Pricingby GlyphNemotron 3 Nano 30B A3B
NVIDIA · Open weights · 262K context · released Dec 14, 2025 · checked 23h ago
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.
Ways to buy 1
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp8 · cached $0.012 | $0.06 | $0.24 | $0.06 / $0.24Cheapest | $0.012 | Cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $10.80 direct.
LiteLLM$10.80+0%
Vercel AI Gateway$10.80+0%
Requesty$11.34+5%
Eden AI$11.39+5.5%
OpenRouter$11.39+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Kong AI GatewayNot offeredNot offered
Neon AI GatewayNot offeredNot offered
PortkeyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
NVIDIA · 1M | $0.06 | $0.35 | $0.06 / $0.35 | $0.133 | 1M | on Darkbloom (nvfp4) | · | NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. |
NVIDIA · 262K | $0.025 | $0.12 | $0.025 / $0.12 | $0.049 | 262K | on Darkbloom (int4) | · | NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. |
NVIDIA · 262K | $0.4 | $1.76 | $0.4 / $1.76 | $0.74 | 262K | on DeepInfra (fp4-flex) | · | NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). |
NVIDIA · 131K | $0.2 | $0.2 | $0.2 / $0.2 | $0.2 | 131K | on DeepInfra (bf16) | · | NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
Meta · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,... |
Cohere · 128K | $0.08 | Free | $0.08 / Free | $0.06 | 128K | Lab list price | · | Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). |
About Nemotron 3 Nano 30B A3B
Takes text in and returns text. First listed Sep 26, 2026. Up to 236K output tokens. Blended price $0.105 per 1M tokens at 3 input to 1 output. Model id nemotron-3-nano-30b-a3b.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Across GlyphCompany profile
Questions
How much does Nemotron 3 Nano 30B A3B cost?
$0.06 per million input tokens and $0.24 per million output tokens, with cached input at $0.012.
What is the context window of Nemotron 3 Nano 30B A3B?
262K tokens, with up to 236K tokens of output.