# Mercury 3 API prices

Mercury 3 (mercury) — 1.0M context, 131k max output.
4 metered per-token offers from 4 providers, in USD per 1M tokens.
Prices as of 2026-11-22.

| Provider | API model ID | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- | --- |
| Inception | `mercury-3` | $0.1 | $0.35 | $0.01 | 1.0M |
| Kilo Gateway | `inception/mercury-3` | $0.1 | $0.35 | $0.01 | 1.0M |
| NanoGPT | `inception/mercury-3` | $0.1 | $0.35 | $0.01 | 1.0M |
| Vercel AI Gateway | `inception/mercury-3` | $0.1 | $0.35 | $0.01 | 1.0M |

## Summary

- Cheapest input: $0.1 per 1M tokens (Inception)
- Cheapest output: $0.35 per 1M tokens (Inception)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-10-16
- Inputs: text

## FAQ

### What is the cheapest Mercury 3 API?

As of Nov 22, 2026, Inception has the lowest Mercury 3 output price at $0.35 per 1M tokens, and Inception has the lowest input price at $0.1 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Mercury 3?

4 providers list Mercury 3 on Sovyron; 4 of them sell it at a metered per-token price.

### Is Mercury 3 free?

No provider in the Sovyron catalog lists a free tier for Mercury 3.

### What is the context window of Mercury 3?

Mercury 3 supports a 1.0M-token context window and up to 131k output tokens.

## Recent price changes

| Date | Provider | Input $/1M | Output $/1M | Change |
| --- | --- | --- | --- | --- |
| 2026-11-13 | Kilo Gateway | $0.2 → $0.1 | $0.7 → $0.35 | −50% |

HTML page: https://sovyron.com/models/mercury-3/
Full dataset: https://sovyron.com/data/catalog.json
