Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Llama 3.1 8B

GroqOpen weights

Llama 3.1 8B by Groq costs $0.05 per 1M input tokens and $0.08 per 1M output tokens, with a 131K-token context window.

Pricing

Input (per 1M tokens)
$0.05
Output (per 1M tokens)
$0.08
Cached input (per 1M)
—

Specifications

Provider
Groq
Context window
131K tokens
Parameters
—
Released
Jul 2024
Open weights
Yes
Frontier model
No

Benchmarks

Epoch Capabilities Index
116.6

Speed & latency

Time to first token
0.64s
Output speed
198 tok/s

Fastest host: novita (via vercel-ai-gateway).

Compare Llama 3.1 8B with…

Llama 3.1 8B vs GPT OSS 20B$0.30/1MLlama 3.1 8B vs Safety GPT OSS 20B$0.30/1MLlama 3.1 8B vs GPT OSS 120B$0.60/1MLlama 3.1 8B vs Llama 3.3 70B$0.79/1MLlama 3.1 8B vs ALLaM-2-7b$0.00/1MLlama 3.1 8B vs Prompt Guard 2 86M$0.04/1M

FAQ

How much does Llama 3.1 8B cost?

Llama 3.1 8B is priced at $0.05 per 1M input tokens and $0.08 per 1M output tokens. Output tokens cost more than input.

What is Llama 3.1 8B's context window?

Llama 3.1 8B supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.

Is Llama 3.1 8B open weight?

Yes — Llama 3.1 8B has openly available weights.

Data as of 2026-10-14. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.