Images

curl https://gateway.toolken.ai/v1/images/generations \
  -H "X-Toolken-Key: tk_live_..." \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A bar chart showing LLM costs by feature",
    "n": 1,
    "size": "1024x1024"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.toolken.ai/v1",
    api_key="sk-...",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.images.generate(
    model="dall-e-3",
    prompt="A bar chart showing LLM costs by feature",
    n=1,
    size="1024x1024",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.toolken.ai/v1",
  apiKey: "sk-...",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.images.generate({
  model: "dall-e-3",
  prompt: "A bar chart showing LLM costs by feature",
  n: 1,
  size: "1024x1024",
});

{
  "created": 1715367049,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/..."
    }
  ]
}

POST

images

generations

curl https://gateway.toolken.ai/v1/images/generations \
  -H "X-Toolken-Key: tk_live_..." \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A bar chart showing LLM costs by feature",
    "n": 1,
    "size": "1024x1024"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.toolken.ai/v1",
    api_key="sk-...",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.images.generate(
    model="dall-e-3",
    prompt="A bar chart showing LLM costs by feature",
    n=1,
    size="1024x1024",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.toolken.ai/v1",
  apiKey: "sk-...",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.images.generate({
  model: "dall-e-3",
  prompt: "A bar chart showing LLM costs by feature",
  n: 1,
  size: "1024x1024",
});

{
  "created": 1715367049,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/..."
    }
  ]
}

Pass-through to the provider’s images endpoint (generation, editing, variations). Request and response bodies follow the standard OpenAI Images API schema. The provider is inferred from the model name (e.g. dall-e-3, gpt-image-1 route to OpenAI).

Image requests pass through to your provider and work today. They are not yet counted toward your cost totals, because the Images API does not return token usage. Full cost tracking for images is coming soon.

Headers

X-Toolken-Key

string

required

Your Toolken API key. Validated by the gateway and stripped before forwarding.

Authorization

string

required

Your provider key in Bearer format (BYOK), e.g. Bearer sk-.... Forwarded untouched, never stored.

X-Toolken-Metadata

string

Primary attribution channel. JSON object of key-value pairs (e.g. {"agent":"research-agent","customer_id":"cust_abc"}). Each key becomes a groupable dimension in the dashboard.

X-Toolken-Metadata-*

string

Flat-header shorthand. X-Toolken-Metadata-Agent: research-agent writes metadata key agent. Equivalent to sending the same key in X-Toolken-Metadata.

X-Toolken-Metadata-Feature

string

Sets the feature metadata key. Use to group costs by agent name, workflow, UI surface, or job type.

X-Toolken-Metadata-Customer-Id

string

Sets the customer_id metadata key. Use to attribute costs to an end-customer, org slug, or account ID.

Body

model

string

required

Image model identifier (e.g. dall-e-3, gpt-image-1).

prompt

string

required

Text description of the image to generate.

integer

Number of images to generate. Defaults to 1.

size

string

Image dimensions (e.g. 1024x1024). Supported values depend on the model.

Response

created

integer

Unix timestamp of when the request was processed.

data

array

Array of generated image objects. Each contains a url or b64_json field depending on the requested response format.

curl https://gateway.toolken.ai/v1/images/generations \
  -H "X-Toolken-Key: tk_live_..." \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A bar chart showing LLM costs by feature",
    "n": 1,
    "size": "1024x1024"
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.toolken.ai/v1",
    api_key="sk-...",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.images.generate(
    model="dall-e-3",
    prompt="A bar chart showing LLM costs by feature",
    n=1,
    size="1024x1024",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.toolken.ai/v1",
  apiKey: "sk-...",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.images.generate({
  model: "dall-e-3",
  prompt: "A bar chart showing LLM costs by feature",
  n: 1,
  size: "1024x1024",
});

{
  "created": 1715367049,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/..."
    }
  ]
}

Audio List Models

Gateway API

AI Gateway

Models

Toolken API

Headers

Body

Response

​Headers

​Body

​Response

Headers

Body

Response