n8n-io/n8n · error · Error

Invalid response format from Gemini API

Error message

Invalid response format from Gemini API

What it means

Thrown by the GoogleGemini image edit operation when the API response from /v1beta/{model}:generateContent fails the isGenerateContentResponse type guard. This guard checks that the response is an object with a 'candidates' array where each candidate has a 'content' object with a 'parts' array. A response that doesn't match this shape is considered malformed. Note: this is a plain Error, not a NodeOperationError.

Source

Thrown at packages/@n8n/nodes-langchain/nodes/vendors/GoogleGemini/actions/image/edit.operation.ts:207

			{
				role: 'user',
				parts: [...fileParts, { text: prompt }],
			},
		],
		generationConfig,
	};

	const response: unknown = await apiRequest.call(
		this,
		'POST',
		`/v1beta/${model}:generateContent`,
		{
			body,
		},
	);

	if (!isGenerateContentResponse(response)) {
		throw new Error('Invalid response format from Gemini API');
	}

	const promises = response.candidates.map(async (candidate) => {
		const imagePart = candidate.content.parts.find((part) => 'inlineData' in part);

		// Check if imagePart exists and has inlineData with actual data
		if (!imagePart?.inlineData?.data) {
			throw new Error('No image data returned from Gemini API');
		}

		const mimeType = imagePart.inlineData.mimeType;
		const fileName = getFilenameFromMimeType(mimeType, 'image', 'png');
		const bufferOut = Buffer.from(imagePart.inlineData.data, 'base64');
		const binaryOut = await this.helpers.prepareBinaryData(bufferOut, fileName, mimeType);
		return {
			binary: {
				[outputKey]: binaryOut,
			},

View on GitHub (pinned to 5ac6606e81)

Solutions

1. Inspect the actual API response body — the error fires because it doesn't match the expected shape. Log or debug the raw response to see what the API returned.
2. Verify the API key is valid and has Gemini API access.
3. Confirm the model ID is correct and supports image generation (e.g. models/gemini-2.5-flash-image-preview).
4. Check for safety filter blocks — the response may contain promptFeedback with safety ratings instead of candidates. Adjust the prompt to avoid triggering filters.
5. Check the Google AI status page for service incidents.

function isGenerateContentResponse(response: unknown): response is {
  candidates: Array<{ content: { parts: Array<Record<string, unknown>> } }>;
} {
  if (typeof response !== 'object' || response === null) return false;
  const obj = response as Record<string, unknown>;
  if (!('candidates' in obj) || !Array.isArray(obj.candidates)) return false;
  return obj.candidates.every((c: unknown) =>
    typeof c === 'object' && c !== null &&
    'content' in (c as object) &&
    typeof (c as Record<string, unknown>).content === 'object' &&
    'parts' in ((c as Record<string, unknown>).content as object) &&
    Array.isArray(((c as Record<string, unknown>).content as Record<string, unknown>).parts)
  );
}

try {
  const response = await apiRequest.call(this, 'POST', `/v1beta/${model}:generateContent`, { body });
  if (!isGenerateContentResponse(response)) {
    // log the raw response for debugging and surface a user-friendly error
    console.error('Unexpected Gemini response:', JSON.stringify(response));
    throw new Error('Gemini API returned an unexpected response format. Check API key, model ID, and safety settings.');
  }
} catch (error) {
  // handle or rethrow
  throw error;
}

When it happens

Trigger: The Gemini API returns a response without a 'candidates' array, or candidates exist but lack 'content.parts'. This can happen when the API returns an error object instead of a generation result (e.g. quota error, invalid API key, model unavailable, safety block with no candidates), when the API version changes the response schema, or when a network proxy mangles the response body.

Common situations: API key invalid or expired (returns error envelope, not candidates); model name incorrect or deprecated; safety filter blocks the request and returns promptFeedback without candidates; API rate limit returns error body; Gemini API version change altering response structure; proxy/gateway stripping or modifying response fields.

Related errors

• Invalid images parameter format
• A non-empty prompt is required.
• No image data returned from Gemini API
• Expected Supabase credentials host to be a string
• A non-empty prompt is required.

AI-assisted analysis of n8n-io/n8n@5ac6606e81 (2026-08-12). Data as JSON: /api/errors/dccbf6b5d8dda9e8. Report an issue: GitHub.