/v1/search — Retired

Quick fix — copy & paste

Choose your language. The "before" block matches the deprecated call; the "after" block is the drop-in replacement.

# OpenAI: /v1/search (deprecated)
model = "/v1/search"

# Replacement
model = "View transition guide"

// OpenAI: /v1/search (deprecated)
const model = "/v1/search";

// Replacement
const model = "View transition guide";

"model": "/v1/search"

"model": "View transition guide"

This migration was generated automatically from the model rename. If your code does more than swap a model id, double-check request/response shapes against the official OpenAI migration guide.

Error messages

Seeing one of these? You're in the right place.

• model_not_found: /v1/search
• The model `/v1/search` has been deprecated
• The model `/v1/search` does not exist or you do not have access to it

Replacement options

• View transition guide Compare token cost →

Other OpenAI deprecations

• dall-e-2 2026-05-12 · 4d
• dall-e-3 2026-05-12 · 4d
• computer-use-preview 2026-07-23 · 76d
• gpt-4o-audio-preview-2024-12-17 2026-07-23 · 76d
• gpt-4o-mini-audio-preview-2024-12-17 2026-07-23 · 76d

What this means for your code

/v1/search is a search-grounded model that calls a web index as part of its response. Search-enabled models have separate pricing for the search call itself. Replacements may change the search backend, citation format, or maximum number of sources per response.

/v1/search was retired by OpenAI on 2022-12-03. API calls now return an error and the model is no longer accessible. New code should use View transition guide; legacy code that still references this model id needs to be updated immediately.

Find every call in your codebase

Before you change anything, locate every place the deprecated model id is referenced. Search source files, environment files, feature flags, and config repos. Use these commands from your project root:

grep -rn '"/v1/search"' --include="*.py" .

grep -rn '"/v1/search"' --include="*.{js,ts,tsx,jsx}" .

grep -rn "/v1/search" .

Migration checklist

Steps in order. Skip any that don't apply, but read the whole list — for search models, the non-obvious steps are usually the ones that break in production.

1. 1. Update the model id and search tool configuration
2. 2. Verify citation format — some models return inline markdown, others structured arrays
3. 3. Re-test queries that depend on freshness or specific source domains
4. 4. Check rate limits — search calls are usually rate-limited separately from token throughput
5. 5. Recompute cost per response including the search-call surcharge