Get Ollama Cloud Models

README.md

curl https://ollama.com/v1/models | jq .

{
  "object": "list",
  "data": [
    {
      "id": "glm-4.6",
      "object": "model",
      "created": 1759104000,
      "owned_by": "ollama"
    },
    {
      "id": "kimi-k2:1t",
      "object": "model",
      "created": 1757030400,
      "owned_by": "ollama"
    },
    {
      "id": "kimi-k2-thinking",
      "object": "model",
      "created": 1762387200,
      "owned_by": "ollama"
    },
    {
      "id": "qwen3-coder:480b",
      "object": "model",
      "created": 1753142400,
      "owned_by": "ollama"
    },
    {
      "id": "deepseek-v3.1:671b",
      "object": "model",
      "created": 1755734400,
      "owned_by": "ollama"
    },
    {
      "id": "gpt-oss:120b",
      "object": "model",
      "created": 1754352000,
      "owned_by": "ollama"
    },
    {
      "id": "gpt-oss:20b",
      "object": "model",
      "created": 1754352000,
      "owned_by": "ollama"
    },
    {
      "id": "qwen3-vl:235b-instruct",
      "object": "model",
      "created": 1758499200,
      "owned_by": "ollama"
    },
    {
      "id": "qwen3-vl:235b",
      "object": "model",
      "created": 1758499200,
      "owned_by": "ollama"
    },
    {
      "id": "minimax-m2",
      "object": "model",
      "created": 1761523200,
      "owned_by": "ollama"
    }
  ]
}

Model capabilities

curl https://ollama.com/api/show \                                                                                                                            [12:06:26]
     -H "Content-Type: application/json" \
     -d '{"name":"kimi-k2-thinking:cloud}' | jq .

[NOTE!] The model name has a cloud suffix. kimi-k2-thinking becomes kimi-k2-thinking:cloud. qwen3-coder:480b becomes qwen3-coder:480b-cloud.

{
  "details": {
    "parent_model": "kimi-k2-thinking",
    "format": "",
    "family": "kimi-k2",
    "families": null,
    "parameter_size": "1042000000000",
    "quantization_level": "INT4"
  },
  "model_info": {
    "general.architecture": "kimi-k2",
    "general.parameter_count": 1042000000000,
    "kimi-k2.context_length": 262144,
    "kimi-k2.embedding_length": 2048
  },
  "capabilities": [
    "completion",
    "tools",
    "thinking"
  ],
  "modified_at": "0001-01-01T00:00:00Z"
}

config.yaml

# LiteLLM Config

```yaml
{
  "details": {
    "parent_model": "kimi-k2-thinking",
    "format": "",
    "family": "kimi-k2",
    "families": null,
    "parameter_size": "1042000000000",
    "quantization_level": "INT4"
  },
  "model_info": {
    "general.architecture": "kimi-k2",
    "general.parameter_count": 1042000000000,
    "kimi-k2.context_length": 262144,
    "kimi-k2.embedding_length": 2048
  },
  "capabilities": [
    "completion",
    "tools",
    "thinking"
  ],
  "modified_at": "0001-01-01T00:00:00Z"
}
```

> [NOTE!]
> You must specify your API key in your `.env` file:
> 
> ```
> OLLAMA_AUTH_HEADER=Bearer XXX
> ```