# GPT-4 API prices

GPT-4 (gpt) — 8k context, 8k max output.
7 metered per-token offers from 7 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Eden AI | $30 | $60 | — | 8k |
| Kilo Gateway | $30 | $60 | — | 8k |
| DevPass (LLM Gateway) | $30 | $60 | — | 8k |
| LLM Gateway | $30 | $60 | — | 8k |
| Merge Gateway | $30 | $60 | — | 8k |
| OpenRouter | $30 | $60 | — | 8k |
| OrcaRouter | $30 | $60 | — | 8k |

## Summary

- Cheapest input: $30 per 1M tokens (Eden AI)
- Cheapest output: $60 per 1M tokens (Eden AI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2023-11-06
- Inputs: pdf, text

## FAQ

### What is the cheapest GPT-4 API?

As of Oct 4, 2026, Eden AI has the lowest GPT-4 output price at $60 per 1M tokens, and Eden AI has the lowest input price at $30 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer GPT-4?

7 providers list GPT-4 on Sovyron; 7 of them sell it at a metered per-token price.

### Is GPT-4 free?

No provider in the Sovyron catalog lists a free tier for GPT-4.

### What is the context window of GPT-4?

GPT-4 supports a 8k-token context window and up to 8k output tokens.

HTML page: https://sovyron.com/models/gpt-4/
Full dataset: https://sovyron.com/data/catalog.json