Agent Switchboard

Tasks

I need to use LLM inference APIs

Hosted and local inference APIs, most of them OpenAI-compatible, that serve open, proprietary and on-device models.

54 tools · 35 official

Picked from listings that mention llm inference, llm api, inference api, open models or local llm in their name, description, tags or skills; those in Language & Translation or Infrastructure & Ops, or with API access, rank higher.

The short answer

Featured and Sponsored first, then the best fits to use LLM inference APIs on Agent Switchboard, as of 20 Nov 2026: Kong AI Gateway (Featured), Pi (Featured) and NVIDIA NIM API, of 54 tools that do it.

Which official tools use LLM inference APIs?
Kong AI Gateway (Featured), NVIDIA NIM API and Crusoe Managed Inference, among 35 that are official.
Which have a hosted MCP server?
None of the 54 tools lists a hosted MCP server address.
Which need no API key or sign-in?
Magnitude, Jan and vLLM, among 13 that need none.

Updated with the weekly drop. Featured and Sponsored listings that do the job come first, labeled; the rest are ranked by how well they fit.

Compared · top 6

As of Nov 20, 2026, the last change to any of these listings. Verified means its URLs load and its access answers; we recheck every month.

ToolAccessSign-inMakerCheckedUpdated
Kong AI GatewayFeaturedapi-gateway. Pick it if you want the vendor's own tool.API · CLI · MCPAPI keyKongOfficialVerifiedNov 2, 2026
PiFeaturedUnified LLM API. Pick it if you work from a terminal.CLI · API · MCPAPI keyEarendil WorksVerifiedSep 13, 2026
NVIDIA NIM APIOpenAI-Compatible Chat. Pick it if you want the vendor's own tool.APIAPI keyNVIDIAOfficialVerifiedNov 2, 2026
Crusoe Managed Inferencellm-inference. Pick it if you want the vendor's own tool.APIAPI keyCrusoeOfficialVerifiedNov 13, 2026
Prime Inferencellm-inference. Pick it if you work from a terminal.API · CLIAPI keyPrime IntellectVerifiedNov 13, 2026
SambaNova Cloud (SambaCloud)llm-inference. Pick it if you want the vendor's own tool.APIAPI keySambaNovaOfficialVerifiedNov 20, 2026

Best fits · 12

See all 54 on Browse, with filters

Official · 35

The ones published by the company behind the product.

See all 35 official on Browse

In stacks

Missing a tool that does this? Suggest a listing.

/tasks/call-llm-apis
I need to use LLM inference APIs · 54 fit · 35 official · keywords: llm inference, llm api, inference api, open models, local llm · categories: language, infrastructure · access: api
Hosted and local inference APIs, most of them OpenAI-compatible, that serve open, proprietary and on-device models.
Featured and Sponsored first, then the best fits to use LLM inference APIs on Agent Switchboard, as of 20 Nov 2026: Kong AI Gateway (Featured), Pi (Featured) and NVIDIA NIM API, of 54 tools that do it.
Which official tools use LLM inference APIs? Kong AI Gateway (Featured), NVIDIA NIM API and Crusoe Managed Inference, among 35 that are official.
Which have a hosted MCP server? None of the 54 tools lists a hosted MCP server address.
Which need no API key or sign-in? Magnitude, Jan and vLLM, among 13 that need none.
Markdown: /tasks/call-llm-apis.md · updated 2026-11-20
compared · as of 2026-11-20
kongapi+cli+mcp · auth: apiKey · official · verified · featuredupdated 2026-11-02pi-agent-toolkitcli+api+mcp · auth: apiKey · verified · featuredupdated 2026-09-13nvidia-nim-apiapi · auth: apiKey · official · verifiedupdated 2026-11-02crusoe-managed-inferenceapi · auth: apiKey · official · verifiedupdated 2026-11-13prime-inferenceapi+cli · auth: apiKey · verifiedupdated 2026-11-13sambanova-cloudapi · auth: apiKey · official · verifiedupdated 2026-11-20
best fits
kongapi+cli+mcp · featuredGoverns and meters LLM and agent traffic through a high-performance API gateway, with an MCP gateway that turns existing REST APIs into agent-callable tools.pi-agent-toolkitcli+api+mcp · featuredUnified LLM API: Presents one interface across model providers so an agent loop swaps models without changing its calling code.nvidia-nim-apiapiOpenAI-Compatible Chat: Runs chat completions on hosted open models at integrate.api.nvidia.com/v1, with SSE streaming and tool calling.crusoe-managed-inferenceapiRun open-source and fine-tuned models through Crusoe Cloud's OpenAI-compatible inference API, on serverless per-token endpoints or dedicated self-serve deployments.prime-inferenceapi+cliServes hosted open models and gateway access to third-party models through one OpenAI-compatible API, with rerank and classify endpoints and a CLI.sambanova-cloudapiServes open models fast on SambaNova chips through an OpenAI-compatible inference API and Python SDK.cerebras-inferenceapiServes open-weight LLMs such as Qwen and GPT OSS through an OpenAI-compatible API on wafer-scale hardware, for developers who need very fast inference.nebius-token-factoryapiRuns inference and fine-tuning on open models through Nebius's OpenAI-compatible API, with sandboxes for agents.kimi-apiapiServes Moonshot AI's Kimi models through OpenAI-compatible Chat Completions, Responses, and Anthropic-compatible Messages APIs, with tool calling, web search, and a 1M-token context.magnitudecli+apiLocal Inference API: Serves OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages routes on port 10100, as JSON or server-sent event…openai-apiapi+cliText Generation: Generates text, code, and structured JSON from prompts with OpenAI models through the Responses API.groqapiLow-latency inference API running open models on custom LPU hardware, with an OpenAI-compatible interface and tool-calling support.
official
kong, nvidia-nim-api, crusoe-managed-inference, sambanova-cloud, cerebras-inference, nebius-token-factory, kimi-api, openai-api, groq, fireworks-ai, together-ai, amazon-bedrock, cloudflare-workers-ai, xiaomi-mimo-api, baseten, reka-api, oci-generative-ai, ai21-studio, alibaba-model-studio, baidu-qianfan, claude-developer-platform, cloudflare-clef, cohere, deepseek-api, gemini-api, hugging-face-inference-providers, meta-model-api, minimax-api, mistral-ai, openrouter, replicate, tencent-hunyuan, volcengine-ark, xai-api, zai-api
related tasks
/tasks/deploy-an-app62 fitdeploy and host an app/tasks/transcribe-audio15 fittranscribe audio/tasks/translate-text7 fittranslate text/tasks/manage-cloud-infrastructure16 fitmanage AWS, Azure or Google Cloud
in stacks
/stacks/realtime-voice-agentcerebras-inferenceA realtime voice agent
more
/browse?task=call-llm-apisall 54, with filters/tasksevery task/api/tasks/call-llm-apisthis task as JSONGET · no auth