Nemotron 3 Super 120b A12b costs $0.150/1M input tokens and $0.650/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 256K tokens context window. o10 lists Nemotron 3 Super 120b A12b on NVIDIA NIM at routing band C4.
Last updated: 2026-06-27. Full catalog
Nemotron 3 Super 120b A12b is a language model in the o10 fulfillment catalog (slug: nemotron-3-super-120b-a12b). Published input pricing starts at $0.150/1M tokens. Context window: 256K tokens.
Catalog snapshot 2026-06-27.
Nemotron 3 Super 120b A12b costs $0.150/1M input tokens and $0.650/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Nemotron 3 Super 120b A12b is configured on NVIDIA NIM. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
Nemotron 3 Super 120b A12b supports a 256K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
Nemotron 3 Super 120b A12b is classified at o10 routing band C4. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
Nemotron 3 Super 120b A12b is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (NVIDIA NIM) supply API access; list pricing may differ by venue.
Nemotron 3 Super 120b A12b in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `nemotron-3-super-120b-a12b` |
| Type | text |
| Band | C4 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | NVIDIA NIM |
| Gateway ID | `nvidia/nemotron-3-super-120b-a12b` |
| Context window | 256,000 tokens |
| Released | 2026-03-18 |
Gateway snapshot pricing for Nemotron 3 Super 120b A12b.
| Unit | Price |
|---|---|
| Input | $0.15/1M tokens |
| Output | $0.65/1M tokens |
Upstream venues configured for Nemotron 3 Super 120b A12b.
| Host | Upstream model ID |
|---|---|
| nvidia | nvidia_nim/nvidia/nemotron-3-super-120b-a12b |
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| baseten | $0.3 | 224ms | 9728.7% |
| bedrock | $0.15 | 1964ms | 9955.7% |
Eval-gated model selection for this slug.
o10 slug: nemotron-3-super-120b-a12b. Band: C4. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/economy) and [/kyi](/kyi) for governance.
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
Nemotron 3 Super 120b A12b costs $0.150/1M input tokens and $0.650/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
Nemotron 3 Super 120b A12b supports 256K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Nemotron 3 Super 120b A12b (nemotron-3-super-120b-a12b) is configured on: NVIDIA NIM. Upstream model IDs are listed in the fulfillment routes section.
Yes. Nemotron 3 Super 120b A12b is routable at band C4. Send model: "nemotron-3-super-120b-a12b" or use an o10 smart routing alias.
Use o10 slug "nemotron-3-super-120b-a12b" or gateway ID "nvidia/nemotron-3-super-120b-a12b" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
o10 routes Nemotron 3 Super 120b A12b only when per-use-case evals clear at your quality floor. Band C4 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.