> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wolffi.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Choosing a Provider

> Configure LLM providers: DeepSeek, Xiaomi MiMo, Kimi, MiniMax, Anthropic, OpenAI, OpenRouter, and Ollama

# Providers

Wolffish communicates with LLMs via nine native cloud providers, an aggregator (OpenRouter), and a local option (Ollama), all using pure `fetch()` — no SDKs. Each provider has its own streaming format and tool-calling convention, which `wernicke.ts` normalizes into a single interface. All cloud providers support tool calling with no hard tool-count limit.

## Choosing a Provider

All supported cloud providers can handle agentic tasks — including complex multi-step tool chains. The difference is cost vs. ceiling.

**Cost-efficient tier — DeepSeek, MiMo, Qwen, Kimi, MiniMax, and Stepfun** handle complex agentic tasks well — including long multi-step tool chains, research workflows, code generation, and autonomous automations. They should be your default. At 5–25× cheaper than the premium tier, the savings compound fast. Start here and only upgrade if you find execution isn't reliable enough for a specific workflow.

**Mid-range tier — xAI** sits between budget and premium, offering Grok models with strong reasoning, vision, and code generation at moderate pricing.

**Premium tier — Anthropic and OpenAI** deliver the strongest raw model capability. Claude Opus 4.8 and GPT-5.5 excel where the cost-efficient tier falls short — particularly **computer-use** (screen interaction), which only Anthropic supports, and edge cases where execution reliability on the cheaper models isn't sufficient.

| Tier           | Provider      | Flagship Model  | Input / Output (per MTok) | Best For                            |
| -------------- | ------------- | --------------- | ------------------------- | ----------------------------------- |
| Cost-efficient | **DeepSeek**  | deepseek-v4-pro | $0.44 / $0.87             | Default for most agentic tasks      |
| Cost-efficient | **MiMo**      | mimo-v2.5-pro   | $0.20 / $2.00             | Cheapest option, multilingual       |
| Cost-efficient | **Qwen**      | qwen3.7-max     | $2.50 / $7.50             | Wide model range, ultra-cheap flash |
| Cost-efficient | **Kimi**      | kimi-k2.6       | $0.95 / $4.00             | Strong reasoning, long context      |
| Cost-efficient | **MiniMax**   | MiniMax-M3      | $0.30 / $1.20             | Reasoning and code                  |
| Cost-efficient | **Stepfun**   | step-3.7-flash  | $0.83 / $6.94             | Always-on reasoning                 |
| Cost-efficient | **Z.ai**      | glm-4.6         | $0.60 / $2.20             | GLM models, 1M-context flagship     |
| Mid-range      | **xAI**       | grok-4.3        | $1.25 / $2.50             | Reasoning, vision, code             |
| Premium        | **Anthropic** | claude-opus-4-8 | $5.00 / $25.00            | Hardest tasks, computer-use         |
| Premium        | **OpenAI**    | gpt-5.5         | $5.00 / $30.00            | Hardest tasks, broad knowledge      |
| Local          | **Ollama**    | varies          | Free                      | Privacy, offline fallback           |

### When to reach for the premium tier

* **Computer-use / screen interaction** — only Anthropic supports this; no alternative
* **Execution not reliable enough** — if you've tried a task on DeepSeek or MiMo and the agent keeps failing or producing poor results, upgrade to Anthropic or OpenAI for that specific workflow

### Our recommendation

Start with DeepSeek or MiMo. They handle complex agentic tasks — long tool chains, research pipelines, code generation, autonomous automations — at a fraction of the cost. Experiment with your actual workflows. If a specific task isn't executing reliably, switch to Anthropic or OpenAI for that task. Most users find they rarely need to.

<Tip>
  Select DeepSeek or MiMo as your Brain model in Settings → Modes. If a task isn't executing reliably on the cost-efficient tier, switch your Brain to Anthropic or OpenAI for that work. There's no automatic fallback — you control which model runs by your explicit choice.
</Tip>

