GeniusRelay
Sign upConsole

NVIDIA: Nvidia Nemotron 70b

llama-3.1-nemotron-70b-instruct-hf

CompareAPIGet an API keyGet an API key

Nvidia Nemotron 70b costs $0.464 per million input tokens and $0.530 per million output tokens, supports 16K context, and is available through the OpenAI-compatible API.

Nvidia's latest Llama fine-tune optimized for instruction following. Early results hints that it might outperform models such as GPT-4o and Claude 3.5 Sonnet.

Modalities

Text → Text

Input / output price

$0.464 / $0.530 per 1M

Context

16K · max output 8K

Capabilities

RoleplayOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.464
Output$0.530
Cached input$0.232

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00182
Per day
$0.9083
Per month (30 days)
$27.25

Nvidia Nemotron 70b: input $0.4641/M · output $0.5304/M · cached input $0.2321/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llama-3.1-nemotron-70b-instruct-hf", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to llama-3.1-nemotron-70b-instruct-hf.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.1-nemotron-70b-instruct-hf",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Nvidia Nemotron 70b billed?
Input is $0.464 and output is $0.530 per million tokens; cached input is $0.232. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
16K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Nvidia Nemotron 70b API pricing · GeniusRelay