Llama 3.1 Nemotron Ultra 253B

llmgateway/llama-3.1-nemotron-ultra-253b · family nemotron · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: text.

$0.90Blended $/1M (3:1)

$0.6Input $/1M

$1.8Output $/1M

$2.401M in + 1M out

—Cache read $/1M

#3040 of 5,000Cheapest rank

Provider: LLM Gateway (llmgateway)
Context: 128,000 tokens
Max output: 8,192 tokens
Capabilities: text

Same model, other providers

“Llama 3.1 Nemotron Ultra 253B” is offered by 2 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	128k
LLM Gateway (this)	$0.6	$1.8	$0.90	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at LLM Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"llama-3.1-nemotron-ultra-253b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):