Nemotron 3 Nano Omni 30B A3B Reasoning
vultr/nemotron-3-nano-omni-30b-a3b-reasoning · family nemotron · in: text, image, video, audio → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video audio.
$0.14
Blended $/1M (3:1)
$0.1
Input $/1M
$0.25
Output $/1M
$0.35
1M in + 1M out
—
Cache read $/1M
#1225 of 7,872
Cheapest rank
- Provider
- Vultr (
vultr) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image video audio
Same model, other providers
“Nemotron 3 Nano Omni 30B A3B Reasoning” is offered by 4 providers — cheapest-effective first. Requesty is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Requesty | free | free | $0.00 | 131k |
| Vultr (this) | $0.1 | $0.25 | $0.14 | 262k |
| Deep Infra | $0.2 | $0.8 | $0.35 | 262k |
| Crusoe | $0.3 | $1.83 | $0.68 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vultr and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nemotron-3-nano-omni-30b-a3b-reasoning","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):