Gemini 3.5 Flash vs GPT-5.2 Codex
google/gemini-3.5-flash · openai/gpt-5.2-codex
As of October 31, 2026, Gemini 3.5 Flash is the cheaper API on UberLLM: $0.0615 per million input tokens and $0.3690 per million output, versus $1.48 / $11.84 for GPT-5.2 Codex, about 97% 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 Gemini 3.5 Flash to cut cost; choose GPT-5.2 Codex when its capabilities fit your task better.
Gemini 3.5 Flash vs GPT-5.2 Codex, side by side
| Spec | Gemini 3.5 Flash | GPT-5.2 Codex |
|---|---|---|
| Price · input / 1M | $0.0615 | $1.48 |
| Price · output / 1M | $0.3690 | $11.84 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 65,536 | 65,536 |
| Input modalities | text, image | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | Yes |
| Reasoning | — | Yes |
| % off list | 96% off | 15% off |
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?
Gemini 3.5 Flash vs GPT-5.2 Codex — FAQ
Is Gemini 3.5 Flash or GPT-5.2 Codex cheaper?
Gemini 3.5 Flash is cheaper on a blended token mix, by about 97%. 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 Gemini 3.5 Flash and GPT-5.2 Codex?
Gemini 3.5 Flash: $0.0615 in / $0.3690 out per 1M tokens. GPT-5.2 Codex: $1.48 in / $11.84 out per 1M tokens. That's roughly a 97% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Gemini 3.5 Flash and GPT-5.2 Codex 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.