Nemotron 3 Ultra 550B A55B
by NVIDIAChat
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
- Context
- 1M tokens
- Max output
- 65,536 tokens
- Released
- 2026-06-04
- Weights
- Open
nvidia/nemotron-3-ultra-550b-a55b · also seen as nemotron-3-ultra-550b-a55b-free, nemotron-3-ultra, accounts/fireworks/models/nemotron-3-ultra-nvfp4, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, +10 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-06-04
- Weights
- Open
- Input
- Text
- Output
- Text
- Context window
- 1,000,000 max across endpoints
- Max output
- 65,536
- Providers
- 10 + 14 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.50–$1.00 in · $2.15–$3.13 out per 1M tokens · 8 of 10 providers have a comparable price
More details
- Last updated
- 2026-06-23
- Knowledge cutoff
- 2026-02
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.50 in / $2.15 out per 1M tokens at CoreWeave on every data refresh since then.
Tracked from 19 Oct 2026, the earliest refresh this model's headline price can be rebuilt from. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Nemotron 3 Ultra 550B A55B |
|---|---|---|---|---|---|
| SonarPerplexity | $0.625 | $0.25 | $2.50 | 128K | −0% cheaper |
| llama-3-70bMeta | $0.623 | $0.59 | $0.79 | 8.2K | −1% cheaper |
| Moonshot Kimi K2 InstructMoonshot AI | $0.633 | $0.40 | $1.80 | 131K | +1% |
| Kimi K2 0711Moonshot AI | $0.633 | $0.40 | $1.80 | 128K | +1% |
| Kimi K2 InstructMoonshot AI | $0.633 | $0.40 | $1.80 | 262K | +1% |
| DeepSeek R1DeepSeek | $0.617 | $0.40 | $1.70 | 164K | −2% cheaper |
| Moonshot Kimi K2.5Moonshot AI | $0.646 | $0.375 | $2.00 | 262K | +3% |
| Gemma 2 27BGoogle | $0.65 | $0.65 | $0.65 | 8.2K | +4% |
More from NVIDIA
Newest NVIDIA models in the catalogue. All NVIDIA models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Nemotron 3.5 Super VL 120B A12B | 2026-10-15 | 1.05M | from $0.10 |
| Switchyard | 2026-09-21 | 1M | unpriced |
| Nemotron 3.5 ASR Streaming Multilingual 0.6B | 2026-08-13 | — | unpriced |
| Nemotron 3.5 Lightning 30B A3B | 2026-08-11 | 262K | from $0.025 |
| Nemotron 3 Nano Omni 30B TEE | 2026-07-23 | 131K | from $0.0245 |
| Nemotron 3 Embed 1B | 2026-07-16 | 32.8K | unpriced |
| Nemotron 3.5 Content Safety | 2026-06-04 | 128K | from $0.05 |
| Nemotron 3 Ultra | 2026-06-01 | 262K | from $0.90 |