# GPT-5-Chat API prices

GPT-5-Chat (gpt-codex) — 400k context, 128k max output.
5 metered per-token offers from 5 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Poe | $1.1 | $9 | $0.11 | 128k |
| Jiekou.AI | $1.125 | $9 | — | 400k |
| Helicone | $1.25 | $10 | $0.125 | 128k |
| Merge Gateway | $1.25 | $10 | $0.125 | 128k |
| OrcaRouter | $1.25 | $10 | $0.125 | 400k |

## Summary

- Cheapest input: $1.1 per 1M tokens (Poe)
- Cheapest output: $9 per 1M tokens (Poe)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-08-07
- Inputs: image, pdf, text

## FAQ

### What is the cheapest GPT-5-Chat API?

As of Oct 4, 2026, Poe has the lowest GPT-5-Chat output price at $9 per 1M tokens, and Poe has the lowest input price at $1.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-5-Chat?

5 providers list GPT-5-Chat on Sovyron; 5 of them sell it at a metered per-token price.

### Is GPT-5-Chat free?

No provider in the Sovyron catalog lists a free tier for GPT-5-Chat.

### What is the context window of GPT-5-Chat?

GPT-5-Chat supports a 400k-token context window and up to 128k output tokens.

HTML page: https://sovyron.com/models/gpt-5-chat/
Full dataset: https://sovyron.com/data/catalog.json