Llama 3.3 70B Instruct
eachlabs/llama-3.3-70b-instruct
- Tools
- JSON mode
- Vision
- Streaming
Released Dec 7, 2024
- Context
- 128K
- Max out
- 128K
- From / 1M
- $0.135
Providers
- EachLabseachlabs/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- Novita AIeachlabs/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- Novita AInovita-ai/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- EachLabsnovita-ai/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- Novita AInovita/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- EachLabsnovita/llama-3.3-70b-instructInput / 1M$0.135Output / 1M$0.40Cache read / 1MN/ASpeed100.0 t/sFirst token549 ms
- AkashMLakash/Llama-3.3-70B-InstructInput / 1M$0.20Output / 1M$0.52Cache read / 1M$0.10Speed142.9 t/sFirst token481 ms
- CoreWeave / W&B Inferenceakash/Llama-3.3-70B-InstructInput / 1M$0.20Output / 1M$0.52Cache read / 1M$0.10Speed142.9 t/sFirst token481 ms
- CoreWeave / W&B Inferencewandb/Llama-3.3-70B-InstructInput / 1M$0.20Output / 1M$0.52Cache read / 1M$0.10Speed142.9 t/sFirst token481 ms
- AkashMLwandb/Llama-3.3-70B-InstructInput / 1M$0.20Output / 1M$0.52Cache read / 1M$0.10Speed142.9 t/sFirst token481 ms