jishie

Llama-3.1-Nemotron-Ultra-253B-v1

nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · family nemotron · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.90Blended $/1M (3:1)
$0.6Input $/1M
$1.8Output $/1M
$2.401M in + 1M out
$0.06 −90%Cache read $/1M
#3036 of 5,000Cheapest rank
Provider
Nebius Token Factory (nebius)
Context
128,000 tokens
Max output
4,096 tokens
Capabilities
toolstext

Same model, other providers

“Llama-3.1-Nemotron-Ultra-253B-v1” is offered by 2 providers — cheapest-effective first. Cortecs is the cheapest at $0.90 blended.

ProviderInputOutputBlendedContext
Cortecs$0.598$1.794$0.90128k
Nebius Token Factory (this)$0.6$1.8$0.90128k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","messages":[{"role":"user","content":"hello"}]}'

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