vertexai/gemini-nano-banana-2.1, served by Comfy Router from Google.
Input: Text, Image, Video · Output: Image + Text
Quick start
Create a key in your Comfy workspace and export it asCOMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk and npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.
Model ID: vertexai/gemini-nano-banana-2.1
Endpoint: POST https://api.comfy.org/v2/models/vertexai/gemini-nano-banana-2.1
- Wait for the result
- Queue and collect later
The same body, sent to
POST https://api.comfy.org/v2/models/vertexai/gemini-nano-banana-2.1/requests. Router answers 201 with a request_id as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. Queued delivery walks through status, cancellation and collection.Serving providers
This model is served by Comfy Router directly unless the request names another provider. The providers below serve it too, on the same endpoint and with the same model ID, selected with themodel_provider query parameter.
- Comfy (default):
POST https://api.comfy.org/v2/models/vertexai/gemini-nano-banana-2.1 - MiniMax, as
minimax/minimax-nano-banana-2.1:POST https://api.comfy.org/v2/models/vertexai/gemini-nano-banana-2.1?model_provider=minimax
strict_mode defaults to false, so Router translates the native request body documented on this page into the provider’s own schema and translates the response back. See model_provider, strict_mode and fallback_provider in the API reference, and Serving providers for every model routed this way.
Schema
Input
The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values:
application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webmInline data in raw bytes. For gemini-2.0-flash-lite and gemini-2.0-flash, you can specify up to 3000 images by using inlineData.
The base64 encoding of the image, PDF, or video to include inline in the prompt. When including media inline, you must also specify the media type (mimeType) of the data. Size limit: 20MBFormat:
byteThe media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values:
application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webmHow the model reads this part’s video. Set “AGENTIC” to let the model decide which segments to inspect, instead of fixed-rate frame sampling. Omit for the default fixed-rate sampling. Supported on gemini-3.7-flash and newer Flash models.
Sampling, length and output settings for the generation. Every field is optional: the fields below that declare a
default apply it when omitted, and the rest fall back to the model’s own behaviour.Optional. The image format that the output should be saved as, on the Vertex AI paths: requests served by Comfy’s own credentials, and BYOK requests authenticated with a GCP service account. Accepted values there are
image/png and image/jpeg, matched case-insensitively and normalised to lower case before the request is forwarded; any other value is rejected with a 400 naming this field. Defaults to image/png when omitted. A BYOK request authenticated with a Google AI Studio API key is the exception: that upstream has no such property and rejects the whole call if it is present, so the field is dropped from the request rather than honoured or rejected, and the output format is whatever AI Studio chooses. On every path, read the media type back from the response part you are given (inlineData.mimeType, or fileData.mimeType when uploadImagesToStorage is set) rather than assuming the value you sent.Optional. Specifies the size of generated images. Supported values are 1K, 2K, 4K. If not specified, the model will use default value 1K.
Maximum number of tokens that can be generated in the response. A token is approximately 4 characters. 100 tokens correspond to roughly 60-80 words.Range:
16 to 65536When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn’t guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. Available for the following models:, gemini-2.5-flash, gemini-2.5-pro, gemini-2.5-flash-preview-04-1, gemini-2.5-pro-preview-05-0, gemini-2.0-flash-lite-00, gemini-2.0-flash-001
The temperature is used for sampling during response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 means that the highest probability tokens are always selected. In this case, responses for a given prompt are mostly deterministic, but a small amount of variation is still possible. If the model returns a response that’s too generic, too short, or the model gives a fallback response, try increasing the temperatureRange:
0 to 2Format: floatOptional. Configuration for thinking features. Thinking is a process where the model breaks down a complex task into smaller steps to generate a higher-quality response.
Optional. The token budget for the model’s thinking process. The model will make a best effort to stay within this budget.
Optional. The thinking level for the model.Possible values:
THINKING_LEVEL_UNSPECIFIED, LOW, MEDIUM, HIGH, MINIMAL, XHIGHTop-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model’s vocabulary. A top-K of 3 means that the next token is selected from among the 3 most probable tokens by using temperature.Range:
1 to …If specified, nucleus sampling is used.
Top-P changes how the model selects tokens for output. Tokens are selected from the most (see top-K) to least probable until the sum of their probabilities equals the top-P value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-P value is 0.5, then the model will select either A or B as the next token by using temperature and excludes C as a candidate.
Specify a lower value for less random responses and a higher value for more random responses.Range:
0 to 1Format: floatPer request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
Possible values:
HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENTPossible values:
OFF, BLOCK_NONE, BLOCK_LOW_AND_ABOVE, BLOCK_MEDIUM_AND_ABOVE, BLOCK_ONLY_HIGHInstructions for the model to steer it toward better performance. For example, “Answer as concisely as possible” or “Don’t use technical terms in your response”. The text strings count toward the token limit. The role field of systemInstruction is ignored and doesn’t affect the performance of the model. Note: Only text should be used in parts and content in each part should be in a separate paragraph.
