OpenAIGPT-5.3-Codex pricing
$1.75 per 1M input tokens and $14.00 per 1M output tokens. In real work that is 1.7¢ per chat answer and 3.0¢ to summarize a 20-page PDF.
What GPT-5.3-Codex 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 | 1.7¢$16.58 / 1,000 | 45 in · 540 out · 639 reasoning | 297 of 336 | estimated |
| Reply to a customer email | 0.18¢$1.77 / 1,000 | 258 in · 94 out | 216 of 336 | estimated |
| Write a 1,500-word blog post | 3.3¢$33.14 / 1,000 | 59 in · 2,217 out · 143 reasoning | 277 of 336 | estimated |
| Write 10 product descriptions | 1.5¢$14.79 / 1,000 | 283 in · 987 out · 34 reasoning | 246 of 336 | estimated |
| Translate 1,000 words | 2.2¢$21.86 / 1,000 | 1,330 in · 1,328 out · 67 reasoning | 254 of 336 | estimated |
| Proofread one page (500 words) | 1.2¢$11.83 / 1,000 | 718 in · 664 out · 91 reasoning | 273 of 336 | estimated |
| Summarize a 20-page PDF | 3.0¢$30.19 / 1,000 | 12,987 in · 449 out · 84 reasoning | 260 of 336 | estimated |
| Extract data from an invoice | 0.85¢$8.52 / 1,000 | 373 in · 422 out · 140 reasoning | 271 of 336 | estimated |
| Analyze a 200-row spreadsheet | 4.7¢$47.48 / 1,000 | 4,779 in · 456 out · 2,338 reasoning | 238 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 1.1¢$11.19 / 1,000 | 3,690 in · 234 out · 104 reasoning | 245 of 336 | estimated |
| Classify 100 support tickets | 1.7¢$16.70 / 1,000 | 1,261 in · 445 out · 590 reasoning | 242 of 336 | estimated |
| Review 500 lines of code | 8.2¢$81.59 / 1,000 | 4,557 in · 337 out · 4,921 reasoning | 281 of 336 | estimated |
| Write a SQL query | 1.1¢$11.17 / 1,000 | 126 in · 266 out · 516 reasoning | 277 of 336 | estimated |
| Run a 50-step coding agent | 83¢$828 / 1,000 | 2,237,500 in · 15,000 out · 7,000 reasoning | 219 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving GPT-5.3-Codex through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Azureunknown | $1.75 / $14.00 | $0.17 | 400K | |
OpenAIunknown | $1.75 / $14.00 | $0.17 | 400K | 100% |
OpenAIunknown | $3.50 / $28.00 | $0.35 | 400K |
Price history
First seen in our price history on Mar 3, 2026 at $1.75 input / $14.00 output. The list price has not changed since.
FAQ
How much does GPT-5.3-Codex cost?
GPT-5.3-Codex costs $1.75 per 1 million input tokens and $14.00 per 1 million output tokens, with cached input at $0.17 (list price on Oct 18, 2026). In practice one chat answer costs about 1.7¢ and summarizing a 20-page PDF about 3.0¢.
Where is GPT-5.3-Codex cheapest?
Among 3 providers we track, the lowest list price today is at Azure: $1.75 input and $14.00 output per 1M tokens.
Does GPT-5.3-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-5.3-Codex cost per task measured or estimated?
Estimated: GPT-5.3-Codex was not run directly. Tokens come from GPT-6 Luna and are rescaled by the tokenizer of OpenAI. Real usage can differ.