cheaper model routing fails error fallback uses expensive model bug

Not specified by the original author.

TL;DR

Use the count to pick the smallest model whose context window fits the input plus your output budget, and to estimate cost. Use exponential backoff with jitter for retries; the SDKs retry automatically on some errors, so know which errors yours retries and which it does not. Run your eval suite with-arm (new routing) and without-arm (old routing) before rolling out, and watch the quality-sensitive criteria, not just the average.

When to use

You are seeing this: Read the current models overview. Use this skill when you run into "Multi-model routing with fallbacks and 429 handling for Claude".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

No specific versions are mentioned in the source material, so treat the fix as generally applicable and check the examples against whatever you have installed.

Build a router that survives lineup changes and capacity hiccups.

1. Read the current models overview. Start from the models overview page, not your memory: it lists the current lineup, which model to default to, and which one is for demanding reasoning and long-horizon agentic work. All current models support text and image input, text output, and tool use, so route on capability needs (context window, reasoning depth, cost) rather than feature support.
2. Token-count before routing. Call the token counting endpoint on the request first. Use the count to pick the smallest model whose context window fits the input plus your output budget, and to estimate cost. Send images and PDFs as base64 for counting; url and file sources are rejected.
3. Define the fallback chain explicitly. Order: primary model, then a cheaper or faster model for retry, then a degraded mode (cached answer, queue for later, or a clear error). Never fall back silently to a weaker model on quality-critical tasks without logging it: silent downgrades are how quality rots.
4. Handle 429s and overloads, not just errors. On ratelimiterror, read the retry-after header and the anthropic-ratelimit-requests-remaining and reset headers to decide whether to wait or fail over. Use exponential backoff with jitter for retries; the SDKs retry automatically on some errors, so know which errors yours retries and which it does not.
5. Know your tier. Start, Build, and Scale tiers carry monthly spend caps; when usage is paused, requests return 429 with no retry-after and retries fail until access resumes. A fallback chain cannot fix a paused org: surface that state to the user instead of looping.
6. Re-run evals on every routing change. Changing the model for a task class is a behavior change. Run your eval suite with-arm (new routing) and without-arm (old routing) before rolling out, and watch the quality-sensitive criteria, not just the average.

Claims verified against Anthropic's official docs (platform.claude.com) on 2026-09-26. Evidence URLs in public_references.

Not specified by the original author.

TL;DR: The SDK gives you three routing layers; use the cheapest one that fits. You will outgrow a single hardcoded model. Layer 1: AI Gateway string ids. model: 'openai/gpt-5' or 'anthropic/claude-opus-4-6'.

You will outgrow a single hardcoded model. The SDK gives you three routing layers; use the cheapest one that fits.

Layer 1: AI Gateway string ids. model: 'openai/gpt-5' or 'anthropic/claude-opus-4-6'. One key (AIGATEWAYAPI_KEY), hundreds of models, zero factories. Best for trying models and simple switching.

Layer 2: provider factories. import { openai } from '@ai-sdk/openai'; model: openai('gpt-5'). Best when you need provider options (custom baseURL, organization, providerOptions).

Layer 3: customProvider for named routing with fallbacks.

import { customProvider } from 'ai'; import { openai } from '@ai-sdk/openai'; import { anthropic } from '@ai-sdk/anthropic';

const registry = customProvider({ languageModels: { 'fast': openai('gpt-5-mini'), 'smart': anthropic('claude-opus-4-6'), }, fallbackProvider: openai, // used when a name does not resolve });

const result = await generateText({ model: registry.languageModel('fast'), prompt: 'Hi' });

Rules:

1. Keep routing names stable ('fast', 'smart', 'cheap') and change the backing models in one place. Prompts and evals reference names, not model ids.
2. Fallbacks need compatible capabilities. Falling back from a tool-using model to one without tool support breaks the turn. Gate fallbacks by feature, not just availability.
3. The v7 codemod renamed experimental_customProvider to customProvider. Old snippets with the prefix still work only if you never upgraded.
4. Log which backing model served each request (messageMetadata or telemetry functionId plus model id). Debugging "the model got worse" requires knowing which model answered.
5. For cost control, route by task: cheap model for classification and drafts, strong model for final answers. The registry makes this a config change.
6. Validate model ids at startup in production. A retired id should fail deploy-time checks, not the first user request (NoSuchModelError at 2am).

When to use

You hit exactly this: Multi-provider routing: customProvider, gateway, and fallbacks in Multi-provider routing.

When not to use

A different error, or the same symptom in a different tool. This page only covers the failure above.

Compatibility

Multi-provider routing (versions mentioned here: v7).

Edge cases

• Best when you need provider options (custom baseURL, organization, providerOptions).
• For cost control, route by task: cheap model for classification and drafts, strong model for final answers.

Verified against the live AI SDK docs 2026-09-26. The introduction shows gateway string ids; the providers-and-models page covers provider packages; the v7 migration codemod table documents experimental_customProvider to customProvider. The message-metadata guide shows attaching model info per message.

Not specified by the original author.

Runway Model Router 'no eligible model': raise max credits or enable more models

TL;DR

[Official Runway API docs (troubleshooting)]: A Model Router 'no eligible model' error means no model satisfies the configuration constraints plus the request together, and the error identifies which constraint(s) emptied the pool. The typical culprit is max credits per generation combined with the requested duration leaving nothing eligible. Fix it in the Developer Portal by adjusting the router configuration: enable additional models or raise the max credits per generation (see Configuring a Model Router).

Use this when you run into the situation in the title.

When not to use this skill: unrelated tasks. It covers only the procedure above.

Compatibility

The steps above apply to the commands named in them. This skill does not pin a version, so if a flag looks different on your machine, check your installed version's docs first.

Details

Context: Official docs (Runway API Troubleshooting Guide): documents why Model Router requests fail with a 'no eligible model' error. The error names which configuration constraints emptied the eligible pool, commonly the max-credits-per-generation and requested duration combination.

Official docs (Runway API Troubleshooting Guide): documents why Model Router requests fail with a 'no eligible model' error. The error names which configuration constraints emptied the eligible pool, commonly the max-credits-per-generation and requested duration combination. Resolved: [Official Runway API docs (troubleshooting)]: A Model Router 'no eligible model' error means no model satisfies the configuration constraints plus the request together, and the error identifies which constraint(s) emptied the pool. The typical culprit is max credits per generation combined with the requested duration leaving nothing eligible. Fix it in the Developer Portal by adjusting the router configuration: enable additional models or raise the max credits per generation (see Configuring a Model Router).