chore: sync Comfy API v2 specification and Comfy Router pages (cloud@1eab676)

development/comfy-router/limitations.mdx

@@ -4,34 +4,38 @@
 description: "Choose Router or a partner proxy, plan for long-running calls, and understand recovery, rate limits, and asset storage."
 ---
 
-Router supports synchronous and queued delivery. Synchronous delivery returns the finished result in one response. Queued delivery returns a request handle and is rolling out by workspace.
+Router runs a partner model through one synchronous HTTP call or, in a gated preview, through a queued request that you submit and collect later. Use it when your application can wait for a finished result or collect one later, and can handle the model's own input and output fields.
 
 ## What Router supports
 
 | Requirement | Router support | Alternative or next step |
 | --- | --- | --- |
 | Generate with one request | `POST /v2/models/{provider}/{model}` returns the finished result. | Start with the [Quickstart](/development/comfy-router/quickstart). |
-| Submit a request and collect it later | Supported through `POST /v2/models/{provider}/{model}/requests` and rolling out by workspace. | See [Queued delivery](/development/comfy-router/queue). |
-| Show progress or stream output | Queued delivery reports queue state and can include queue position, but no percentage progress, streaming output, or preview frames. | Poll the returned `status_url`, or use a supported proxy operation for provider-specific progress. |
-| Recover after a lost connection | After receiving a queued request handle, use its returned URLs. If submission is interrupted before that, retry with the same idempotency key. Synchronous calls can sometimes be collected the same way. | Preserve the idempotency key and follow [retry guidance](/development/comfy-router/api#retry-outcomes). |
+| Submit a job and collect it later | Queued delivery, in a gated preview: `POST /v2/models/{provider}/{model}/requests` returns a `request_id` to poll and collect. No completion webhook. | Use [queued delivery](/development/comfy-router/queue) where it is enabled; otherwise run Router from a worker, or use a partner proxy with submit-and-poll operations. |
+| Show progress or stream output | No live progress, streaming, or preview frames during the call. | Show an indeterminate state, or use a supported proxy operation. |
+| Recover after a lost connection | Same-key collection is available when Router retained a handle to an accepted generation. | Preserve the key and follow [retry guidance](/development/comfy-router/api#retry-outcomes). |
 | Reconcile Comfy charges | No universal Comfy cost or credit-balance field on the response. | Use [workspace billing](https://platform.comfy.org). |
 | Store results permanently | Asset URLs can expire, including rehosted and replayed URLs. | Download the assets; see [result assets](/development/comfy-router/reference#result-assets). |
 
-## Queued delivery availability
+<span id="no-queued-submission" />
 
-Queued delivery returns a `request_id` and URLs for status, result collection, and cancellation. It is rolling out by workspace; workspaces without access receive `403` with `not_enabled`. Cancellation is best effort, and Router does not provide a completion webhook. See [Queued delivery](/development/comfy-router/queue) for examples and the full lifecycle.
+## Queued submission is a gated preview
 
-## Synchronous calls are cut off at a server deadline
+Router holds the connection while the model runs. For asynchronous providers, it submits the job and polls internally. Queued delivery (submit, get a `request_id`, poll, collect) is in a gated preview: see [Queued delivery](/development/comfy-router/queue). It is scoped to the workspace behind the credential, so it needs a key created in your Comfy workspace and a workspace that is enabled; otherwise the submit route answers `403` with `not_enabled`. Outside the preview, Router does not expose a job ID, status endpoint, callback, or webhook.
+
+If your request cannot stay open long enough, call Router from a worker and track the job in your application. Use a [partner proxy](#router-does-not-cover-every-partner-operation) when you need the provider's submit-and-poll controls.
+
+## Calls are cut off at a server deadline
 
 Router's default deadline is **10 minutes**, configurable by the deployment. Set your client timeout above it so Router can return its error and request ID first.
 
 `504` / `deadline_exceeded` means Router stopped waiting; `504` / `provider_timeout` means the provider timed out. A timeout or lost connection does not prove that a generation was unbilled, and it does not cancel accepted provider work. Read [timeouts and collection](/development/comfy-router/api#timeouts-and-collection) before retrying.
 
 <span id="no-way-to-resume-a-call-you-lost" />
 
 ## Recovery depends on the provider
 
 Router can retain a provider handle for an accepted submit-and-poll generation. Reuse the same `Idempotency-Key` to collect it later; completed replayable responses can also come from the key record.
 
