← All models

Llama 3.1 8B Instant (Groq)

groq/llama-3.1-8b-instant

Ultra-fast open model via Groq. 170ms latency. Free during launch.

Callable nowFree: $0/request

Model facts

Lifecycle
free_beta
Availability
available

Verified 2026-07-25. Fastest available model.

Capabilities
text, json
Provenance
Provider-observed label: llama-3.1-8b-instant. This is not an independently verified upstream provenance claim.
Endpoint
https://api.clervo.dev/v1/chat/completions
Limits
Up to 24000 input characters and 1024 output tokens.

Open the quickstart · Machine-readable detail