Meta Llama 3.1 8B Instant
Compact Llama instruction model for fast chat and local deployment
Model facts
- Context window
- 131K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.05 per 1M tokens
- Cheapest paid output
- $0.08 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
tool calling, temperature control, text.
Observed price history
- 2026-08-24: $0.05 input / $0.08 output per 1M tokens
API providers
- Helicone — model id llama-3.1-8b-instant; $0.05 input / $0.08 output per 1M tokens; provider documentation