OpenAI Assistants API · sunset August 26, 2026
An OpenAI Assistants API alternative you can migrate to in minutes
OpenAI is retiring /v1/assistants and /v1/threads. Moving to the Responses API means rewriting how your agent holds state and runs its tools. Moving to Glytos means connecting your key and picking your assistants off a list.
Your OpenAI key is used for the import request and never stored.
Last updated
The deadline
What is actually being turned off
Worth being precise about, because the announcement is easy to read as bigger than it is.
Source: OpenAI deprecations
Your options
There are three honest ways out, and one of them is not us
You are going to rebuild something either way. It is worth knowing which rebuild you are choosing.
Move to the Responses API
Stay entirely inside OpenAI. You rewrite state handling, tool loops and streaming against the new object model, and you keep owning the orchestration, the retries and the observability yourself.
Text-only agents already woven deeply into OpenAI, with engineering time to spend on the migration.
Build it yourself
A framework or your own code. You own threads, retries, tool execution, logging and the billing arithmetic. Nothing is hidden from you, and nothing is done for you either.
Agents that are one component inside a larger system you already run and monitor.
Move to Glytos
Your assistant becomes a Glytos agent with the same instructions, the same model and the same JSON schema. Keep your OpenAI key and its token cost stays between you and OpenAI. What you gain is a platform that also runs voice and phone, and a cost breakdown for every conversation.
Agents where the assistant is the product, and where text was only ever half of what you wanted.
Parity
What comes across, and what needs you
The honest version, including the rows that are not automatic. The importer tells you the same thing in the app, so nothing here is a surprise you find later.
| In your Assistant | In Glytos | Status |
|---|---|---|
| Instructions | Agent system prompt | Imported |
| Model, temperature, top_p | Agent model settingsImported as they were, then editable. The model becomes a dropdown rather than a fixture of the assistant. | Imported |
| response_format | Structured outputsjson_object and json_schema both carry over. A strict schema is adjusted automatically to the form OpenAI requires, so it does not start rejecting requests. | Imported |
| Function tools | HTTP toolsName, description and JSON schema come across. The endpoint behind a tool is not something an Assistant stores, so you set the URL and auth once per tool. | Imported |
| Strict function calling | Strict tools | Built in |
| File Search | Knowledge base and vector storesYour files stay on OpenAI, so re-upload them here. Retrieval is hybrid: vector similarity plus full-text search over the same documents. | Manual step |
| Code Interpreter | Not carried overThe importer does not bring Code Interpreter tools across. Get in touch if an assistant of yours depends on running code. | Not imported |
| Streaming | Server-sent token streaming | Built in |
| Vision | Image input | Built in |
| Threads | SessionsEach one keeps its transcript, its event timeline and its cost, and can be replayed against a newer version of the agent. | Built in |
| Files attached to a run | Conversation files | Built in |
| No equivalent | Voice, phone numbers, outbound campaignsNothing an Assistant could do. Voice agents are their own kind here, built from the same prompt and running on the same engine, on a number you connect from your own carrier. | New here |
Once it lands
Chat is its own kind of agent here, not a bolt-on
Glytos is known for voice, so this is worth showing rather than claiming. A chat agent is a first-class type with its own builder, and your instructions arrive in it verbatim - the same prompt, the same model settings, the same JSON schema, ready to edit.
Migration
Four steps, and you can stop after the third
Bringing the assistants across and finishing their configuration are separate jobs. Do the first one now while the API is still up, and take your time over the second.
- 1
Connect your OpenAI key
Paste the key you already use. It authorises the one request that lists your assistants, and is discarded afterwards - it is never written to our database.
- 2
Pick the assistants to bring
Everything on your account is listed by name. Choose one or several; each becomes its own Glytos agent.
- 3
Read the import report
It names exactly what came across and what is still waiting on you: which tools need an endpoint, and which assistants had files that must be re-uploaded.
- 4
Finish the tools and ship
Point each imported tool at its endpoint, try the agent in the playground, then put it live on your site or behind the API.
After the move
What it gets once it is a Glytos agent
Parity is the floor. This is the part that makes the migration worth doing rather than merely necessary.
