NVIDIA
Llama 3.1 Nemotron Instruct 70b
Llama 3.1 Nemotron Instruct 70b is a NVIDIA model with function calling capabilities. It is priced at $1.2 per million input tokens and $1.2 per million output tokens, and has a 131K token context window. Access the Llama 3.1 Nemotron Instruct 70b API through Inworld Router or Realtime API.
→Function Calling
curl --location 'https://api.inworld.ai/router/v1/routers' \
--header 'Content-Type: application/json' \
--header 'Authorization: Basic <your-api-key>' \
--data '{
"name": "compare-frontier-models",
"default_route": {
"route_id": "default",
"variants": [
{
"variant": { "variant_id": "deepinfra",
"model_id": "deepinfra/llama-3-1-nemotron-instruct-70b" },
"weight": 33
},
{
"variant": {
"variant_id": "deepinfra",
"model_id": "deepinfra/nvidia-nemotron-3-nano-30b-a3b"
},
"weight": 33
},
{
"variant": {
"variant_id": "deepinfra",
"model_id": "deepinfra/nvidia-nemotron-nano-12b-v2-vl"
},
"weight": 34
}
]
}
}'Inference providers
Access Llama 3.1 Nemotron Instruct 70b through DeepInfra via Inworld Router or Realtime API.
| Capabilities | Input modalities | Output modalities | |||||
|---|---|---|---|---|---|---|---|
 DeepInfra | 131.1K | 131.1K | $1.20 | $1.20 |
More models by NVIDIA
Other NVIDIA models available through Inworld Router or Realtime API.
| Capabilities | Input modalities | Output modalities | Inference provider | |||||
|---|---|---|---|---|---|---|---|---|
| Nvidia Nemotron 3 Nano 30b A3b | — | — | $0.05 | $0.20 | — | |||
| Nvidia Nemotron Nano 12b V2 Vl | — | — | $0.20 | $0.60 | — | |||
| Nvidia Nemotron Nano 9b V2 | 131.1K | 131.1K | $0.04 | $0.16 | ||||
| Nvidia/Llama 3.3 Nemotron Super 49B V1.5 | 131.1K | 131.1K | $0.10 | $0.40 |
Start building with Llama 3.1 Nemotron Instruct 70b
Access Llama 3.1 Nemotron Instruct 70b and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.