nvidia/Nemotron-120B-A12B:
Everything you need to know about the model

nvidia/Nemotron-120B-A12B is a NVIDIA model available through Merge Gateway via Baseten. Use it with Gateway routing policies, spend controls, request logs, and a 203,000 token context window. It supports streaming through at least one Gateway vendor route.

nvidia/Nemotron-120B-A12B pricing

| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention | | --- | ---: | ---: | --- | | Baseten | $0.3000 | $0.7500 | Yes |

Test nvidia/Nemotron-120B-A12B with Merge Gateway’s Simulator

nvidia/Nemotron-120B-A12B
Synced
Synced
Run simulation to see response

Ready to try it out?

Start routing requests to hundreds of large language models in your product within minutes.

Route requests to nvidia/Nemotron-120B-A12B with Merge Gateway

Merge Gateway is a unified LLM API that lets your product route requests to nvidia/Nemotron-120B-A12B and every other major model through a single endpoint. You get built-in fallback routing, per-request cost tracking, zero data retention support, and observability without changing your application architecture.
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Install the Merge Gateway SDK
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Make your first API call
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11
Try a diffrent model
Python
1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Explore other models available in Merge Gateway

model logo
Gemini 3.1 Pro Preview
model logo
Gemini 3.1 Pro Preview Customtools
model logo
Gemini 3.5 Flash
model logo
Gemini 3 Flash Preview
model logo
Gemini 3 Pro Preview
model logo
Gemini Flash Latest
model logo
Gemini Flash Lite Latest
model logo
Gemini Pro Latest
model logo
Gemma 3 12B
model logo
Gemma 3 27B
model logo
Gemma 3 4B
model logo
GLM-4-32B-0414-128K
model logo
GLM-4.5
model logo
GLM-4.5-Air
model logo
GLM-4.5-AirX
model logo
GLM-4.5-X
model logo
GLM-4.6
model logo
Glm47
model logo
GLM 4.7
model logo
GLM 4.7 Flash
model logo
GLM-4.7-FlashX
model logo
Glm 5
model logo
GLM-5
model logo
GLM-5-Turbo

nvidia/Nemotron-120B-A12B FAQ

In case you have any more questions on using nvidia/Nemotron-120B-A12B, we’ve addressed several below.

Heading

What provider owns nvidia/Nemotron-120B-A12B?

nvidia/Nemotron-120B-A12B is a NVIDIA model.

Which vendors can run nvidia/Nemotron-120B-A12B?

Baseten is the default listed vendor, and other active vendors may also be available.

What context window does nvidia/Nemotron-120B-A12B support?

nvidia/Nemotron-120B-A12B supports 203,000 tokens on the primary listed vendor route.

What capabilities does nvidia/Nemotron-120B-A12B support?

Gateway currently lists streaming support for nvidia/Nemotron-120B-A12B across its available vendor routes.

Try nvidia/Nemotron-120B-A12B through Merge Gateway

Route, observe, and control AI requests across providers from one API.