Nemotron 3 Ultra API Benchmarks, Pricing & Provider Data
Compare Nemotron 3 Ultra with another model
Choose a model to open its comparison page.
Nemotron 3 Ultra benchmark, API pricing, and provider data cover 28 API providers, with prices starting at $0.0010/request. Nemotron 3 Ultra free API options are available from 1 provider.
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts ar...
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 2 / 8
- Methodology
- V3.0
#1Reasoning56.8Provisional1/4 Measured dimensions
#2Coding52.3Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Total parameters
- 550B
- Active parameters
- 55B
- Released
- Jun 2026
- Tokenizer
- Other
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Rankings
Excels at
Detailed scores
Updated: Aug 22, 2026Speed & latency
undefined metric} other undefined metrics}}
Output speed120.3 tok/s#30 / 74Time to first token1.78 s#51 / 74
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.600/M#93 / 180Output price$2.75/M#95 / 180
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Agents
V3.0undefined metric} other undefined metrics}} · No data
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score52.380% interval36.3–68.31/4 Measured dimensionsSciCode39.9%#85 / 204
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Provisional
Score56.880% interval42.9–70.71/4 Measured dimensionsGPQA86.7%#51 / 211HLE28.4%#56 / 208
Reasoning
V3.0undefined metric} other undefined metrics}} · Provisional
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · No data
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
OpenRouter endpoints
4 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
DeepInfra deepinfra/fp4 | $0.500/M | $2.20/M | 99.9% | — | — | undefined tokens / undefined tokens |
BaseTen baseten/fp4 | $0.600/M | $2.40/M | 99.3% | — | — | undefined tokens / undefined tokens |
Together together | $0.600/M | $3.60/M | 96.8% | — | — | undefined tokens / — |
Venice venice/fp8 | $0.625/M | $3.13/M | 95.9% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Nemotron 3 Ultra API pricing across 27 providers. Prices range from $0.0010/request to $4995.00/M. CM-API 公益站 offers the lowest rate at $0.0010/request. 1 provider offers free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | nvidia/nemotron-3-ultra-550b-a55b:free | free | $0.0010/request | - | — | — | — | |
L1 100% | nvidia/nemotron-3-ultra-550b-a55b | 国产模型 | $0.010/request | - | — | — | — | |
L1 99% L2 88% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — | |
L1 100% | nvidia/nemotron-3-ultra-550b-a55b | default | $375.00/M | $375.00/M | — | — | — | |
L1 100% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — | |
L1 99% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — | |
L1 95% | nvidia/nemotron-3-ultra-550b-a55b | 0倍倍率分组 | -98%$0.014/M | -99%$0.041/M | — | — | — | |
L1 47% | nvidia/nemotron-3-ultra-550b-a55b | default | $4995.00/M Cache read$1498.50/M | $24975.00/M | — | — | — | |
L1 3% | nemotron-3-ultra-550b-a55b | 小叶币 | $0.050/request | - | — | — | — | |
L1 44% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — | |
L1 100% | nvidia/nemotron-3-ultra-550b-a55b:free | default | $0.010/request | - | — | — | — | |
L1 91% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — | |
Dext API Free | L1 11% | nemotron-3-ultra-550b-a55b | 公益 | Free | Free | — | — | — |
L1 0% | nvidia/nemotron-3-ultra-550b-a55b:free | 懒人 | -46%$0.321/M | -88%$0.321/M | — | — | — | |
L1 0% | nvidia/nemotron-3-ultra-550b-a55b | Free | -17%$0.500/M Cache read$0.100/M | -20%$2.20/M | — | — | — | |
L1 0% | nvidia/nemotron-3-ultra-550b-a55b | default | $75.00/M | $75.00/M | — | — | — |
Alternatives & Similar Models
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
Kimi K2.6
kimi-k2-6
Moonshot Kimi K2.6 is an open-source native multimodal agent model with 1 trillion MoE parameters, a 256K context window, and state-of-the-art coding, vision, and long-horizon agent swarm capabilities.
Qwen3.5
qwen3-5
Alibaba Qwen3.5 is a Qwen3 generation model with improved reasoning, multilingual support, and efficient inference for chat, coding, and agent applications.
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
Frequently Asked Questions
- What benchmark data does Nemotron 3 Ultra include?
- LMSpeed shows Nemotron 3 Ultra benchmark context, API price, output speed, first-token latency, and provider data across 28 providers when those signals are available.
- What is the Nemotron 3 Ultra API price?
- Nemotron 3 Ultra has pricing from 28 providers, ranging from $0.0010/request to $4995.00/M. CM-API 公益站 has the lowest listed price.
- What does the Nemotron 3 Ultra API pricing table include?
- The Nemotron 3 Ultra API pricing table compares 28 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Nemotron 3 Ultra API pricing?
- CM-API 公益站 currently has the lowest listed Nemotron 3 Ultra price at $0.0010/request across 28 providers.
- Is Nemotron 3 Ultra API free?
- Yes, Nemotron 3 Ultra free API options are available through 1 providerundefined other undefined} on LMSpeed, including Dext API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Nemotron 3 Ultra free API access?
- LMSpeed currently lists 1 free API providerundefined other undefined} for Nemotron 3 Ultra: Dext API. Check each provider row before using it because free tier limits can change.