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

# Get LLM Integration

> Gets details about a specific LLM integration.

`Unary` · [`Runner Configurations`](https://ona.com/docs/api-reference/generated/runner-configuration/overview)

Gets details about a specific LLM integration.

Use this method to:

* View integration settings
* Check integration status
* Verify configuration

### Examples

* Get integration details:

  Retrieves information about a specific integration.

  ```yaml theme={null}
  id: "d2c94c27-3b76-4a42-b88c-95a85e392c68"
  ```

## Endpoint

```text theme={null}
POST /api/gitpod.v1.RunnerConfigurationService/GetLLMIntegration
```

Send a Bearer token as described in [Authentication](https://ona.com/docs/api-reference.md#authenticate-requests). If your organization uses a custom management-plane domain, replace `https://app.ona.com` with that domain.

## Request example

```bash cURL theme={null}
export ONA_HOST=https://app.ona.com
export ONA_API_KEY=<your-token>

curl --request POST \
  --url "$ONA_HOST/api/gitpod.v1.RunnerConfigurationService/GetLLMIntegration" \
  --header "Authorization: Bearer $ONA_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "id": "<id>"
}'
```

```python Python theme={null}
import gitpod.v1.runner_configuration_pb2 as runner_configuration_pb2
from ona_sdk import create_client_from_env

ona = create_client_from_env()
request = runner_configuration_pb2.GetLLMIntegrationRequest(
    id="<id>",
)
response = ona.services.runner_configuration.get_llm_integration(request)
print(response)
```

```typescript TypeScript theme={null}
import { create } from "@bufbuild/protobuf";
import { createClientFromEnv } from "@gitpod/sdk";
import { GetLLMIntegrationRequestSchema } from "@gitpod/sdk/gitpod/v1/runner_configuration_pb";

async function main() {
  const ona = createClientFromEnv();
  const request = create(GetLLMIntegrationRequestSchema, {
    id: "<id>",
  });
  const response = await ona.services.runnerConfiguration.getLLMIntegration(request);
  console.log(response);
}

main().catch(console.error);
```

```go Go theme={null}
package main

import (
	"context"
	"fmt"
	"log"

	"connectrpc.com/connect"
	"github.com/gitpod-io/gitpod-sdk-go/sdk"
	gitpodpb "github.com/gitpod-io/gitpod-sdk-go/v1"
)

func main() {
	ona, err := sdk.NewFromEnv()
	if err != nil {
		log.Fatal(err)
	}

	request := connect.NewRequest(&gitpodpb.GetLLMIntegrationRequest{
		Id: "<id>",
	})
	response, err := ona.Services.RunnerConfiguration.GetLLMIntegration(context.Background(), request)
	if err != nil {
		log.Fatal(err)
	}
	fmt.Println(response.Msg)
}
```

```json Request body theme={null}
{
  "id": "<id>"
}
```

## Request

`gitpod.v1.GetLLMIntegrationRequest`

| Field | Type | Required | Description |
| - | - | - | - |
| `id` | string | No | Constraints: `string.uuid=true`. |

## Response

`gitpod.v1.GetLLMIntegrationResponse`

| Field | Type | Required | Description |
| - | - | - | - |
| `integration` | [LLMIntegration](#type-gitpod-v1-llm-integration) | No | |

## Related types

> [accordion] LLMIntegration
>
> `gitpod.v1.LLMIntegration`
>
> | Field | Type | Required | Description |
> | - | - | - | - |
> | `id` | string | No | id is the unique identifier of the LLM integration |
> | `runnerId` | string | No | |
> | `models` | array of [SupportedModel](#enum-gitpod-v1-supported-model) | No | models represents the supported LLM models for this integration |
> | `endpoint` | string | No | |
> | `encryptedApiKey` | base64 string | No | encrypted\_api\_key is the LLM provider's API key encrypted with the runner's public key. |
> | `maxTokens` | 64-bit integer string | No | the maximum number of tokens to generate before stopping. 0 is a model default. |
> | `phase` | [LLMIntegrationPhase](#enum-gitpod-v1-llm-integration-phase) | No | phase represents the current status/phase of the LLM integration |
> | `phaseReason` | string | No | phase\_reason provides explanation for the current phase (e.g., "insufficient funds", "user disabled") |
> | `requestHeaders` | array of [LLMIntegrationRequestHeader](#type-gitpod-v1-llm-integration-request-header) | No | request\_headers contains optional headers for the LLM integration. |
> | `provider` | [LLMProvider](#enum-gitpod-v1-llm-provider) | No | provider identifies the governance provider family for this integration. |

> [accordion] LLMIntegrationRequestHeader
>
> LLMIntegrationRequestHeader represents a custom header to be passed to LLM requests.
> The value field contains:
>
> * Plain text values in update requests (will be encrypted server-side).
> * Encrypted binary values on read requests (decrypt directly to get original value).
>
> `gitpod.v1.LLMIntegrationRequestHeader`
>
> | Field | Type | Required | Description |
> | - | - | - | - |
> | `key` | string | No | |
> | `value` | base64 string | No | |
> | `headerType` | [LLMIntegrationRequestHeaderType](#enum-gitpod-v1-llm-integration-request-header-type) | No | header\_type controls how value is interpreted. Unspecified values are treated as literals for backward compatibility. Constraints: `enum.defined_only=true`. |

