Processing or generating 10,000 words (approximately 12,800 tokens) with GPT-5.3 Codex ranges from $0.00224 (cached input) to $0.1792 (full generation).
Quick answer
For 10,000 words, GPT-5.3 Codex processes approximately 12,800 tokens. That costs $0.0224 as uncached input, $0.00224 with the modeled cache discount, or $0.1792 when generated as output.
Method & trust
The estimate converts the selected English word count with the model tokenizer family, then applies the published input/output price per million tokens. Real prompts vary with code, formatting, language, and system instructions.
You send 10,000 words as prompt context, documentation, or background knowledge.
GPT-5.3 Codex drafts a complete 10,000 words article, chapter, or code module.
8,000 words input prompt + 2,000 words output reply.
| Model | Provider | Input Cost (10,000 words) | Cached Input Cost | Output Cost (10,000 words) | Context Limit |
|---|---|---|---|---|---|
| GPT-5.3 Codex (Current) | openai | $0.0224 | $0.00224 | $0.1792 | 256,000 |
| DeepSeek Coder V2.5 | deepseek | $0.001866 | $0.000187 | $0.003732 | 128,000 |
| Codestral 2501 | mistral | $0.003999 | $0.0004 | $0.012 | 256,000 |
| Grok Build 0.1 | xai | $0.0133 | $0.002666 | $0.0267 | 256,000 |
| Qwen 2.5 Coder 32B | qwen | $0.002666 | $0.000267 | $0.007998 | 128,000 |
| GLM-5.3 (Z.ai) | zai | $0.0187 | $0.003466 | $0.0587 | 1,048,576 |
For GPT-5.3 Codex (o200k_base tokenizer), 10,000 words is approximately 12,800 tokens (an average ratio of 1.28 tokens per word in English). Code, technical vocabulary, and non-English scripts will have higher token densities.
Sending 10,000 words as input costs $0.0224 (or $0.00224 with prompt caching). Generating 10,000 words as output costs $0.1792. Output tokens are more expensive because autoregressive token generation requires significantly more computation per token.
Yes! If your input text is part of a repeated context, prompt caching saves 50% to 90% (costing $0.00224). For non-urgent asynchronous batch processing, 24-hour batch queues provide a flat 50% discount across all tokens (costing $0.0112 for input, $0.0896 for output).
At an average human reading speed of 250 words per minute, 10,000 words takes approximately 40 minutes to read. In contrast, GPT-5.3 Codex can process or generate this text in seconds.