Claude Fable 5 vs GPT-5.2 Codex
anthropic/claude-fable-5 · openai/gpt-5.2-codex
As of November 1, 2026, Claude Fable 5 is the cheaper API on UberLLM: $0.5228 per million input tokens and $2.61 per million output, versus $0.4375 / $3.50 for GPT-5.2 Codex, about 24% 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 Claude Fable 5 to cut cost; choose GPT-5.2 Codex when its capabilities fit your task better.
Claude Fable 5 vs GPT-5.2 Codex, side by side
| Spec | Claude Fable 5 | GPT-5.2 Codex |
|---|---|---|
| Price · input / 1M | $0.5228 | $0.4375 |
| Price · output / 1M | $2.61 | $3.50 |
| Context length | 1,000,000 | 256,000 |
| Max output tokens | 128,000 | 65,536 |
| Input modalities | text, image | text, image |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | Yes |
| Reasoning | Yes | Yes |
| % off list | 94.8% off | 75% off |
Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 1, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Claude Fable 5 vs GPT-5.2 Codex — FAQ
Is Claude Fable 5 or GPT-5.2 Codex cheaper?
Claude Fable 5 is cheaper on a blended token mix, by about 24%. 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 Claude Fable 5 and GPT-5.2 Codex?
Claude Fable 5: $0.5228 in / $2.61 out per 1M tokens. GPT-5.2 Codex: $0.4375 in / $3.50 out per 1M tokens. That's roughly a 24% blended difference. Prices are live; UberLLM adds no fee.
Can I use both Claude Fable 5 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.