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

Meta: Llama 3 8B Instruct

Meta

Meta: Llama 3 8B Instruct by Meta costs $0.14 per 1M input tokens and $0.14 per 1M output tokens, with a 8K-token context window.

Pricing

Input (per 1M tokens)
$0.14
Output (per 1M tokens)
$0.14
Cached input (per 1M)
—

Specifications

Provider
Meta
Context window
8K tokens
Parameters
—
Released
—
Open weights
—
Frontier model
No
Hugging Face
meta-llama/Meta-Llama-3-8B-Instruct

Benchmarks

LMArena (Chatbot Arena) Elo
1165.5

Compare Meta: Llama 3 8B Instruct with…

Meta: Llama 3 8B Instruct vs Nova Micro 1.0$0.14/1MMeta: Llama 3 8B Instruct vs Phi 4$0.14/1MMeta: Llama 3 8B Instruct vs gpt-oss-120b (batch)$0.14/1MMeta: Llama 3 8B Instruct vs Gemma 3 12B$0.15/1MMeta: Llama 3 8B Instruct vs Gemma 3 12B IT$0.15/1MMeta: Llama 3 8B Instruct vs Qwen3.5-9B$0.15/1M

FAQ

How much does Meta: Llama 3 8B Instruct cost?

Meta: Llama 3 8B Instruct is priced at $0.14 per 1M input tokens and $0.14 per 1M output tokens. Output tokens cost more than input.

What is Meta: Llama 3 8B Instruct's context window?

Meta: Llama 3 8B Instruct supports a context window of 8K tokens — the maximum prompt plus response length it can handle in a single request.

Is Meta: Llama 3 8B Instruct open weight?

Open-weight status for Meta: Llama 3 8B Instruct is not recorded in our dataset.

Data as of 2026-06-28. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.