Aion 3.5 Mini vs GPT-5.3 Codex
aion-labs/aion-3-5-mini · openai/gpt-5.3-codex
As of November 2, 2026, Aion 3.5 Mini is the cheaper API on UberLLM: $0.3063 per million input tokens and $0.6125 per million output, versus $0.1921 / $1.54 for GPT-5.3 Codex, about 55% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Aion 3.5 Mini to cut cost; choose GPT-5.3 Codex when context size wins. GPT-5.3 Codex carries the larger context window (400,000 vs 262,144 tokens), which can matter for long-document work.
Aion 3.5 Mini vs GPT-5.3 Codex, side by side
| Spec | Aion 3.5 Mini | GPT-5.3 Codex |
|---|---|---|
| Price · input / 1M | $0.3063 | $0.1921 |
| Price · output / 1M | $0.6125 | $1.54 |
| Context length | 262,144 | 400,000 |
| Max output tokens | 32,768 | 128,000 |
| Input modalities | text | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | — | Yes |
| Reasoning | Yes | Yes |
| % off list | 65% off | 89% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 2, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Aion 3.5 Mini vs GPT-5.3 Codex — FAQ
Is Aion 3.5 Mini or GPT-5.3 Codex cheaper?
Aion 3.5 Mini is cheaper on a blended token mix, by about 55%. 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 Aion 3.5 Mini and GPT-5.3 Codex?
Aion 3.5 Mini: $0.3063 in / $0.6125 out per 1M tokens. GPT-5.3 Codex: $0.1921 in / $1.54 out per 1M tokens. That's roughly a 55% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Aion 3.5 Mini and GPT-5.3 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.