Qwen/Qwen3.8-Max vs OpenAI: GPT-5.3-Codex
They cost about the same for input tokens: Qwen/Qwen3.8-Max $1.65 per M, OpenAI: GPT-5.3-Codex $1.75 per M. Qwen/Qwen3.8-Max is 2.8× cheaper for output tokens: Qwen/Qwen3.8-Max costs $4.95 per M and OpenAI: GPT-5.3-Codex costs $14.00 per M. OpenAI: GPT-5.3-Codex reads more: Qwen/Qwen3.8-Max takes up to 256,000 tokens of context and OpenAI: GPT-5.3-Codex up to 400,000. Qwen/Qwen3.8-Max accepts text; OpenAI: GPT-5.3-Codex accepts file, image, text.
| Qwen/Qwen3.8-Max | OpenAI: GPT-5.3-Codex | |
|---|---|---|
| Model id | Qwen/Qwen3.8-Max | openai/gpt-5.3-codex |
| Input | $1.65 per M | $1.75 per M |
| Output | $4.95 per M | $14.00 per M |
| Context length | 256,000 tokens | 400,000 tokens |
| Accepts | text | file, image, text |
| Produces | text | text |
| Served by | deepinfra | openai |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.