Nemotron 3 Ultra 550B A55B API pricing & setup
As of 2026-10-17, the cheapest Nemotron 3 Ultra 550B A55B channel is OpenRouter: $0.625 input / $3.125 output per 1M tokens (blended $1.25). Context 262K.
Context: 262K · Max output: 183K · Modalities: text · Listed: 2026-06-04
Channel comparison (per 1M tokens)
| Channel | Blended | Input | Output | Cached | Access & payment (this channel) | Notes | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterThird-party host $0.625 / $3.125 | $1.25 | $0.625 | $3.13 | $0.188 | ✓CN direct✓Alipay✗ID✗Intl card conditions source2026-10-17 | Third-party host: Venice (fp8) Quantized min $0.5 / $2.2 (fp4, DeepInfra) | openrouter.ai 2026-10-17 |
Access & payment conditions are verified per channel (see the column above); unverified never counts as met.
Free & deals
- Free on OpenRouter: NVIDIA Nemotron 3 Ultra (free) (context 1,000,000), rate-limited; #7 on OpenRouter weekly ranking · official
How to use Nemotron 3 Ultra 550B A55B in Claude Code / Codex / OpenCode
Provider-specific setup not yet verified. Generic setup: guides
Cheaper alternatives
ERNIE 5.1 ($1.12) · Mistral Large 4 ($1.03) · Qwen3.8 27B ($0.956) ·
Related comparisons
ERNIE 5.1 vs Qwen3.8 Max (0902) · Gemini 3.8 Flash vs GPT-6 Luna · MiniMax-M3 vs Kimi K2.6 · Compare any two →
Rankings: Cheapest LLM APIs · LLM APIs usable from mainland China · All NVIDIA models
Price history
- 2026-10-17 · OpenRouter · Nemotron 3 Ultra 550B A55B cached: $0.12 → $0.1875 (OpenRouter basis change: model list price → Venice (third-party host); not a provider price change)
- 2026-10-17 · OpenRouter · Nemotron 3 Ultra 550B A55B output: $2.4 → $3.125 (OpenRouter basis change: model list price → Venice (third-party host); not a provider price change)
- 2026-10-17 · OpenRouter · Nemotron 3 Ultra 550B A55B input: $0.6 → $0.625 (OpenRouter basis change: model list price → Venice (third-party host); not a provider price change)
- 2026-10-17 · OpenRouter · Nemotron 3 Ultra 550B A55B listed · $0.6 / $2.4 (Hand-added at 2026-10-17 01:59 UTC; added to the catalog for automatic fetching at 03:47 UTC)
FAQ
How much does the Nemotron 3 Ultra 550B A55B API cost?
Cheapest channel (OpenRouter): $0.625 input / $3.125 output per 1M tokens, verified 2026-10-17.
Can I use Nemotron 3 Ultra 550B A55B from China?
OpenRouter: direct yes, Alipay yes, ID required no, overseas card no
Is Nemotron 3 Ultra 550B A55B free?
Free on OpenRouter: NVIDIA Nemotron 3 Ultra (free) (context 1,000,000), rate-limited; #7 on OpenRouter weekly ranking
What is Nemotron 3 Ultra 550B A55B's context window?
262K tokens