1.25 per 1M input tokens and $10.00 per 1M output tokens. In real work that is 0.67¢ per chat answer and 2.1¢ to summarize a 20-page PDF.
What GPT-5.1-Codex costs per task
Token counts estimated from a measured model of the same lab (GPT-6.1 Sol), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.67¢$6.69 / 1,000 | 45 in · 560 out · 103 reasoning | 243 of 336 | estimated |
| Reply to a customer email | 0.16¢$1.58 / 1,000 | 258 in · 126 out | 206 of 336 | estimated |
| Write a 1,500-word blog post | 2.3¢$22.95 / 1,000 | 59 in · 2,116 out · 172 reasoning | 249 of 336 | estimated |
| Write 10 product descriptions | 1.2¢$12.10 / 1,000 | 283 in · 1,103 out · 72 reasoning | 221 of 336 | estimated |
| Translate 1,000 words | 1.5¢$14.99 / 1,000 | 1,330 in · 1,289 out · 44 reasoning | 213 of 336 | estimated |
| Proofread one page (500 words) | 0.75¢$7.52 / 1,000 | 718 in · 662 out | 244 of 336 | estimated |
| Summarize a 20-page PDF | 2.1¢$21.31 / 1,000 | 12,987 in · 482 out · 26 reasoning | 246 of 336 | estimated |
| Extract data from an invoice | 0.50¢$4.97 / 1,000 | 373 in · 450 out | 224 of 336 | estimated |
| Analyze a 200-row spreadsheet | 8.1¢$80.69 / 1,000 | 4,779 in · 919 out · 6,553 reasoning | 269 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.90¢$9.03 / 1,000 | 3,690 in · 442 out | 224 of 336 | estimated |
| Classify 100 support tickets | 0.68¢$6.77 / 1,000 | 1,261 in · 442 out · 77 reasoning | 167 of 336 | estimated |
| Review 500 lines of code | 4.5¢$45.48 / 1,000 | 4,557 in · 1,135 out · 2,843 reasoning | 249 of 336 | estimated |
| Write a SQL query | 0.47¢$4.75 / 1,000 | 126 in · 312 out · 147 reasoning | 215 of 336 | estimated |
| Run a 50-step coding agent | 53¢$532 / 1,000 | 2,237,500 in · 15,000 out | 178 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-5.1-Codex through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Azureunknown | $1.25 / $10.00 | $0.13 | 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-Codex cost?
GPT-5.1-Codex costs $1.25 per 1 million input tokens and $10.00 per 1 million output tokens, with cached input at $0.13 (list price on Oct 18, 2026). In practice one chat answer costs about 0.67¢ and summarizing a 20-page PDF about 2.1¢.
Where is GPT-5.1-Codex cheapest?
Among 1 providers we track, the lowest list price today is at Azure: $1.25 input and $10.00 output per 1M tokens.
Does GPT-5.1-Codex 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-Codex cost per task measured or estimated?
Estimated: GPT-5.1-Codex was not run directly. Tokens come from GPT-6.1 Sol and are rescaled by the tokenizer of OpenAI. Real usage can differ.