 Not every disconnected call is recoverable. Preserve the request and key before sending, then use the [retry outcome table](/development/comfy-router/api#retry-outcomes). A new key creates a new call and may incur another charge.
 
@@ -46,11 +50,11 @@
 
 Cache catalog and schema reads. Revalidate schemas with `ETag` and `If-None-Match`. See [Headers](/development/comfy-router/headers) for retry and committed-spend fields.
 
-## No live progress while a request runs
+## No progress while a call runs
 
-Synchronous delivery returns only the final response. Queued delivery exposes queue state and can include queue position, but neither mode provides streamed tokens, server-sent events, percentage updates, or intermediate preview frames. A provider's internal progress is not forwarded.
+Router returns a final response, with no streamed tokens, server-sent events, percentage updates, or intermediate preview frames. A provider's internal polling state is not forwarded during the request.
 
-Show an indeterminate progress indicator after a queued request begins running. If you need provider-specific progress or streaming, use a partner-proxy operation that exposes it.
+Show an indeterminate progress indicator. If you need progress or streaming, use a partner-proxy operation that exposes it.
 
 <span id="no-cost-or-credit-figures-on-a-response" />
 
@@ -68,7 +72,7 @@
 
 Input and output fields vary by model. Moving from a provider SDK or proxy can change both the route and how you read the result.
 
 Some assets are rehosted on Comfy storage; others are provider URLs or inline bytes. See [Result assets](/development/comfy-router/reference#result-assets) for lifetimes and replay behavior.
 
 ## Next
 

development/comfy-router/models/heygen/starfish/code.mdx

@@ -30,7 +30,7 @@
     result = client.models.run(
         "heygen/starfish",
         {
-            "text": "This is a billing verification test for HeyGen speech generation.",
+            "text": "Hello from Comfy. This voice is generated with the HeyGen Starfish engine.",
             "voice_id": "d2f4f24783d04e22ab49ee8fdc3715e0",
         },
     )
@@ -44,7 +44,7 @@
 // Reads COMFY_API_KEY from the environment.
 // The SDK automatically creates an idempotency key and reuses it for automatic retries.
 const { data } = await comfy.models.run("heygen/starfish", {
-  text: "This is a billing verification test for HeyGen speech generation.",
+  text: "Hello from Comfy. This voice is generated with the HeyGen Starfish engine.",
   voice_id: "d2f4f24783d04e22ab49ee8fdc3715e0",
 });
 
@@ -56,7 +56,7 @@
   -H "X-API-Key: $COMFY_API_KEY" \
   -H "Idempotency-Key: $(uuidgen)" \
   -H "Content-Type: application/json" \
-  -d "{\"text\": \"This is a billing verification test for HeyGen speech generation.\", \"voice_id\": \"d2f4f24783d04e22ab49ee8fdc3715e0\"}"
+  -d "{\"text\": \"Hello from Comfy. This voice is generated with the HeyGen Starfish engine.\", \"voice_id\": \"d2f4f24783d04e22ab49ee8fdc3715e0\"}"
 ```
 </CodeGroup>
   </Tab>
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -73,7 +73,7 @@
     handle = client.models.submit(
         "heygen/starfish",
         {
-            "text": "This is a billing verification test for HeyGen speech generation.",
+            "text": "Hello from Comfy. This voice is generated with the HeyGen Starfish engine.",
             "voice_id": "d2f4f24783d04e22ab49ee8fdc3715e0",
         },
     )
@@ -96,7 +96,7 @@
 // Reads COMFY_API_KEY from the environment.
 // Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
 const handle = await comfy.models.submit("heygen/starfish", {
-  text: "This is a billing verification test for HeyGen speech generation.",
+  text: "Hello from Comfy. This voice is generated with the HeyGen Starfish engine.",
   voice_id: "d2f4f24783d04e22ab49ee8fdc3715e0",
 });
 console.log("requestId:", handle.requestId); // with the model ID, all another process needs
@@ -118,7 +118,7 @@
   -H "X-API-Key: $COMFY_API_KEY" \
   -H "Idempotency-Key: $(uuidgen)" \
   -H "Content-Type: application/json" \
-  -d "{\"text\": \"This is a billing verification test for HeyGen speech generation.\", \"voice_id\": \"d2f4f24783d04e22ab49ee8fdc3715e0\"}"
+  -d "{\"text\": \"Hello from Comfy. This voice is generated with the HeyGen Starfish engine.\", \"voice_id\": \"d2f4f24783d04e22ab49ee8fdc3715e0\"}"
 
 # 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
 REQUEST_ID="<request_id from the 201 body>"
@@ -138,7 +138,7 @@
 ### Input
 
 <ParamField body="input_type" type="string">
   Type of the input: 'text' for plain text, 'ssml' for SSML markup. Defaults to 'text'
 </ParamField>
 
 <ParamField body="language" type="string">
@@ -213,7 +213,7 @@
 
