Nemotron 3 Nano 30B A3B FP8

infomaniak/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 · family nemotron · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.11Blended $/1M (3:1)

$0.06Input $/1M

$0.25Output $/1M

$0.311M in + 1M out

—Cache read $/1M

#802 of 5,000Cheapest rank

Provider: Infomaniak (infomaniak)
Context: 1,000,000 tokens
Max output: 262,144 tokens
Capabilities: toolsreasoningtext

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","messages":[{"role":"user","content":"hello"}]}'

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