## DeepSeek (Recommended)

```
POST https://api.deepseek.com/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format.

**DeepSeek V4 Pro is Wolffish's recommended default for agentic tasks.** Following the [permanent 75% price cut](https://deepseek.ai/blog/deepseek-v4-pro-api-price-cut-permanent) (May 2026), it delivers frontier-class reasoning and tool-use reliability at 29–34× less than competing frontier models on output-heavy workloads — while matching or exceeding their agentic performance on multi-step tool chains. It's also MIT-licensed, so you can self-host for \$0 in API fees if you have the infra.

Best for: Agentic multi-step workflows, tool calling, research chains, cost-efficient daily automations.

<Tip>
  If you're setting up Wolffish for the first time and want one provider that does it all — reliable tool use, strong reasoning, fast responses, minimal cost — start with DeepSeek V4 Pro. You can always add Anthropic or OpenAI later for specific use cases.
</Tip>

### Getting an API Key

1. Go to [platform.deepseek.com](https://platform.deepseek.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → DeepSeek

### Models

| Model               | Context | Max Output | Input / Output (per MTok) | Notes                                                                       |
| ------------------- | ------- | ---------- | ------------------------- | --------------------------------------------------------------------------- |
| **deepseek-v4-pro** | 1M      | 32K        | $0.435 / $0.87            | Recommended default. Frontier agentic performance. Cached: \$0.003625/MTok. |
| deepseek-v4-flash   | 1M      | 32K        | $0.14 / $0.28             | Fast and cheap. Cached: \$0.0028/MTok.                                      |

***

## Xiaomi MiMo

```
POST https://api.xiaomimimo.com/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and PDF document input.

Following [Xiaomi's permanent price cut of up to 99%](https://www.studioglobal.ai/ms/discover/answers/what-prompted-xiaomi-to-cut-its-mimo-v2-5-6a179fe3f9dbfce068be8b7e) — matching DeepSeek V4 Pro rates — MiMo V2.5 is one of the cheapest cloud providers available.

Best for: Cost-efficient agentic workflows, multilingual tasks, multi-step tool chains, high-volume automations.

### Getting an API Key

1. Go to [platform.xiaomimimo.com](https://platform.xiaomimimo.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Xiaomi Mimo

### Models

| Model             | Context | Max Output | Input / Output (per MTok) | Notes                                               |
| ----------------- | ------- | ---------- | ------------------------- | --------------------------------------------------- |
| **mimo-v2.5-pro** | 1M      | 64K        | $0.20 / $2.00             | Best MiMo model. Strong reasoning and multilingual. |
| mimo-v2.5         | 1M      | 32K        | $0.08 / $0.80             | Good balance of quality and cost.                   |
| mimo-v2-flash     | 256K    | 16K        | $0.01 / $0.30             | Ultra-cheap for high-volume tasks.                  |

***

## Kimi (Moonshot AI)

```
POST https://api.moonshot.ai/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision and reasoning content.

Best for: Agentic workflows, long-context tasks, reasoning-heavy workloads.

### Getting an API Key

1. Go to [platform.moonshot.ai](https://platform.moonshot.ai)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Kimi

### Models

| Model            | Context | Max Output | Input / Output (per MTok) | Notes                              |
| ---------------- | ------- | ---------- | ------------------------- | ---------------------------------- |
| **kimi-k2.6**    | 256K    | 64K        | $0.95 / $4.00             | Latest flagship. Strong reasoning. |
| kimi-k2.5        | 256K    | 64K        | $0.60 / $3.00             | Good balance of cost and quality.  |
| moonshot-v1-128k | 128K    | 16K        | $2.00 / $5.00             | Long-context.                      |
| moonshot-v1-32k  | 32K     | 8K         | $1.00 / $3.00             | Mid-context.                       |

***

## MiniMax

```
POST https://api.minimaxi.chat/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports reasoning content.

Best for: Reasoning-heavy workloads, code generation, agentic workflows. DeepSeek and MiMo remain cheaper and more capable for most workloads.

### Getting an API Key

1. Go to [platform.minimaxi.chat](https://platform.minimaxi.chat)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → MiniMax

### Models

| Model          | Context | Max Output | Input / Output (per MTok) | Notes                              |
| -------------- | ------- | ---------- | ------------------------- | ---------------------------------- |
| **MiniMax-M3** | 1M      | 64K        | $0.30 / $1.20             | Latest flagship. Strong reasoning. |
| MiniMax-M2.7   | 200K    | 32K        | $0.30 / $1.20             | Previous gen.                      |
| MiniMax-M2.5   | 200K    | 32K        | $0.30 / $1.20             | Balanced quality and cost.         |

***

## Qwen (Alibaba Cloud)

```
POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision and reasoning content.

Best for: Cost-efficient agentic workflows, code generation, multilingual tasks.

### Getting an API Key

1. Go to [qwencloud.com](https://www.qwencloud.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Qwen

### Models

| Model            | Context | Max Output | Modes           | Input / Output (per MTok) | Notes                              |
| ---------------- | ------- | ---------- | --------------- | ------------------------- | ---------------------------------- |
| **qwen3.7-max**  | 1M      | 64K        | None, High, Max | $2.50 / $7.50             | Flagship. Frontier reasoning.      |
| qwen3.7-plus     | 1M      | 64K        | None, High, Max | $0.40 / $1.60             | Strong reasoning, mid-range price. |
| qwen3.5-flash    | 1M      | 64K        | None, High, Max | $0.06 / $0.24             | Ultra-cheap reasoning.             |
| qwen3-coder-plus | 131K    | 32K        | None, High, Max | $0.40 / $1.60             | Code-optimized.                    |

***

## Stepfun

```
POST https://api.stepfun.ai/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision and reasoning content.