> [accordion] LLMIntegrationPhase
>
> LLMIntegrationPhase represents the current status/phase of an LLM integration
>
> | Value | Number | Description |
> | - | -: | - |
> | `LLM_INTEGRATION_PHASE_UNSPECIFIED` | 0 | |
> | `LLM_INTEGRATION_PHASE_AVAILABLE` | 1 | The integration can be used to make requests |
> | `LLM_INTEGRATION_PHASE_UNAVAILABLE` | 2 | The integration cannot be used, likely due to insufficient funds |
> | `LLM_INTEGRATION_PHASE_DISABLED` | 3 | The integration cannot be used because the user disabled it |

> [accordion] LLMIntegrationRequestHeaderType
>
> LLMIntegrationRequestHeaderType describes how an LLM integration request
> header value is resolved.
>
> | Value | Number | Description |
> | - | -: | - |
> | `LLM_INTEGRATION_REQUEST_HEADER_TYPE_UNSPECIFIED` | 0 | Existing untyped headers are literal values. |
> | `LLM_INTEGRATION_REQUEST_HEADER_TYPE_LITERAL` | 1 | The configured value is sent as-is when the request does not already contain the header. |
> | `LLM_INTEGRATION_REQUEST_HEADER_TYPE_CEL_EXPRESSION` | 2 | The configured value is a CEL expression evaluated by a supported agent. |

> [accordion] LLMProvider
>
> | Value | Number | Description |
> | - | -: | - |
> | `LLM_PROVIDER_UNSPECIFIED` | 0 | |
> | `LLM_PROVIDER_ANTHROPIC` | 1 | Anthropic models, including Claude-family models served via Anthropic, Bedrock, or Vertex endpoints. |
> | `LLM_PROVIDER_OPENAI` | 2 | OpenAI models, including OPENAI\_AUTO and OpenAI-compatible endpoints. |

> [accordion] SupportedModel
>
> SupportedModel enumerates the LLM models available for agent executions
>
> | Value | Number | Description |
> | - | -: | - |
> | `SUPPORTED_MODEL_UNSPECIFIED` | 0 | |
> | `SUPPORTED_MODEL_SONNET_3_5` | 1 | |
> | `SUPPORTED_MODEL_SONNET_3_7` | 2 | |
> | `SUPPORTED_MODEL_SONNET_3_7_EXTENDED` | 3 | |
> | `SUPPORTED_MODEL_SONNET_4` | 4 | |
> | `SUPPORTED_MODEL_SONNET_4_EXTENDED` | 5 | |
> | `SUPPORTED_MODEL_SONNET_4_5` | 8 | |
> | `SUPPORTED_MODEL_SONNET_4_5_EXTENDED` | 9 | |
> | `SUPPORTED_MODEL_SONNET_4_6` | 18 | |
> | `SUPPORTED_MODEL_SONNET_4_6_EXTENDED` | 19 | |
> | `SUPPORTED_MODEL_SONNET_5` | 32 | |
> | `SUPPORTED_MODEL_OPUS_4` | 6 | |
> | `SUPPORTED_MODEL_OPUS_4_EXTENDED` | 7 | |
> | `SUPPORTED_MODEL_OPUS_4_5` | 14 | |
> | `SUPPORTED_MODEL_OPUS_4_5_EXTENDED` | 15 | |
> | `SUPPORTED_MODEL_OPUS_4_6` | 16 | |
> | `SUPPORTED_MODEL_OPUS_4_6_EXTENDED` | 17 | |
> | `SUPPORTED_MODEL_OPUS_4_7` | 22 | |
> | `SUPPORTED_MODEL_OPUS_4_8` | 31 | |
> | `SUPPORTED_MODEL_HAIKU_4_5` | 21 | |
> | `SUPPORTED_MODEL_OPENAI_4O` | 10 | |
> | `SUPPORTED_MODEL_OPENAI_4O_MINI` | 11 | |
> | `SUPPORTED_MODEL_OPENAI_O1` | 12 | |
> | `SUPPORTED_MODEL_OPENAI_O1_MINI` | 13 | |
> | `SUPPORTED_MODEL_OPENAI_AUTO` | 23 | SUPPORTED\_MODEL\_OPENAI\_AUTO flags a request as OpenAI-bound without encoding a specific model slug. The actual model is chosen by the client (today: native Codex via \~/.codex/config.toml) and captured from the upstream Responses-API response.model field for metering and rate-card lookup. This keeps the proto stable across OpenAI model-catalog churn. Reserved numbers 24-30 are intentionally left free for future OpenAI routing sentinels if we ever need to distinguish sub-families. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.