GPT-5.2 Codex vs GLM 5.3
openai/gpt-5.2-codex · z-ai/glm-5.3
As of October 31, 2026, GLM 5.3 is the cheaper API on UberLLM: $0.0022 per million input tokens and $0.0448 per million output, versus $1.48 / $11.84 for GPT-5.2 Codex, about 100% less when output is 3 tokens for every input token. These are the median prices buyers paid over the last 24 hours. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose GLM 5.3 to cut cost; choose GPT-5.2 Codex when its capabilities fit your task better.
GPT-5.2 Codex vs GLM 5.3, side by side
| Spec | GPT-5.2 Codex | GLM 5.3 |
|---|---|---|
| Price · input / 1M | $1.48 | $0.0022 |
| Price · output / 1M | $11.84 | $0.0448 |
| Context length | 256,000 | 1,000,000 |
| Max output tokens | 65,536 | 131,072 |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| Reasoning | Yes | Yes |
| % off list | 15% off | 97% off |
| First token, median (7 days) | — | 3.5 s (156 requests) |
Median prices buyers paid on UberLLM over the last 24 hours. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated October 31, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
GPT-5.2 Codex vs GLM 5.3 — FAQ
Is GPT-5.2 Codex or GLM 5.3 cheaper?
GLM 5.3 is cheaper on a blended token mix, by about 100%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between GPT-5.2 Codex and GLM 5.3?
GPT-5.2 Codex: $1.48 in / $11.84 out per 1M tokens. GLM 5.3: $0.0022 in / $0.0448 out per 1M tokens. That's roughly a 100% blended difference. Prices are live; UberLLM adds no fee.
Can I use both GPT-5.2 Codex and GLM 5.3 with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.