CheapestCoding Long-contextBest value Get an API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › nvidia

nvidia models — pricing & benchmarks

nvidia offers 10 models through the Appmo API, priced from $0.05 per 1M input tokens. All are callable with one OpenAI-compatible key.
ModelProviderIn $/1MOut $/1MContextIntelligenceCoding
NVIDIA: Nemotron 3.5 Lightningnvidia$0.08$0.2262K——
NVIDIA: Nemotron 3.5 Lightning (free)nvidia$0$01M——
NVIDIA: Nemotron 3.5 Content Safety (free)nvidia$0$0128K——
NVIDIA: Nemotron 3 Ultranvidia$0.5$2.2262K——
NVIDIA: Nemotron 3 Ultra (batch)nvidia$0.6$3.6512K——
NVIDIA: Nemotron 3 Ultra (free)nvidia$0$01M——
NVIDIA: Nemotron 3 Nano Omni (free)nvidia$0$0256K——
NVIDIA: Nemotron 3 Supernvidia$0.085$0.41M——
NVIDIA: Nemotron 3 Super (free)nvidia$0$0262K——
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia$0.05$0.2262K——