 ```json
 {
-  "text": "This is a billing verification test for HeyGen speech generation.",
+  "text": "Hello from Comfy. This voice is generated with the HeyGen Starfish engine.",
   "voice_id": "d2f4f24783d04e22ab49ee8fdc3715e0"
 }
 ```

development/comfy-router/models/recraft/recraftv2/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V2 with Comfy Router"
 description: "Call recraft/recraftv2 through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V2"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv2/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples

development/comfy-router/models/recraft/recraftv3/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V3 with Comfy Router"
 description: "Call recraft/recraftv3 through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V3"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv3/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples

development/comfy-router/models/recraft/recraftv4-1-pro-vector/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V4.1 Pro Vector with Comfy Router"
 description: "Call recraft/recraftv4_1_pro_vector through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V4.1 Pro Vector"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv4_1_pro_vector/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples

development/comfy-router/models/recraft/recraftv4-1-pro/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V4.1 Pro with Comfy Router"
 description: "Call recraft/recraftv4_1_pro through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V4.1 Pro"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv4_1_pro/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples

development/comfy-router/models/recraft/recraftv4-1-utility-pro-vector/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V4.1 Utility Pro Vector with Comfy Router"
 description: "Call recraft/recraftv4_1_utility_pro_vector through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V4.1 Utility Pro Vector"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv4_1_utility_pro_vector/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples

development/comfy-router/models/recraft/recraftv4-1-utility-pro/code.mdx

@@ -1,5 +1,5 @@
 ---
 title: "Use Recraft V4.1 Utility Pro with Comfy Router"
 description: "Call recraft/recraftv4_1_utility_pro through Comfy Router: endpoint, request shape and the response Router returns."
 sidebarTitle: "Recraft V4.1 Utility Pro"
 ---
@@ -65,7 +65,7 @@
 
 <CodeGroup>
 ```python Python
 from comfy_sdk import Comfy
 
 # Reads COMFY_API_KEY from the environment.
 # Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
@@ -172,7 +172,7 @@
 </ParamField>
 
 <ParamField body="n" type="integer">
-  The number of images to generate
+  The number of images to generate. Recraft accepts 1-6.
 
   Range: `1` to `6`
 </ParamField>
@@ -181,16 +181,20 @@
   The text prompt describing the image to generate
 </ParamField>
 
+<ParamField body="response_format" type="string">
+  Possible values: `url`, `b64_json`
+</ParamField>
+
 <ParamField body="size" type="string">
   The size of the generated image (e.g., "1024x1024")
 </ParamField>
 
 <ParamField body="style" type="string">
   The style to apply to the generated image (e.g., "digital_illustration")
 </ParamField>
 
 <ParamField body="style_id" type="string">
   The style ID to apply to the generated image (e.g., "123e4567-e89b-12d3-a456-426614174000"). If style_id is provided, style should not be provided. REQUIRED by the four `recraftv4_styles*` models: Recraft rejects those without a style_id or style reference. Mint one with `POST /proxy/recraft/styles`, which this same proxy serves under the same credentials. Nothing on this route enforces the pairing — the body is forwarded to Recraft unchanged, so a `recraftv4_styles*` call without it reaches the partner and comes back 4xx.
 </ParamField>
 
 Generated from the schema Router serves at `GET /v2/models/recraft/recraftv4_1_utility_pro/openapi.json`, the same document it validates a call against before the request reaches the provider.
@@ -209,12 +213,20 @@
   Array of generated image information
 </ResponseField>
 
+<ResponseField name="data[].b64_json" type="string">
+  Base64-encoded image data (present instead of `url` when the request set `response_format: b64_json`)
+</ResponseField>
+
 <ResponseField name="data[].image_id" type="string">
   Unique identifier for the generated image
 </ResponseField>
 
 <ResponseField name="data[].url" type="string">
-  URL to access the generated image
+  URL to access the generated image (present when `response_format` is `url`, the default)
+</ResponseField>
+
+<ResponseField name="style_id" type="string">
+  The resolved style id, returned by Recraft when style references are used (notably required-input models recraftv4_styles*); reusable as `style_id` in later requests.
 </ResponseField>
 
 ## Examples