Llama 3.1 8B Instruct
by Nvidia · family llama · listed Jan 2025TW
Open Llama instruction model for multilingual chat, reasoning, and coding
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
meta/llama-3.1-8b-instruct- Context window
- 16K tokens
- Max output
- 4K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Dec 2023
- Released
- 2025-01-01
- Last updated
- 2025-01-01
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- Helicone$0.02 in · $0.05 out
- NovitaAI$0.02 in · $0.05 out
- Kilo Gateway$0.02 in · $0.04 out
- Inference$0.025 in · $0.025 out
- OpenRouter$0.05 in · $0.08 out
- NanoGPT$0.0544 in · $0.085 out
- Hugging Face$0.06 in · $0.06 out
- Cortecs$0.167 in · $0.167 out
- Pioneer$0.20 in · $0.20 out
- Merge Gateway$0.22 in · $0.22 out
- Weights & Biases$0.22 in · $0.22 out