Best for: Reasoning-heavy tasks where you always want the model to think.

### Getting an API Key

1. Go to [platform.stepfun.ai](https://platform.stepfun.ai)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Stepfun

### Models

| Model              | Context | Max Output | Modes     | Input / Output (per MTok) | Notes                       |
| ------------------ | ------- | ---------- | --------- | ------------------------- | --------------------------- |
| **step-3.7-flash** | 128K    | 32K        | Always-on | $0.83 / $6.94             | Latest. Frontier reasoning. |
| step-3.5-flash     | 128K    | 32K        | Always-on | $0.83 / $6.94             | Fast reasoning.             |

***

## Z.ai (Zhipu GLM)

```
POST https://api.z.ai/api/paas/v4/chat/completions
```

OpenAI-compatible SSE streaming with tool-calling — the same wire format as Kimi. GLM thinking is binary (on/off, no effort levels), and GLM-5.2 offers a 1M-token context window.

Best for: Cost-efficient agentic work and long-context workflows.

### Getting an API Key

1. Go to [z.ai](https://z.ai)
2. Sign up or log in
3. Open **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Z.ai

### Models

| Model       | Context | Max Output | Modes           | Input / Output (per MTok) | Notes                                  |
| ----------- | ------- | ---------- | --------------- | ------------------------- | -------------------------------------- |
| **glm-4.6** | 200K    | 64K        | Thinking on/off | $0.60 / $2.20             | Recommended. Cost-efficient workhorse. |
| glm-4.5-air | 128K    | 64K        | Thinking on/off | $0.20 / $1.10             | Cheapest.                              |
| glm-5.2     | 1M      | 64K        | Thinking on/off | $1.40 / $4.40             | Flagship. Largest context.             |

For the full GLM lineup and per-model details, see the [Z.ai page](/configuration/zai).

***

## Anthropic (Claude)

```
POST https://api.anthropic.com/v1/messages
```

Uses SSE streaming. Tool calls arrive as `tool_use` content blocks.

Best for: Complex reasoning, detailed instruction following, nuanced tool use, computer-use (screen interaction).

### Getting an API Key

1. Go to [console.anthropic.com](https://console.anthropic.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → Anthropic

### Models

| Model                 | Context | Max Output | Modes           | Input / Output (per MTok) | Notes                                              |
| --------------------- | ------- | ---------- | --------------- | ------------------------- | -------------------------------------------------- |
| claude-opus-4-8       | 1M      | 32K        | None, High, Max | $5.00 / $25.00            | Latest. Frontier reasoning.                        |
| **claude-sonnet-4-6** | 1M      | 64K        | None, High, Max | $3.00 / $15.00            | Best balance of quality and cost.                  |
| claude-haiku-4-5      | 200K    | 8K         | None, High      | $1.00 / $5.00             | Fast and cheap. Not recommended for agentic tasks. |

<Note>
  Anthropic is the only provider that supports **computer-use** (screen interaction). If you need Wolffish to drive a browser or desktop UI, you need an Anthropic key.
</Note>

***

## xAI (Grok)

```
POST https://api.x.ai/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision and reasoning content.

Best for: Reasoning-heavy workflows, code generation, vision tasks.

### Getting an API Key

1. Go to [console.x.ai](https://console.x.ai)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → xAI

### Models

| Model          | Context | Max Output | Modes           | Input / Output (per MTok) | Notes                         |
| -------------- | ------- | ---------- | --------------- | ------------------------- | ----------------------------- |
| **grok-4.3**   | 1M      | 64K        | None, High, Max | $1.25 / $2.50             | Flagship. Vision + reasoning. |
| grok-build-0.1 | 256K    | 32K        | None, High, Max | $1.00 / $2.00             | Code-optimized.               |
| grok-3-mini    | 131K    | 32K        | None, High      | $0.30 / $0.50             | Fast and cheap.               |

***

## OpenAI (GPT)

