modelgrep
S

Sao10K: Llama 3.3 Euryale 70B

sao10k/l3.3-euryale-70b

JSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
9
288th fastest
Latency
1.1s
first token
Input price
$0.650
179th cheapest
Context
131K
16K max out

How it compares

Faster than2%
of all ranked models
Cheaper than40%
of all ranked models

Overview

Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
NextBitbf16$0.650$0.750100%

Specifications

Context window131K
Max output16K
Knowledge cutoffDec 2023
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Llama 3.3 Euryale 70B FAQ

How much does Llama 3.3 Euryale 70B cost?

Llama 3.3 Euryale 70B costs $0.650 per million input tokens and $0.750 per million output tokens via OpenRouter, making it 179th cheapest of 298 paid models.

How fast is Llama 3.3 Euryale 70B?

Llama 3.3 Euryale 70B generates around 9 tokens per second with 1.1s time-to-first-token (p50), the 288th fastest tracked model.

What is Llama 3.3 Euryale 70B's context window?

Llama 3.3 Euryale 70B supports a 131K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head