Nemotron 3 Ultra 550B A55B
kilo/nvidia/nemotron-3-ultra-550b-a55b · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.74
Blended $/1M (3:1)
$0.4
Input $/1M
$1.76
Output $/1M
$2.16
1M in + 1M out
$0.08 −80%
Cache read $/1M
#3863 of 8,511
Cheapest rank
- Provider
- Kilo Gateway (
kilo) - Kind
- text (outputs text)
- Context
- 202,800 tokens
- Max output
- 182,520 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Nemotron 3 Ultra 550B A55B” is offered by 12 providers — cheapest-effective first. Requesty is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Requesty | free | free | $0.00 | 1M |
| UnoRouter | free | free | $0.00 | 1M |
| Nvidia | free | free | $0.00 | 1M |
| routing.run | $0.1 | $0.1 | $0.10 | 131k |
| Kilo Gateway (this) | $0.4 | $1.76 | $0.74 | 203k |
| DevPass (LLM Gateway) | $0.5 | $2.2 | $0.93 | 1M |
| CommandCode | $0.6 | $2.4 | $1.05 | 1M |
| OpenRouter | $0.6 | $2.4 | $1.05 | 262k |
| Together AI | $0.6 | $3.6 | $1.35 | 512k |
| Nebius Token Factory | $1 | $3 | $1.50 | 1M |
| Kenari | $0.6857 | $4.29 | $1.59 | 1M |
| Thinking Machines | $1.8 | $6.23 | $2.91 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Kilo Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):