# Llama 3.1 70B API prices

Llama 3.1 70B (llama) — 131k context, 131k 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 |
| --- | --- | --- | --- | --- |
| CoreWeave | $0.8 | $0.8 | $0.8 | 131k |
| Merge Gateway | $0.99 | $0.99 | — | 128k |

## Summary

- Cheapest input: $0.8 per 1M tokens (CoreWeave)
- Cheapest output: $0.8 per 1M tokens (CoreWeave)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-07-23
- Inputs: text

## FAQ

### What is the cheapest Llama 3.1 70B API?

As of Oct 4, 2026, CoreWeave has the lowest Llama 3.1 70B output price at $0.8 per 1M tokens, and CoreWeave has the lowest input price at $0.8 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Llama 3.1 70B?

2 providers list Llama 3.1 70B on Sovyron; 2 of them sell it at a metered per-token price.

### Is Llama 3.1 70B free?

No provider in the Sovyron catalog lists a free tier for Llama 3.1 70B.

### What is the context window of Llama 3.1 70B?

Llama 3.1 70B supports a 131k-token context window and up to 131k output tokens.

HTML page: https://sovyron.com/models/llama-3-1-70b/
Full dataset: https://sovyron.com/data/catalog.json