Meta
Llama 3.1 405B
Llama 3.1 405B hosted by IONOS in Berlin, Germany. Zero data retention.
Model facts
- Context window
- 131K tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $1.95 per 1M tokens
- Cheapest paid output
- $1.95 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 7.3 | not measured | 3.0 | not measured |
Observed price history
- 2026-09-11: $1.95 input / $1.95 output per 1M tokens
API providers
- Cortecs — model id llama-3.1-405b-instruct; $1.95 input / $1.95 output per 1M tokens; provider documentation
- NanoGPT — model id meta-llama/llama-3.1-405b-instruct; $2.03 input / $2.03 output per 1M tokens; provider documentation