modelgrep
S

Sao10K: Llama 3.1 70B Hanami x1

sao10k/l3.1-70b-hanami-x1

Use via OpenRouter ↗
Intelligence
Design Elo
Speed
7
289th fastest
Latency
966ms
first token
Input price
$3.00
269th cheapest
Context
16K

How it compares

Faster than1%
of all ranked models
Cheaper than10%
of all ranked models

Overview

This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Infermaticbf16$3.00$3.00

Specifications

Context window16K
Max output
Knowledge cutoffDec 2023
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Llama 3.1 70B Hanami x1 FAQ

How much does Llama 3.1 70B Hanami x1 cost?

Llama 3.1 70B Hanami x1 costs $3.00 per million input tokens and $3.00 per million output tokens via OpenRouter, making it 269th cheapest of 298 paid models.

How fast is Llama 3.1 70B Hanami x1?

Llama 3.1 70B Hanami x1 generates around 7 tokens per second with 966ms time-to-first-token (p50), the 289th fastest tracked model.

What is Llama 3.1 70B Hanami x1's context window?

Llama 3.1 70B Hanami x1 supports a 16K-token context window. It accepts text input.

Compare head-to-head