vercel/ai · error · TooManyEmbeddingValuesForCallError

Too many embedding values for a single call. Model "${modelI

Error message

Too many embedding values for a single call. Model "${modelId}" can only embed up to ${maxEmbeddingsPerCall} values per call.

What it means

Error "Too many embedding values for a single call. Model "${modelId}" can only embed up to ${maxEmbeddingsPerCall} values per call." thrown in vercel/ai.

Source

Thrown at packages/google-vertex/src/google-vertex-embedding-model.ts:95

      googleOptions = await parseProviderOptions({
        provider: 'vertex',
        providerOptions,
        schema: googleVertexEmbeddingModelOptions,
      });
    }

    if (googleOptions == null) {
      googleOptions = await parseProviderOptions({
        provider: 'google',
        providerOptions,
        schema: googleVertexEmbeddingModelOptions,
      });
    }

    googleOptions = googleOptions ?? {};

    if (values.length > this.maxEmbeddingsPerCall) {
      throw new TooManyEmbeddingValuesForCallError({
        provider: this.provider,
        modelId: this.modelId,
        maxEmbeddingsPerCall: this.maxEmbeddingsPerCall,
        values,
      });
    }

    const mergedHeaders = combineHeaders(
      this.config.headers ? await resolve(this.config.headers) : undefined,
      headers,
    );

    if (usesEmbedContentEndpoint(this.modelId)) {
      const {
        responseHeaders,
        value: response,
        rawValue,
      } = await postJsonToApi({

View on GitHub (pinned to 69428b1f8b)

When it happens

Trigger: Thrown at packages/google-vertex/src/google-vertex-embedding-model.ts:95 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of vercel/ai@69428b1f8b (2026-08-30). Data as JSON: /api/errors/334a8ebd7b96340a. Report an issue: GitHub.