Get started

Llama 3.1 8B Instruct Fast

Zerogpu text

zerogpu/llama-3.1-8b-instruct-fast

Input

$0.1500

per 1M input tokens

Output

$0.2800

per 1M output tokens

Cache read

$0.0250

per 1M cached read tokens

Cache write

n/a

per 1M cache write tokens

Context window

131,072

Max output

8,192

Effective date

Oct 29, 2026

Estimate a workload

Enter token counts to see the cost at this model's rates.

Estimated cost: $0.00

Price history

blended $ per 1M tokens (3:1)

One price on record so far (Oct 29, 2026). This chart fills in as the price changes over time. We check daily.

Effective Input Output Blended
Oct 29, 2026 $0.15 $0.28 $0.18

Other Zerogpu models

zerogpu/LFM2.5-1.2B-Instruct · $0.0500/Mtok out zerogpu/LFM2.5-1.2B-Thinking · $0.0500/Mtok out zerogpu/llama-3.2-3b-instruct-fast · $0.3000/Mtok out zerogpu/glm-5.3-flash · $0.3500/Mtok out zerogpu/gpt-6-luna · $0.5000/Mtok out zerogpu/qwen3-30b-a3b-fp8 · $0.4500/Mtok out

Source: litellm. Confirm against the provider's official pricing before relying on these figures.