EvoLink

https://evolink.ai/docs/en/
Admin
EvoLink is an enterprise AI gateway platform that provides unified access, robust task management,...
Tokens:996,104
Snippets:4,913
Trust Score:7.1
Update:5 days ago
Show doc for...
Tokens:
Raw
### Run OpenClaw Onboarding with Daemon

Source: https://evolink.ai/docs/en/integration-guide/openclaw-feishu

Run the onboarding command to guide through initial setup and install the background daemon service.

```bash
openclaw onboard --install-daemon

```

--------------------------------

### Go example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Go example using net/http to GET /v1/credits. Replace <token> with your API token. Prints the response body.

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/credits"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Combined setup for installed CLI

Source: https://evolink.ai/docs/en/cli/claude-code

Run the setup command to check the environment, synchronize skills, sign in when needed, and verify access. Look for 'setup_complete: true'; host discovery still needs confirmation.

```bash
evolink setup --agent claude-code --json
```

--------------------------------

### Run Hermes setup wizard

Source: https://evolink.ai/docs/en/integration-guide/hermes

Starts the interactive setup wizard to configure the EvoLink endpoint. Select 'custom endpoint' and enter the API base URL, API key, and compatibility mode.

```bash
hermes model

```

--------------------------------

### Combined setup for an installed CLI

Source: https://evolink.ai/docs/en/cli/cursor

Run `evolink setup` to check the environment, synchronize skills, sign in when needed, and verify access. Look for `setup_complete: true`; host discovery still needs confirmation. Use `phase`, `steps`, `error`, and `recovery` to identify failures.

```bash
evolink setup --agent cursor --json

```

--------------------------------

### POST /v1/responses

Source: https://evolink.ai/docs/en/api-manual/language-series/glm/responses/responses-quickstart

Creates a model response. The minimum required fields are model and input. The examples also set an output budget and reasoning effort to help you get started.

```APIDOC
## POST /v1/responses

### Description
Creates a model response. The minimum required fields are model and input. The examples also set an output budget and reasoning effort to help you get started.

### Method
POST

### Endpoint
/v1/responses

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for the response.
- **input** (string/array) - Required - The input prompt or messages.
- **output_budget** (integer) - Optional - The maximum number of output tokens to generate.
- **reasoning** (object) - Optional - Contains the reasoning effort configuration.
  - **effort** (string) - Optional - The reasoning effort level. Supported values: `low`, `high`, `max`, `xhigh`, `medium`, `minimal`, `none`. See compatibility rules for glm-5.3 series.

### Request Example
{
  "model": "glm-5.3",
  "input": "Hello, world!",
  "output_budget": 1000,
  "reasoning": {
    "effort": "low"
  }
}

### Response
#### Success Response (200)
- **id** (string) - The response ID.
- **object** (string) - The object type, e.g., "response".
- **created_at** (integer) - Unix timestamp of creation.
- **status** (string) - The status of the response.
- **output** (array) - The generated output items.
- **usage** (object) - Token usage details, including `output_tokens` and `reasoning_tokens`.

#### Response Example
{
  "id": "resp_123",
  "object": "response",
  "created_at": 1710000000,
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you?"
        }
      ]
    }
  ],
  "usage": {
    "output_tokens": 10,
    "reasoning_tokens": 0
  }
}

### Notes
- The default BaseURL is `https://direct.evolink.ai`, which has better support for text models and long-lived connections. `https://api.evolink.ai` is the primary endpoint for multimodal services and serves as a fallback address for text models.
- Responses uses nested `reasoning.effort`, rather than top-level `reasoning_effort` or thinking.
- Reasoning usage is included in `output_tokens`. Simple tasks may return `reasoning_tokens=0`; this does not imply that thinking can be disabled.
- **Compatibility rules for `glm-5.3` / `glm-5.3-flash` / `glm-5.3-flashx`**:
  - `low` / `high` / `max` - Unchanged
  - `xhigh` - `max`
  - `medium` - `high`
  - `minimal` / `none` - `low`; thinking remains enabled
- `minimal` and `none` do not disable thinking on the 5.3 series. Thinking tokens are billed as output. Unrecognized values are unchanged and have no compatibility mapping; use the listed values. These mappings do not apply to glm-5.2.
- On this endpoint, `glm-5.2` may still produce reasoning tokens with `none`. This value does not guarantee that thinking is disabled.
```

