Mercury 3 is not named in any of the candidate sources, so these products are offered as the closest general options for running and calling LLMs through an API. Inference platforms such as Replicate 1, Hugging Face 4 and SGLang 9 host or serve language models, and LangChain 5 builds agents on top of them. Which platform or model setup you need depends on whether you want a hosted API or self-serving.
A question back: Do you want to call Mercury 3 through a hosted API, or serve it yourself on your own GPUs?
- 1
Replicatereplicate.comverified and signed
Runs open-source machine learning models, including Llama-family language models, through a cloud API. 1
+14 community tools built for it
for agents: stability-ai/stable-diffusion-3 · meta/meta-llama-3-70b · meta/meta-llama-3-8b
- 2
Hugging Facehuggingface.coverified and signed
Hosts and serves models through its Inference Providers API with access to a large catalogue of models, plus a Hub for models and datasets. 4
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: huggingface-inference-api · huggingface-inference-api-typescript · huggingface-tool-builder
- 3
SGLangsglang.iowebsite read, tools not yet checked
Open-source serving framework for large language and multimodal models, for running your own inference deployments. 9
+2 community tools built for it
- 4
LangChainlangchain.comverified and signed
Open agent engineering platform for building agents that call language models, with a Python library and LangGraph docs. 5
+163 community tools built for it
for agents: langchain · get_docs · langgraph
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 4Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 5LangChain: the open agent platform to own your intelligencelangchain.com · read 2026-10-29
- 9SGLang – Fast, Open-Source LLM & Multimodal Serving Frameworksglang.io · read 2026-10-29
For agents: the 10 actions behind this answer
stability-ai/stable-diffusion-3 · stability-ai/stable-diffusion-3 verified and signed
A text-to-image model with greatly improved performance in image quality, typography, complex prompt understanding, and resource-efficiency
custom_api_call · OpenAI (Activepieces) verified and signed
Custom API Call — Make a custom API call to a specific endpoint
language-modeling · Llama-3.3-nemotron-super-49b-v1.5 verified and signed
Task: Language Modeling
huggingface-inference-api · @huggingface/inference verified and signed
langchain · Docs by LangChain verified and signed
Use when building AI agents, integrating language models with
api · ghapi verified and signed
typespec-create-api-plugin · typespec-create-api-plugin verified and signed
Generate a TypeSpec API plugin with REST operations, authentication, and Adaptive Cards for Microsoft 365 Copilot
get_mermaid_config_str · Neo4j MCP Clients & Servers found in code, not yet checked
Get the Mermaid configuration string for the data model. This may be visualized in Claude Desktop and other applications with Mermaid support. Accepts either a DataModel object or a JSON string of the DataModel object.
· SGLang website read, tools not yet checked
SGLang powers fast, scalable inference for large language and multimodal models. Open-source serving framework with state-of-the-art performance.
add-new-jit-ee-api · add-new-jit-ee-api verified and signed
Add a new API to the JIT-VM (aka JIT-EE) interface in the codebase.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.