> ## Documentation Index
> Fetch the complete documentation index at: https://docs.arouter.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Supported Providers
> All LLM providers available through ARouter, with their supported models and endpoints.
## Provider List
ARouter supports the following providers. All are accessible through the
OpenAI-compatible `/v1/chat/completions` endpoint using the `provider/model` format.
**Provider ID:** `openai`
| Model | Description |
| -------------- | -------------------------------------------------------- |
| `gpt-5.4` | Flagship multimodal model |
| `gpt-5.4-mini` | Fast and cost-efficient |
| `gpt-5.4-nano` | Ultra-lightweight, ideal for classification & extraction |
| `o4-mini` | Latest compact reasoning model |
| `o3` | Advanced reasoning model |
```python theme={null}
response = client.chat.completions.create(
model="openai/gpt-5.4",
messages=[{"role": "user", "content": "Hello!"}],
)
```
**Provider ID:** `anthropic`
| Model | Description |
| ------------------- | ----------------------------------------- |
| `claude-sonnet-4.6` | Latest Sonnet — best balanced performance |
| `claude-opus-4.6` | Most capable Claude model |
| `claude-haiku-4.5` | Fast and lightweight |
Works with both the OpenAI-compatible endpoint and the native Anthropic endpoint:
```python theme={null}
# Via OpenAI SDK
response = client.chat.completions.create(
model="anthropic/claude-sonnet-4.6", ...
)
# Via Anthropic SDK (native)
message = anthropic_client.messages.create(
model="claude-sonnet-4.6", ...
)
```
**Provider ID:** `google`
| Model | Description |
| ------------------ | -------------------------------------------- |
| `gemini-2.5-flash` | Fast multimodal model with built-in thinking |
| `gemini-2.5-pro` | Most capable Gemini model, 1M context |
Works with both the OpenAI-compatible endpoint and the native Gemini endpoint:
```python theme={null}
# Via OpenAI SDK
response = client.chat.completions.create(
model="google/gemini-2.5-flash", ...
)
# Via Gemini SDK (native)
model = genai.GenerativeModel("gemini-2.5-flash")
response = model.generate_content("Hello!")
```
**Provider ID:** `deepseek`
| Model | Description |
| --------------- | -------------------------------------------------------------- |
| `deepseek-v3.2` | Flagship general model — GPT-5 class at a fraction of the cost |
| `deepseek-r1` | Chain-of-thought reasoning model |
```python theme={null}
response = client.chat.completions.create(
model="deepseek/deepseek-v3.2", ...
)
```
**Provider ID:** `x-ai`
| Model | Description |
| --------------- | ---------------------------------------------------- |
| `grok-4.20` | Latest flagship model with lowest hallucination rate |
| `grok-4.1-fast` | Ultra-fast model with 2M context window |
```python theme={null}
response = client.chat.completions.create(
model="x-ai/grok-4.20", ...
)
```
**Provider ID:** `mistralai`
| Model | Description |
| -------------------- | -------------------------------------------- |
| `mistral-large-2512` | Mistral Large 3 — most capable Mistral model |
| `mistral-medium-3.1` | Balanced performance and cost |
| `codestral-2508` | Optimized for code generation |
```python theme={null}
response = client.chat.completions.create(
model="mistralai/mistral-large-2512", ...
)
```
**Provider ID:** `groq`
| Model | Description |
| ----------------------------- | ------------------------------------------------- |
| `meta-llama/llama-4-maverick` | Llama 4 Maverick on Groq — multimodal, ultra-fast |
| `meta-llama/llama-4-scout` | Llama 4 Scout on Groq — 10M context window |
```python theme={null}
response = client.chat.completions.create(
model="groq/meta-llama/llama-4-maverick", ...
)
```
**Provider ID:** `moonshotai`
| Model | Description |
| ----------- | --------------------------------------------- |
| `kimi-k2.5` | Latest Kimi flagship — multimodal with vision |
```python theme={null}
response = client.chat.completions.create(
model="moonshotai/kimi-k2.5", ...
)
```
**Provider ID:** `minimax`
| Model | Description |
| -------------- | ---------------------------------------- |
| `minimax-m2.7` | Latest flagship — long-context reasoning |
Native MiniMax endpoint is also supported:
```python theme={null}
response = client.chat.completions.create(
model="minimax/minimax-m2.7", ...
)
```
**Provider ID:** `meta-llama`
| Model | Description |
| ------------------ | -------------------------------------------------------- |
| `llama-4-maverick` | Llama 4 flagship — natively multimodal, 128K context |
| `llama-4-scout` | Llama 4 Scout — 10M context window, single GPU efficient |
```python theme={null}
response = client.chat.completions.create(
model="meta-llama/llama-4-maverick", ...
)
```
**Provider ID:** `qwen`
| Model | Description |
| ------------------- | ------------------------------------------------------- |
| `qwen3.5-397b-a17b` | Qwen 3.5 flagship — multimodal with video understanding |
| `qwen3-coder` | 480B coding specialist |
```python theme={null}
response = client.chat.completions.create(
model="qwen/qwen3.5-397b-a17b", ...
)
```
## Listing Available Models
Use the models endpoint to see all models accessible with your current API key:
```bash theme={null}
curl https://api.arouter.ai/v1/models \
-H "Authorization: Bearer lr_live_xxxx"
```
Response:
```json theme={null}
{
"object": "list",
"data": [
{
"id": "openai/gpt-5.4",
"object": "model",
"owned_by": "openai"
},
{
"id": "anthropic/claude-sonnet-4.6",
"object": "model",
"owned_by": "anthropic"
}
]
}
```
The models list is filtered based on your API key's `allowed_providers` setting.
If your key restricts providers, only models from allowed providers will appear.