CHOOSE YOUR PUMP / nvidia
NVIDIA NIM
Connect NVIDIA NIM models to your coding client or MCP helper. Bring your provider account and key; the provider bills inference.
Preview: $4.99 per month for managed setup and compatibility, with a 7-day trial. The trial needs no card and ends without a charge. A monthly plan starts only after explicit recurring checkout. Provider inference is billed separately.
Your selected provider receives the context you send. RouteMyAgent does not audit whether it is retained, shared or used for training. Review the provider’s terms and account settings. Data boundaries ↗
EXACT IDS / YOUR ACCOUNT CONTROLS ACCESS
Find your model.
Public model inventory refreshed; account access and inference are not verified. Task/API metadata status: fresh. Listed capabilities are metadata, not proof of your account’s quota or model performance. Provider API types describe documented upstream operations; they do not add RouteMyAgent embedding, OCR, speech, image or video routes. All model types and provider prices remain in the full directory.
| Model | Exact ID | Task | Provider API types | Context | Tool calling | Reasoning | Use it |
|---|---|---|---|---|---|---|---|
| 01-ai/yi-large | 01-ai/yi-large | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| adept/fuyu-8b | adept/fuyu-8b | Unknown | /v1/vlm/adept/fuyu-8b | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| ai21labs/jamba-1.5-large-instruct | ai21labs/jamba-1.5-large-instruct | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| aisingapore/sea-lion-7b-instruct | aisingapore/sea-lion-7b-instruct | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| bigcode/starcoder2-15b | bigcode/starcoder2-15b | Unknown | /v1/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| databricks/dbrx-instruct | databricks/dbrx-instruct | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| DeepSeek V4.1 Flash | deepseek-ai/deepseek-v4.1-flash | Chat | /v1/chat/completions | 1048576 tokens | Advertised | Advertised | Connect clientConnect MCP |
| deepseek-ai/deepseek-coder-6.7b-instruct | deepseek-ai/deepseek-coder-6.7b-instruct | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| DiffusionGemma 26B A4B IT | google/diffusiongemma-26b-a4b-it | Chat | /v1/chat/completions | 250000 tokens | Advertised | Advertised | Connect clientConnect MCP |
| Gemma-4-31B-IT | google/gemma-4-31b-it | Chat | /v1/chat/completions | 256000 tokens | Advertised | Advertised | Connect clientConnect MCP |
| GLM-5.3 | z-ai/glm-5.3 | Unknown | Unknown | 1000000 tokens | Advertised | Advertised | Review exact-model setupProvider API docs |
| GLM-5.3-Flash | z-ai/glm-5.3-flash | Unknown | Unknown | 1000000 tokens | Advertised | Advertised | Review exact-model setupProvider API docs |
| google/codegemma-1.1-7b | google/codegemma-1.1-7b | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/codegemma-7b | google/codegemma-7b | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/deplot | google/deplot | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/gemma-2b | google/gemma-2b | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/gemma-3-12b-it | google/gemma-3-12b-it | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/gemma-3-4b-it | google/gemma-3-4b-it | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| google/recurrentgemma-2b | google/recurrentgemma-2b | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| GPT OSS 20B | openai/gpt-oss-20b | Chat | /v1/chat/completions | 131072 tokens | Advertised | Advertised | Connect clientConnect MCP |
| ibm/granite-3.0-3b-a800m-instruct | ibm/granite-3.0-3b-a800m-instruct | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| ibm/granite-3.0-8b-instruct | ibm/granite-3.0-8b-instruct | Unknown | Unknown | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| ibm/granite-34b-code-instruct | ibm/granite-34b-code-instruct | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
| ibm/granite-8b-code-instruct | ibm/granite-8b-code-instruct | Unknown | /v1/chat/completions | Unknown | Unknown | Unknown | Review exact-model setupProvider API docs |
Showing up to 24 model records. Search the full provider catalog ↗
Provider-direct through your local connector.
The preview supplies configuration metadata for native AgentNet. Enter provider credentials only in its native OS-store UI, not a hosted header or setup document. The actual local endpoint comes from the downloaded Windows preview package. Verify its SHA-256; this is an unsigned Windows download, and no fixed localhost port or other-platform installer is promised here.