Models and prices
NVIDIA Nemotron 3 Super
NVIDIA
nvidia/nemotron-3-super-120b-a12b- Type
- Text
- Context window, tokens
- 262,144
- Output length, tokens
- 16,384
- Tool calls
- Supported
- Prompt cache
- Not supported
- Intelligence Index
- Not scored yet
There is no independent score for this model yet: Artificial Analysis does not evaluate it or has not added this version.Full model leaderboard
Hosts and prices
Prices in the host's currency. A call goes to the default host; the next host takes it only when the first one fails.
| Host | Input per 1M | Cache read per 1M | Cache write per 1M | Output per 1M | Checked |
|---|---|---|---|---|---|
| DeepInfradefaultProcesses data outside Russia | $0.09 | $0.09 | $0.09 | $0.48 | November 14, 2026 |
| OpenRouterProcesses data outside Russia | $0.10128 | $0.10128 | $0.10128 | $0.5697 | November 14, 2026 |
How a call is billed
- A call costs what the host that answered it charges, plus our 20%. Prices on this page already include it.
- A dollar price is charged to the balance in rubles at the official Central Bank of Russia rate of the day of the call.
- Before the call, an estimate by the dearest host of the route is reserved on the balance. After the answer, the actual cost is charged and the rest of the reserve is returned.
- There is no top-up fee, and the unspent remainder is refunded in full.
Request example
Pass an organization key with the models:write scope in the Authorization header. The same address works with the OpenAI SDK and OpenRouter clients.
curl https://api.samreshuuu.ru/v1/chat/completions \
-H "Authorization: Bearer $SAMRESHUUU_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"user","content":"Hi! What can you do?"}]}'