> ## Documentation Index
> Fetch the complete documentation index at: https://www.shipfox.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Model Providers Reference
> The complete Shipfox agent provider catalog: every supported provider, its provider ID, and default model — plus how provider config and model resolution work.
Agent steps run against an **AI provider**. This page is the canonical list of every
supported provider, the `provider` ID you use in workflow YAML, and the default
model Shipfox uses when a step doesn't name one. For a step-by-step setup walkthrough
see the Model Providers guide.
## Supported providers
Each provider is configured per workspace with its credentials. The **default model**
is used when an agent step names the provider but not a `model`.
| Provider | `provider` ID | Default model |
| ----------------------- | ------------------------ | ------------------------------------------- |
| Anthropic | `anthropic` | `claude-opus-4-8` |
| OpenAI | `openai` | `gpt-5.5-pro` |
| Azure OpenAI | `azure-openai-responses` | `gpt-5.5-pro` |
| DeepSeek | `deepseek` | `deepseek-v4-pro` |
| Google AI Studio | `google` | `gemini-3.1-pro-preview` |
| xAI | `xai` | `grok-4.3` |
| Mistral | `mistral` | `mistral-large-latest` |
| Groq | `groq` | `openai/gpt-oss-120b` |
| Cerebras | `cerebras` | `gpt-oss-120b` |
| OpenRouter | `openrouter` | `anthropic/claude-opus-4.8` |
| Vercel AI Gateway | `vercel-ai-gateway` | `anthropic/claude-opus-4.8` |
| Cloudflare AI Gateway | `cloudflare-ai-gateway` | `claude-opus-4-8` |
| Cloudflare Workers AI | `cloudflare-workers-ai` | `@cf/moonshotai/kimi-k2.7-code` |
| Hugging Face | `huggingface` | `deepseek-ai/DeepSeek-V4-Pro` |
| Together AI | `together` | `deepseek-ai/DeepSeek-V4-Pro` |
| Fireworks | `fireworks` | `accounts/fireworks/models/deepseek-v4-pro` |
| NVIDIA | `nvidia` | `nvidia/nemotron-3-ultra-550b-a55b` |
| Ant Ling | `ant-ling` | `Ring-2.6-1T` |
| OpenCode | `opencode` | `claude-opus-4-8` |
| OpenCode Go | `opencode-go` | `kimi-k2.7-code` |
| Z.ai | `zai` | `glm-5.2` |
| Z.ai Coding (CN) | `zai-coding-cn` | `glm-5.2` |
| Kimi Coding | `kimi-coding` | `k2p7` |
| MiniMax | `minimax` | `MiniMax-M3` |
| MiniMax (CN) | `minimax-cn` | `MiniMax-M3` |
| Moonshot AI | `moonshotai` | `kimi-k2.7-code` |
| Moonshot AI (CN) | `moonshotai-cn` | `kimi-k2.7-code` |
| Xiaomi | `xiaomi` | `mimo-v2.5-pro` |
| Xiaomi Token Plan (CN) | `xiaomi-token-plan-cn` | `mimo-v2.5-pro` |
| Xiaomi Token Plan (AMS) | `xiaomi-token-plan-ams` | `mimo-v2.5-pro` |
| Xiaomi Token Plan (SGP) | `xiaomi-token-plan-sgp` | `mimo-v2.5-pro` |
Most providers need only an **API key**. Azure OpenAI also requires an endpoint;
Cloudflare providers require an account ID (and a gateway ID for the AI Gateway).
The configuration form shows the fields each provider needs.
### Selecting a model
The `model` you set on an agent step is passed to the provider and **validated
against that provider's available models** — an unrecognized model ID fails the step
with a clear error. Each provider's full model list comes from the provider's own
catalog; the default model above is what Shipfox picks when you omit `model`.
## How configuration works
Providers are configured **per workspace**. For each provider you configure, you
supply its credentials and can optionally set a **default model** and mark one
provider as the **workspace default**. Credentials are stored securely — Shipfox
keeps only fingerprints, never the raw secret. Configuration takes effect
immediately; no redeploy is needed.
## Resolution and defaults
When an agent step runs, Shipfox resolves the provider, model, and thinking level in
this order:
* **Provider** — the step's `provider`, else the workspace default provider, else
`anthropic`.
* **Model** — the step's `model`, else the configured default model for the resolved
provider, else that provider's catalog default (the table above).
* **Thinking** — the step's `thinking`, else the provider's configured default, else
`high`.
So an agent step with just a `prompt` runs on your workspace default provider and its
default model; naming a `provider` but no `model` uses that provider's default model.
## Unsupported providers
**Amazon Bedrock**, **Google Vertex AI**, **OpenAI Codex**, and **GitHub Copilot**
appear in the catalog but are **not yet supported** — they require cloud IAM
credentials or OAuth flows that API-key configuration can't provide. Support is
planned for a future release.
## Related pages
Configure a provider and use it in a workflow, step by step.
Models, thinking levels, and providers on an agent step.