sao10k Open weights

Llama 3.1 Euryale 70B v2.2 pricing & benchmarks

Released Aug 28, 2024 · served by 2 providers

Input / 1M tokens$0.850
Output / 1M tokens$0.850
Context window131K
Cached input
1M in + 300K out$1.10

What Llama 3.1 Euryale 70B v2.2 is

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).

Providers and prices for Llama 3.1 Euryale 70B v2.2

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.850 $0.850 131K fp8 99.8%
Novita $1.45 $1.45 8K fp8 99.7%

FAQ

How much does the Llama 3.1 Euryale 70B v2.2 API cost?

$0.850 per 1M input tokens and $0.850 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.10.

Is Llama 3.1 Euryale 70B v2.2 free?

No. It is a paid model starting at $0.850 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Llama 3.1 Euryale 70B v2.2?

DeepInfra at $0.850 input / $0.850 output per 1M tokens (fp8 quantization).

Can I self-host Llama 3.1 Euryale 70B v2.2?

Yes — weights are published as Sao10K/L3.1-70B-Euryale-v2.2 on Hugging Face, so you can run it on your own hardware.