# ERNIE-4.5-21B-A3B-Thinking API prices

ERNIE-4.5-21B-A3B-Thinking (ernie) — 131k context, 66k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Helicone | $0.07 | $0.28 | — | 128k |
| NovitaAI | $0.07 | $0.28 | — | 131k |

## Summary

- Cheapest input: $0.07 per 1M tokens (Helicone)
- Cheapest output: $0.28 per 1M tokens (Helicone)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-03-16
- Inputs: text

## FAQ

### What is the cheapest ERNIE-4.5-21B-A3B-Thinking API?

As of Oct 4, 2026, Helicone has the lowest ERNIE-4.5-21B-A3B-Thinking output price at $0.28 per 1M tokens, and Helicone has the lowest input price at $0.07 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer ERNIE-4.5-21B-A3B-Thinking?

2 providers list ERNIE-4.5-21B-A3B-Thinking on Sovyron; 2 of them sell it at a metered per-token price.

### Is ERNIE-4.5-21B-A3B-Thinking free?

No provider in the Sovyron catalog lists a free tier for ERNIE-4.5-21B-A3B-Thinking.

### What is the context window of ERNIE-4.5-21B-A3B-Thinking?

ERNIE-4.5-21B-A3B-Thinking supports a 131k-token context window and up to 66k output tokens.

HTML page: https://sovyron.com/models/ernie-4-5-21b-a3b-thinking/
Full dataset: https://sovyron.com/data/catalog.json