--------------------------------

### Example: instructions string

Source: https://evolink.ai/docs/en/api-manual/language-series/gpt/responses/responses-reference

Example value for the 'instructions' parameter: system-level instructions for the assistant.

```text
"You are a concise assistant. Answer in no more than three sentences."
```

--------------------------------

### Ask your agent to install EvoLink

Source: https://evolink.ai/docs/en/cli/cursor

Paste this prompt into the agent conversation to set up EvoLink for media generation. It instructs the agent to install the CLI, sign in, install the companion skill, and verify the connection. Complete browser sign-in and permission review yourself.

```markdown
Set up EvoLink so I can generate images, video and audio directly here.
1. Install the CLI: run `npm install -g @evolinkai/cli`.
2. Sign in: run `evolink auth login`.
3. Install the companion skill: run `evolink skills install`.
4. Verify the connection. Once successful, tell me I can get started.

```

--------------------------------

### Ruby example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Ruby example using Net::HTTP to GET /v1/credits. Replace <token> with your API token. Prints the response body.

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.evolink.ai/v1/credits")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
```

--------------------------------

### Manual CLI installation and verification commands

Source: https://evolink.ai/docs/en/cli/overview

Basic manual sequence to install the CLI, sign in, install the skill, and verify with balance and doctor commands. Wait for sign-in to complete before continuing.

```bash
npm install -g @evolinkai/cli
evolink auth login
evolink skills install
evolink balance --json
evolink doctor --json

```

--------------------------------

### Java Unirest example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Java example using Unirest to GET /v1/credits. Replace <token> with your API token. Returns the response as a string.

```java
HttpResponse<String> response = Unirest.get("https://api.evolink.ai/v1/credits")
  .header("Authorization", "Bearer <token>")
  .asString();
```

--------------------------------

### JavaScript fetch example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

JavaScript example using fetch to GET /v1/credits. Replace <token> with your API token. Logs the JSON response.

```javascript
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.evolink.ai/v1/credits', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
```

--------------------------------

### PHP cURL example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

PHP example using cURL to GET /v1/credits. Replace <token> with your API token. Outputs the response or a cURL error.

```php
<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.evolink.ai/v1/credits",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}
```

--------------------------------

### Python requests example to get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Python example using the requests library to GET /v1/credits. Replace <token> with your API token. Prints the response text.

```python
import requests

url = "https://api.evolink.ai/v1/credits"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)
```

--------------------------------

### evolink setup --agent codex --json

Source: https://evolink.ai/docs/en/cli/reference

Checks prerequisites, logs in, syncs skills, and verifies free connection.

```APIDOC
## evolink setup --agent codex --json

### Description
Checks prerequisites, logs in, syncs skills, and verifies free connection.

### Command
`evolink setup --agent codex --json`

### Options
- `--agent` (string) - Agent name (e.g., codex). Default: all.
- `--json` (flag) - Output in JSON format.

### Output
Includes `update` object with `status`, `update_available`, `latest_version`, `command`.
```

--------------------------------

### Install only the MCP skill

Source: https://evolink.ai/docs/en/mcp/plugins

Use this command to install the repository skills through the skills installer when native MCP is already configured. It does not install EvoLink CLI, start local MCP, or complete OAuth.

