Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 8.7 | — | mirror | openrouter | Jul 23, 2026 |
| AA Coding Index | coding | 37.7 | — | mirror | openrouter | Jul 23, 2026 |
| AA Intelligence Index | intelligence | 25.4 | — | mirror | openrouter | Jul 23, 2026 |
Includes index data from Artificial Analysis.
Providers
Live operational stats per hosting endpoint, via OpenRouter.
| Provider | Quant | Context | $/1M in · out | Uptime 24h | Latency | Throughput |
|---|---|---|---|---|---|---|
| DeepInfra | bf16 | 262K | $0.085 · $0.4 | 94.63% | — | — |
| DekaLLM | fp8 | 262K | $0.08 · $0.45 | 96.58% | — | — |
| DigitalOcean | — | 1M | $0.21 · $0.455 | 98.97% | — | — |
| Nebius | fp4 | 262K | $0.3 · $0.9 | 97.61% | — | — |