Providers catalog

Nika’s stdlib v0.1 ships canonical providers: local / self-hosted runners, cloud APIs, and deterministic mock. You select one with a single model: <provider>/<name> field. Local first · nothing leaves your machine unless a cloud provider is explicitly selected.

Canonical source: stdlib/providers-v0.1.md in the spec (counts from canon.yaml). The engine additionally carries an extended catalog of TOML records (crates/nika-catalog/data/llm-providers.toml) used for capability metadata. Anything outside the canonical catalog routes through the openai + base_url escape hatch, not its own prefix.

Overview

Providers

canonical: local · cloud · mock

API dialects

3: openai-chat (the 5 local + most cloud) · anthropic · gemini

Capability rules

in model-capabilities.toml

How to pick a provider

Pick your trust model

Local / self-hosted (Ollama / LM Studio / llama.cpp / LocalAI / vLLM): zero key, zero egress, sovereign by default. EU cloud (Mistral). US frontier (Anthropic / OpenAI / Google). Aggregator (OpenRouter). Each has different residency and compliance trade-offs.

Check the `api_dialect`

All 5 local providers + most cloud providers speak openai-chat: same request shape, differing base URL. anthropic and gemini have native dialects.

Verify the backend is reachable

Local providers need their server running (e.g. the Ollama daemon on localhost:11434) and no key. Cloud providers declare an env_var (e.g., MISTRAL_API_KEY). nika doctor checks provider readiness before run.

Pick default vs cheap model

Every provider declares both. default_model is the capable tier; cheap_model is the cost-optimized tier. Capability rules in model-capabilities.toml determine which models support vision / tools / streaming / structured output.

By category

Local/open-weight first (sovereignty default), then cloud starting with Mistral (EU) — anthropic/openai are never presented first, per the catalog’s own presentation-order note in canon.yaml.

Local / self-hosted (5)
Cloud (11)
Test (1)

ID	Name	Dialect	Env var	Example model
`ollama`	Ollama daemon (`localhost:11434`)	`openai-chat`	`(none)`	`llama3.1`
`llamacpp`	llama.cpp `llama-server` (`localhost:8080/v1`)	`openai-chat`	`(none)`	`qwen2.5-7b-instruct`
`vllm`	vLLM OpenAI server (`localhost:8000/v1`)	`openai-chat`	`(none)`	`meta-llama-3.1-70b-instruct`
`lmstudio`	LM Studio (`localhost:1234/v1`)	`openai-chat`	`(none)`	`qwen2.5-14b-instruct`
`localai`	LocalAI (`localhost:8080/v1`)	`openai-chat`	`(none)`	`llama-3.1-8b-instruct`

The sovereign default. No API key, no cloud egress: model: ollama/llama3.2:3b runs offline / air-gapped. Any other OpenAI-compatible local server (Jan · llamafile · KoboldCpp) routes through the openai + base_url escape hatch.

ID	Name	Dialect	Env var	Default model
`mistral`	Mistral AI (EU · sovereign-leaning)	`openai-chat`	`MISTRAL_API_KEY`	`mistral-large-latest`
`huggingface`	Hugging Face Inference Providers (100+ open-weight · 18 backends)	`openai-chat`	`HF_TOKEN`	`Qwen/Qwen3.5-9B:cheapest`
`openai`	OpenAI	`openai-chat`	`OPENAI_API_KEY`	`gpt-4o`
`xai`	xAI Grok	`openai-chat`	`XAI_API_KEY`	`grok-3`
`anthropic`	Anthropic Claude	`anthropic`	`ANTHROPIC_API_KEY`	`claude-sonnet-4-6`
`gemini`	Google Gemini	`gemini`	`GEMINI_API_KEY`	`gemini-2.5-flash`
`deepseek`	DeepSeek	`openai-chat`	`DEEPSEEK_API_KEY`	`deepseek-chat`
`groq`	Groq (fastest open-weight)	`openai-chat`	`GROQ_API_KEY`	`llama-3.3-70b-versatile`
`openrouter`	OpenRouter gateway	`openai-chat`	`OPENROUTER_API_KEY`	`anthropic/claude-sonnet-4-6`
`nvidia`	NVIDIA API (Nemotron 3 · NIM self-hostable)	`openai-chat`	`NVIDIA_API_KEY`	`nvidia/nemotron-3-super-120b-a12b`
`moonshot`	Moonshot AI (Kimi K3 · frontier open-weight)	`openai-chat`	`MOONSHOT_API_KEY`	`kimi-k3`

Keys live in ${{ secrets.* }} / env vars, never inline in the workflow. OpenRouter aggregates ~200 models under one key (openrouter/<vendor>/<model>); Hugging Face routes 100+ open models across 18 backends under one HF_TOKEN. Use either to experiment across vendors without per-vendor keys.

ID	Name	Dialect	Env var	Default model
`mock`	Mock provider	custom	`(none)`	`echo` (deterministic)

Mock ships with every install for deterministic tests: model: mock/echo returns the prompt verbatim, zero network, zero entropy. The canonical examples + CI rely on it.

Full alphabetical list

anthropic · deepseek · gemini · groq · huggingface · llamacpp · lmstudio · localai · mistral · mock · moonshot · nvidia · ollama · openai · openrouter · vllm · xai total: local · cloud · test · matches canon.yaml in the spec repo. The engine’s extended capability catalog ( TOML records) is an implementation detail: extended IDs are reached via the openai + base_url escape hatch, never their own prefix.

Example: invoke a provider

nika: v1
workflow:
  id: multi-provider

tasks:
  primary:
    on_error: { skip: true }   # a dead provider skips (error preserved) · the gate below reads it
    infer:
      model: ollama/llama3.2:3b              # local · zero key
      prompt: "Explain linear algebra in one sentence."

  fallback:
    with:
      problem: ${{ tasks.primary.error }}   # failure-observation edge · a skip carries its preserved error
    when: "${{ with.problem != null }}"     # local read of the binding
    infer:
      model: mistral/mistral-large
      prompt: "Explain linear algebra in one sentence."

ollama pull llama3.2:3b         # local primary · no key
export MISTRAL_API_KEY=...      # cloud fallback only
nika run workflow.nika.yaml

infer: is live in v. Run nika doctor first to see which provider keys or local servers are available without printing secrets.

Capability rules

The rules that govern which models support which features.

Concepts · Providers

How provider routing works at runtime.

Error codes

NIKA-1xx provider errors.

Schema

Workflow envelope, .nika.yaml top-level keys.

YAML

CLI & errors

Data catalogs

Workspace

Providers catalog

Overview

Providers

API dialects

Capability rules

How to pick a provider

By category

Full alphabetical list

Example: invoke a provider

See also

Capability rules

Concepts · Providers

Error codes

Schema

​Overview

Providers

API dialects

Capability rules

​How to pick a provider

​By category

​Full alphabetical list

​Example: invoke a provider

​See also

Capability rules

Concepts · Providers

Error codes

Schema

Overview

How to pick a provider

By category

Full alphabetical list

Example: invoke a provider

See also