Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

Llama 3 8B Instruct Lite pricing

Llama 3 8B Instruct Lite from Together AI costs $0.140 per 1M input tokens and $0.140 per 1M output tokens.

API id llama-3-8b-instruct-lite · Together AI · source · updated 2026-09-25 · general-purpose

$0.140
Input / 1M tokens
$0.140
Output / 1M tokens
—
Cached input / 1M
—
Context window

Llama 3 8B Instruct Lite specifications

Provider
Together AI
API id
llama-3-8b-instruct-lite
Model type
general-purpose
Context window
— tokens
Max output
not published
Currency
USD
Price source
First-party
Last checked
2026-09-25

Tags

  • fast

What Llama 3 8B Instruct Lite costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0002
Document summary50,0002,000$0.0073
1M tokens in, 200K out1,000,000200,000$0.17

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does Llama 3 8B Instruct Lite cost per 1M tokens?
Llama 3 8B Instruct Lite costs $0.140 per 1M input tokens and $0.140 per 1M output tokens on the standard tier.
What is Llama 3 8B Instruct Lite's context window?
Together AI does not publish a context window for Llama 3 8B Instruct Lite on its pricing page.
Is there a cheaper Together AI model than Llama 3 8B Instruct Lite?
Yes. Qwen3.8 Flash is $0.090 per 1M input tokens versus $0.140 for Llama 3 8B Instruct Lite.
Where does this Llama 3 8B Instruct Lite price come from?
Directly from Together AI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.

Head-to-head comparisons

Other Together AI models

See all Together AI pricing →