```shell
npx skills add Evolink-AI/mcp-plugin -g -y

```

--------------------------------

### Go example for image generation

Source: https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-1/beta/nanobanana-image-generate

Uses net/http to POST the nano-banana-beta model and prompt to the image generation endpoint. Prints the response body.

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"nano-banana-beta\",\n  \"prompt\": \"A cat playing on the grass\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Install skill for Gemini agent

Source: https://evolink.ai/docs/en/cli/setup

Example of installing the skill for the Gemini CLI agent using the agent name 'gemini'.

```bash
evolink skills install --agent gemini
evolink doctor --agent gemini --json

```

--------------------------------

### Get npm installation prefix

Source: https://evolink.ai/docs/en/cli/billing

Run this command to check npm's installation location, which helps diagnose missing evolink commands.

```bash
npm config get prefix
```

--------------------------------

### Go example for video generation

Source: https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-text-to-video

Go example using net/http to POST to the video generation endpoint. Prints the response body.

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"grok-imagine-text-to-video-beta\",\n  \"prompt\": \"A cat playing piano in a jazz club\",\n  \"duration\": 6,\n  \"mode\": \"fun\",\n  \"aspect_ratio\": \"16:9\",\n  \"quality\": \"480p\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Go example for image-to-video generation

Source: https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-image-to-video

Uses the net/http package to POST the image-to-video generation request to the Evolink API. Prints the response body.

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"gemini-omni-flash-image-to-video\",\n  \"prompt\": \"Have the person in the image slowly turn their head and smile while the leaves in the background sway gently in the breeze\",\n  \"image_urls\": [\n    \"https://example.com/portrait.jpg\"\n  ],\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 10\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Success response for get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Example JSON response for a successful GET /v1/credits request. Shows remaining and used credits for both the token and the user.

```json
{
  "data": {
    "token": {
      "remaining_credits": 99416.4429,
      "unlimited_credits": false,
      "used_credits": 583.5571
    },
    "user": {
      "remaining_credits": 1095.3996,
      "used_credits": 135.9048
    }
  },
  "message": "",
  "success": true
}
```

--------------------------------

### Go example for wan2.5-image-to-image

Source: https://evolink.ai/docs/en/api-manual/image-series/wan2.5/wan2.5-image-to-image

Go example using net/http to POST to the image generation endpoint. Replace <token> with your API token. Prints the response body.

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"wan2.5-image-to-image\",\n  \"prompt\": \"Replace the background with a starry sky\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Go example for video generation

Source: https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-i2v

Uses the net/http package to POST the video generation request to the Evolink API. Prints the response body. Replace <token> with your API key.

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.evolink.ai/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"grok-imagine-video-1.0-i2v\",\n  \"prompt\": \"The person starts dancing\",\n  \"image_urls\": [\n    \"https://cdn.evolink.ai/Model-Example/GrokImagine1.5/generated-image.png\"\n  ],\n  \"duration\": 6,\n  \"quality\": \"480p\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
```

--------------------------------

### Error response 403 for get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Example error response for HTTP 403 Access denied.

```json
{
  "error": {
    "code": 403,
    "message": "Access denied",
    "type": "permission_error"
  }
}
```

--------------------------------

### Example: input string

Source: https://evolink.ai/docs/en/api-manual/language-series/gpt/responses/responses-reference

Example value for the 'input' parameter: a user message asking for a web search and summary.

```text
"Search for AI news from the past week and summarize it in three sentences."
```

--------------------------------

### Verify existing installation and sign-in

Source: https://evolink.ai/docs/en/cli/cursor

Run these commands to verify the CLI is installed and authenticated. Look for a CLI version and `authenticated: true` in the output.

```bash
evolink --version
evolink auth status --json

```

--------------------------------

### Error response 400 for get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Example error response for HTTP 400 Invalid request.

```json
{
  "error": {
    "code": 400,
    "message": "Invalid request",
    "type": "invalid_request_error"
  }
}
```

--------------------------------

### Error response 401 for get credits

Source: https://evolink.ai/docs/en/api-manual/account-management/get-credits

Example error response for HTTP 401 Invalid or expired token.

```json
{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}
```
Tokens:
Raw