```
POST https://api.openai.com/v1/chat/completions
```

Uses SSE streaming. Tool calls arrive as `function_call` objects.

Best for: General-purpose tasks, broad knowledge, fast responses.

### Getting an API Key

1. Go to [platform.openai.com](https://platform.openai.com)
2. Sign up or log in
3. Navigate to **API Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → OpenAI

### Models

| Model        | Context | Max Output | Modes           | Input / Output (per MTok) | Notes                       |
| ------------ | ------- | ---------- | --------------- | ------------------------- | --------------------------- |
| **gpt-5.5**  | 1M      | 64K        | None, High, Max | $5.00 / $30.00            | Flagship. Strong reasoning. |
| gpt-5.4-mini | 1M      | 64K        | None, High, Max | $0.75 / $4.50             | Fast reasoning.             |
| gpt-5.4-nano | 1M      | 64K        | None, High, Max | $0.20 / $1.25             | Ultra-cheap reasoning.      |

***

## OpenRouter (Aggregator)

```
POST https://openrouter.ai/api/v1/chat/completions
```

Uses SSE streaming with OpenAI-compatible tool-calling format. Routes requests to any model from any provider through a single API key.

**OpenRouter is a model aggregator** — a single API endpoint that proxies requests to Anthropic, OpenAI, DeepSeek, Qwen, xAI, Meta, Mistral, Google, and dozens more. One key, one billing account, access to everything.

<Warning>
  **We recommend configuring providers directly whenever possible.** Direct integration gives you lower latency (no proxy hop), accurate cost tracking, provider-specific features (Anthropic's ephemeral caching, DeepSeek's FIM), and no middleman markup. OpenRouter adds a routing layer that can introduce latency and occasionally inconsistent behavior across providers.

  Use OpenRouter when you want to experiment with models you haven't set up directly, or as a convenient fallback for providers where you don't want to manage a separate API key.
</Warning>

### Getting an API Key

1. Go to [openrouter.ai](https://openrouter.ai)
2. Sign up or log in
3. Navigate to **Keys** and create a new key
4. Paste it into Wolffish → Settings → Models → OpenRouter

### Supported Models

OpenRouter supports hundreds of models. Wolffish normalizes output caps to match each provider's native limits:

| Model (via OpenRouter) | Max Output | Notes                          |
| ---------------------- | ---------- | ------------------------------ |
| anthropic/claude-\*    | 32K        | Matches native Anthropic caps. |
| openai/gpt-5\*         | 64K        | Matches native OpenAI caps.    |
| openai/o3, openai/o4   | 64K        | Reasoning models.              |
| deepseek/\*            | 32K        | Matches native DeepSeek caps.  |
| x-ai/grok-\*           | 32K        | Matches native xAI caps.       |
| google/gemini-\*       | 64K        | Google Gemini models.          |
| meta-llama/\*          | 16K        | Meta Llama models.             |
| qwen/\*                | 32K        | Matches native Qwen caps.      |
| mistralai/\*           | 32K        | Mistral models.                |

### When to Use OpenRouter

**Good fit:**

* Trying models from providers you haven't configured yet
* Quick A/B testing across different model families
* Unified billing when you only want one API bill
* Accessing niche or newer models not yet natively supported

**Use direct integration instead when:**

* The provider is already natively supported (DeepSeek, Anthropic, OpenAI, etc.)
* You need the lowest possible latency
* You want provider-specific features (caching, prompt prefixes, etc.)
* You're running high-volume production workloads where the proxy hop adds up

<Tip>
  If you're already using DeepSeek, Anthropic, or any other natively supported provider, keep that direct connection. Add OpenRouter only for models you can't access directly — then pick an OpenRouter model as your Brain (or Worker) when you want it. There's no cascade; the model you select is the one that runs.
</Tip>

***

## Ollama (Local)

```
POST http://localhost:11434/api/chat
```

Uses NDJSON streaming. Tool calls arrive as structured JSON in the response. No API key needed — runs entirely on your machine. See the [Ollama integration guide](/configuration/ollama) for model requirements and hardware recommendations.

Best for: Privacy, offline use, zero-cost experimentation, always-available fallback.

## Retries & Health

The selected Brain model runs every turn — there's no fallback to other providers. When a cloud Brain hits a transient error, `thalamus` retries the **same** model on a backoff schedule (it also checks `net.isOnline()` for instant offline detection). Workers in orchestrator mode are single-shot and don't retry on their own; any failure surfaces to the orchestrator, which owns the retry decision. Health tracking informs this retry logic and diagnostics — it does not route you to a different provider.

## Choosing Your Brain Model

Select your Brain model explicitly in **Settings → Modes** — one provider, one model. The model you choose is the one that runs; there's no fallback order and no "primary" with a chain behind it. Connect API keys in **Settings → Models**, then pick the model that powers Wolffish.

Want a second model for parallel work? Turn on [orchestrator mode](/configuration/orchestrator-mode) and assign a Worker model alongside your Brain. There's still no automatic cascade — both are explicit choices.

All providers are optional — you only need the one (or two) you select. To run on Ollama, select it as your Brain model; for offline work, switch your Brain to Ollama before you go offline, since there's no automatic fall-through to local.