Nemotron 3 Super 120B a12b:thinking API
NVIDIA's Nemotron 3 Super 120B a12b:thinking costs $0.05 per million input tokens and $0.25 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send nemotron-3-super-120b-a12b:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About Nemotron 3 Super 120B a12b:thinking
Nemotron 3 Super 120B a12b:thinking is a language model from NVIDIA. Its release date is 11 March 2026. Nemotron middle tier for collaborative agents and high-volume reasoning workloads. Its weights are open. Its training data ends in June 2025. It takes text and gives text. The largest offer takes 262,144 input tokens. It has 1 supplier on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- nemotron-3-super-120b-a12b:thinking
- Maker
- NVIDIA
- Context window
- 262.1K tokens
- Input price
- $0.05 per million tokens
- Output price
- $0.25 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $0.05 input and $0.25 output per million tokens, $0.025 cache read per million tokens, 262.1K tokens of context
Scores
- HLE: 20.8, #161 of 465
- GPQA: 80.0, #165 of 432
- AA-LCR: 65.7, #201 of 409
- SciCode: 36.2, #146 of 178
- Terminal-Bench Hard: 28.8, #110 of 311
- τ²-Bench: 67.8, #135 of 313
- IFBench: 71.5, #54 of 321
Scores: Artificial Analysis (https://artificialanalysis.ai/)
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-super-120b-a12b:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Nemotron 3 Super 120B a12b:thinking?
- Nemotron 3 Super 120B a12b:thinking is a language model from NVIDIA. Its release date is 11 March 2026. Nemotron middle tier for collaborative agents and high-volume reasoning workloads. Its weights are open. Its training data ends in June 2025.
- How much does Nemotron 3 Super 120B a12b:thinking cost?
- Offers now ask $0.05 per million input tokens and $0.25 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Nemotron 3 Super 120B a12b:thinking?
- The largest offer takes 262,144 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Nemotron 3 Super 120B a12b:thinking do?
- Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Nemotron 3 Super 120B a12b:thinking support?
- Text → Text.
- Which providers serve Nemotron 3 Super 120B a12b:thinking?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call Nemotron 3 Super 120B a12b:thinking?
- Send "nemotron-3-super-120b-a12b:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Nemotron 3 Super 120B a12b:thinking released?
- Its creator released it on 11 March 2026.
- When was Nemotron 3 Super 120B a12b:thinking listed?
- The exchange first listed it on 10/10/2026. This is not its release date.
Related pages
- Nemotron 3 Ultra 550B a55b
- Nemotron 3.5 Lightning
- Nemotron 3.5 Content Safety
- Llama 3.3 Nemotron Super 49B V1
- Nemotron: Nano 9B V2
- Nvidia: Nemotron 3.5 Lightning 30B a3b BF16
- Reasoning models
- Set up a client
- All models
- Providers
- Discover the best model for your budget
- Quickstart
- llms.txt: the index of every page, as Markdown
- llms-full.txt: every page in one file
- This page as Markdown