DayuanJiang/next-ai-draw-io · error · Error

Model ID is required when using custom AI provider. Please s

Error message

Model ID is required when using custom AI provider. Please specify a model in Settings.

What it means

When the client supplies its own provider override (Settings custom AI config) but no modelId and no AI_MODEL env fallback exists, getAIModel throws asking for a model in Settings.

Source

Thrown at lib/ai-providers.ts:746

                `Please provide your own API key in Settings.`,
        )
    }

    // Check if client is providing their own provider override
    const isClientOverride = !!(
        overrides?.provider &&
        (overrides?.apiKey ||
            (overrides?.provider === "vertexai" && overrides?.vertexApiKey))
    )

    // Use client override if provided, otherwise fall back to env vars.
    // AI_MODEL may be comma-separated (multi-model fallback); pick the first.
    const envModel = process.env.AI_MODEL?.split(",")[0]?.trim() || undefined
    const modelId = overrides?.modelId || envModel

    if (!modelId) {
        if (isClientOverride) {
            throw new Error(
                `Model ID is required when using custom AI provider. Please specify a model in Settings.`,
            )
        }
        throw new Error(
            `AI_MODEL environment variable is required. Example: AI_MODEL=claude-sonnet-4-5`,
        )
    }

    // Determine provider: client override > explicit config > auto-detect > error
    let provider: ProviderName
    if (overrides?.provider) {
        // Validate client-provided provider
        if (
            !ALLOWED_CLIENT_PROVIDERS.includes(
                overrides.provider as ProviderName,
            )
        ) {
            throw new Error(

View on GitHub (pinned to 155ef4f7ac)

Solutions

1. Enter a model ID in Settings (e.g. claude-sonnet-4-5) for the custom provider
2. Alternatively set AI_MODEL in .env.local as a server-side fallback
3. Ensure the model name matches what the chosen provider exposes

Example fix

// before
overrides = { provider: 'anthropic' } // no modelId

// after
overrides = { provider: 'anthropic', modelId: 'claude-sonnet-4-5' }

const hasModel = !!overrides?.modelId || !!process.env.AI_MODEL
if (!hasModel) disableSubmit('Model ID required')

const hasModelId = (o?: { modelId?: string }): boolean =>
  !!o?.modelId || !!process.env.AI_MODEL

try { getAIModel(overrides) } catch (e) { if ((e as Error).message.includes('Model ID is required')) focusModelFieldInSettings() }

When it happens

Trigger: User configures a custom provider/baseUrl in the UI but leaves the model field empty while AI_MODEL is unset in the environment.

Common situations: Setting up BYO-provider in Settings and forgetting the model name, or AI_MODEL removed from .env.local after switching to UI config.

Related errors

• ModelScope API error (${response.status}): ${errorText}
• Unexpected response format: ${contentType}
• Invalid preset name
• ${varName} must be a valid integer, got: ${value}
• ${varName} must be >= ${min}, got: ${parsed}

AI-assisted analysis of DayuanJiang/next-ai-draw-io@155ef4f7ac (2026-08-27). Data as JSON: /api/errors/4ab7b73b2109dcc4. Report an issue: GitHub.