Voice, without a second platform
Chat and voice run on the same engine here. Build a voice agent from the prompt you just imported, give it a number from your own carrier or a SIP trunk you bring directly, and it takes calls - same model, same tools, same session logs.
Cost you can see per conversation
Every session shows what it cost, split into model tokens, speech and platform fee. Not a number you reconcile at the end of the month - a number attached to the conversation that caused it.
Not tied to one vendor's model list
Your assistant arrives on the model it was already using, and after that the model is a dropdown - OpenAI, Anthropic, Google, xAI and several more. Moving an agent between them is a setting, not a rewrite: the prompt, the tools and the response schema all come with it.
The whole decision trail
Transcript, tool calls, retrieval hits, routing decisions and latency on one timeline per session. When an agent answers oddly, the reason is on the screen rather than in a reproduction attempt.
Development, staging, production
Three environments per organisation with promotion between them, so you can rebuild a prompt without touching the agent your customers are talking to right now.
An exit that actually works
Export any agent as portable JSON with no secrets in it. The importer that brought you in will take you back out. A migration page that did not say this would be worth less.
Pricing
Your model bill does not change
Bring the OpenAI key you already use and your token cost stays between you and OpenAI, exactly as it is now - and the same holds for any other provider you bring a key for. Glytos charges a tenth of a cent for each reply that actually ran the model; a canned message or an empty response is never billed. A thousand replies is a dollar.
No key of your own? We can run it on ours at provider list price plus a transparent margin. Voice, if you add it, is metered separately. How pricing works
Questions
What people ask before moving
When exactly does the OpenAI Assistants API shut down?
August 26, 2026. After that, requests to /v1/assistants, /v1/threads and the endpoints around them stop responding. OpenAI announced the deprecation a year in advance and publishes the date on its deprecations page.
Can I bring my existing assistants across?
Yes. Connect your OpenAI key and choose them from a list. Instructions, model, temperature, top_p, the JSON response format and every function tool schema come across, and each assistant becomes its own agent.
Is my OpenAI API key stored anywhere?
No. It authorises the request that reads your assistants and is discarded when that request finishes. If you later want an agent to run on your own key, that is a separate, deliberate step where the key is encrypted at rest.
What happens to my File Search files?
They stay on OpenAI and are not transferred. Re-upload them into a Glytos knowledge base or vector store; the import report tells you which agents are waiting on it. Retrieval here is hybrid - vector similarity merged with full-text search.
Do my function tools keep working?
Their names, descriptions and JSON schemas are imported and the agent knows how to call them. The endpoint behind each tool is not stored on an Assistant, so it is the one thing you supply: a URL, and auth if it needs it.
Can I keep using OpenAI models, or move to another provider?
Both. The import keeps the model your assistant was already on, and with your own key its token cost never appears on your Glytos bill. Changing it afterwards is one setting. Wired in today: OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral, Perplexity, Together and MiniMax, with around seventy models between them. The prompt, tools and response schema carry over unchanged when you switch.
What replaces threads?
Sessions. Each one holds its transcript, its event timeline and its cost, and a real recorded conversation can be replayed against a newer version of the agent to see whether a change helped.
Can I leave later?
Yes. Export any agent as portable JSON containing no secrets, and import it elsewhere or keep it as a backup. Being easy to leave is the point of a platform you are being asked to move to.
What is the best replacement for the OpenAI Assistants API?
It depends on what the assistant is for. If it is text-only and tied deeply to OpenAI, the Responses API is the official replacement and a reasonable one. If the assistant is the product - if you want it answering on a phone line, costed per conversation, and observable turn by turn - a hosted platform is the better replacement, and Glytos imports your assistants rather than making you rewrite them.
Do I have to move to the Responses API?
No. It is OpenAI's replacement for its own orchestration layer, not a requirement for using OpenAI models. You can keep calling GPT models with your own key from anywhere, including from a Glytos agent, without adopting the Responses API at all.
Bring your assistants over before OpenAI's API closes
Connect your key, pick the assistants, and read the report. It takes minutes, and everything after that can wait.
OpenAI removes its Assistants API on August 26, 2026. Glytos agents are unaffected.