Nemotron 3.5 Lightning 30B A3B
runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.08
Blended $/1M (3:1)
$0.05
Input $/1M
$0.15
Output $/1M
$0.20
1M in + 1M out
$0.01 −80%
Cache read $/1M
#821 of 9,420
Cheapest rank
- Provider
- RunInfra (
runinfra) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Nemotron 3.5 Lightning 30B A3B” is offered by 10 providers — cheapest-effective first. InferAll is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| InferAll | free | free | $0.00 | 262k |
| Requesty | free | free | $0.00 | 1M |
| Merge Gateway | free | free | $0.00 | 1M |
| Nvidia | free | free | $0.00 | 262k |
| Kilo Gateway | $0.025 | $0.12 | $0.05 | 262k |
| RunInfra (this) | $0.05 | $0.15 | $0.08 | 262k |
| Pioneer | $0.07 | $0.2 | $0.10 | 66k |
| OpenRouter | $0.07 | $0.2 | $0.10 | 262k |
| Nebius Token Factory | $0.06 | $0.24 | $0.10 | 1M |
| Thinking Machines | $0.184 | $0.495 | $0.26 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at RunInfra 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-3.5-Lightning-30B-A3B-BF16","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):