A list of ordered parts that make up a single message. Different parts may have different IANA MIME types. For limits on the inputs, such as the maximum number of tokens or the number of images, see the model specifications on the Google models page.
The identity of the entity that creates the message. The following values are supported: user: This indicates that the message is sent by a real person, typically a user-generated message. model: This indicates that the message is generated by the model. The model value is used to insert messages from the model into the conversation during multi-turn conversations. For non-multi-turn conversations, this field can be left blank or unset.Possible values:
user, modelA piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. See Function calling.
If true, generated images will be uploaded to cloud storage and returned as signed URLs instead of inline base64 data. The URLs expire after 24 hours.
For video input, the start and end offset of the video in Duration format. For example, to specify a 10 second clip starting at 1:00, set “startOffset”: { “seconds”: 60 } and “endOffset”: { “seconds”: 70 }. The metadata should only be specified while the video data is presented in inlineData or fileData.
Signed fractions of a second at nanosecond resolution. Negative second values with fractions must still have non-negative nanos values.Range:
0 to 999999999Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive.Range:
-315576000000 to 315576000000Signed fractions of a second at nanosecond resolution. Negative second values with fractions must still have non-negative nanos values.Range:
0 to 999999999Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive.Range:
-315576000000 to 315576000000GET /v2/models/vertexai/gemini-nano-banana-2.1/openapi.json, the same document it validates a call against before the request reaches the provider.
Output
The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history and the latest request.
The media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values:
application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webmInline data in raw bytes. For gemini-2.0-flash-lite and gemini-2.0-flash, you can specify up to 3000 images by using inlineData.
The base64 encoding of the image, PDF, or video to include inline in the prompt. When including media inline, you must also specify the media type (mimeType) of the data. Size limit: 20MBFormat:
byteThe media type of the file specified in the data or fileUri fields. Acceptable values include the following. For gemini-2.0-flash-lite and gemini-2.0-flash, the maximum length of an audio file is 8.4 hours and the maximum length of a video file (without audio) is one hour. For more information, see Gemini audio and video requirements. Text files must be UTF-8 encoded. The contents of the text file count toward the token limit. There is no limit on image resolution.Possible values:
application/pdf, audio/mpeg, audio/mp3, audio/wav, image/png, image/jpeg, image/webp, text/plain, video/mov, video/mpeg, video/mp4, video/mpg, video/avi, video/wmv, video/mpegps, video/flv, image/heic, image/heif, audio/flac, video/webmHow the model reads this part’s video. Set “AGENTIC” to let the model decide which segments to inspect, instead of fixed-rate frame sampling. Omit for the default fixed-rate sampling. Supported on gemini-3.7-flash and newer Flash models.
Possible values:
HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENTThe probability that the content violates the specified safety categoryPossible values:
NEGLIGIBLE, LOW, MEDIUM, HIGH, UNKNOWNPossible values:
HARM_CATEGORY_SEXUALLY_EXPLICIT, HARM_CATEGORY_HATE_SPEECH, HARM_CATEGORY_HARASSMENT, HARM_CATEGORY_DANGEROUS_CONTENTThe probability that the content violates the specified safety categoryPossible values:
NEGLIGIBLE, LOW, MEDIUM, HIGH, UNKNOWNType of input or output content modality.Possible values:
MODALITY_UNSPECIFIED, TEXT, IMAGE, VIDEO, AUDIO, DOCUMENTNumber of tokens in the request. When cachedContent is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
Type of input or output content modality.Possible values:
MODALITY_UNSPECIFIED, TEXT, IMAGE, VIDEO, AUDIO, DOCUMENTType of input or output content modality.Possible values:
MODALITY_UNSPECIFIED, TEXT, IMAGE, VIDEO, AUDIO, DOCUMENTExamples
Input
Output
Before you ship
The SDKs create anIdempotency-Key and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.
When a request fails, Router sends an X-Comfy-Error-Type response header explaining why. A 422 means Router rejected the input before calling the provider, and a 413 means the request body was larger than Router accepts. Download generated assets promptly because result URLs can expire.
Any size limit named in a field description above is the provider’s own bound on that field, quoted from the provider’s specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see request body size.
This page documents one partner model called through Comfy Router. The same comfy-sdk / @comfyorg/sdk package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: Comfy(api_key=...) / new Comfy({ apiKey }), with client.workflows, client.assets and client.jobs. See Comfy SDKs.
Headers
Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
Using the Router API
Model discovery, validation errors, retries, and billing.
Limitations
What Router does not do today, and what to use instead.