An AI API returns "Unknown model": where do I find the right model name?
Unknown model '...' error (HTTP 400) means the model name in your request isn't a callable model on the Wiozen API. The error text also lists the valid names after Available models: .... The same list comes from GET https://api.wiozen.com/v1/models, which needs no key. Write the name exactly as listed. Case matters, and deepseek-v4.1 isn't recognised; the correct name is deepseek-v4.1-flash.What does the error look like?
On /v1/chat/completions and the other OpenAI-format endpoints the body looks like this:
{"error":{"message":"Unknown model 'deepseek-v4.1'. Available models: deepseek-v4.1-flash, flux-2-klein-4b, gemini-3.1-flash-image, ...","type":"invalid_request_error"}}On /v1/messages the same message comes in Anthropic format:
{"type":"error","error":{"type":"invalid_request_error","message":"Unknown model 'deepseek-v4.1'. Available models: ..."}}The first part of the message is the first 80 characters of the name you sent. The list after it contains every name that can be called right now, in alphabetical order; image generation and speech-to-text models are in it alongside the chat models.
Where do I find the right model name?
There are three places. The first is the error itself: the Available models list can be copied straight out. The second is GET /v1/models. It needs no key, returns only active models that can be called, and the id field of each entry is the model name:
curl https://api.wiozen.com/v1/models
import requests
models = requests.get("https://api.wiozen.com/v1/models", timeout=30).json()["data"]
print([m["id"] for m in models])The third is the Models page, which shows price, context window and the last hour's status next to each name. The /v1/models response has no price, capabilities or model type.
As of 12 November 2026 the list has nine names. For chat: wiozen-coder, deepseek-v4.1-flash and gemini-3.8-flash-high. For image generation: gemini-3.1-flash-image, gpt-image-2.5, gpt-image-2.6-flare, gpt-image-2.6-sunburst and flux-2-klein-4b. For speech-to-text: whisper-large-v3. What each one is for is covered in the model choice guide.
I think the name is right, but I still get the error
Common causes:
- The name is incomplete or has extra parts.
deepseek-v4.1,deepseekandwiozen-coder-1aren't recognised; the name has to match the list in full. - Letter case.
DeepSeek-V4.1-Flashanddeepseek-v4.1-flasharen't treated as the same model. - The tool's own default name. Editor extensions and chat interfaces often write their own default into the model field. A connection test can pass and the first real request then fails with this error; change the model field in the tool by hand to a name from the list.
- The model was switched off. A model removed from the catalog also leaves the list, and its name now gives this error. Instead of hard-coding a name you can read it from
/v1/models. - The model belongs to a different endpoint. See below.
The most confusing example of the last item is whisper-large-v3. The name sits in the /v1/models list, but /v1/chat/completions answers Unknown model, because the speech-to-text model only works on /v1/audio/transcriptions, and it is priced per minute (speech-to-text guide). The reverse holds too: give the transcription endpoint a chat model's name and you get Unknown model again. The image endpoint uses its own message: The model '...' does not exist or is not an image model.
Is this error charged?
No. On the chat endpoint the model name is checked before any balance is set aside, so after a 400 your balance is unchanged. If the error is 401 or 429 instead of 400 the problem is something else: 401 is about the key (401 guide), 429 about balance or limits (429 guide).
Frequently asked questions
What does the Unknown model error mean?
Available models list.Can I get the model list without a key?
GET https://api.wiozen.com/v1/models needs no key. If you do add a key to the request it is checked, and an invalid one gets a 401 instead of the list.Is the model name case sensitive?
deepseek-v4.1-flash works, DeepSeek-V4.1-Flash doesn't.whisper-large-v3 is in the list, so why does the chat endpoint reject it?
/v1/audio/transcriptions. The chat endpoint doesn't route it, but the /v1/models list shows every callable model regardless of type.Does the model list change?
Where to put the model name when you connect a tool is in the OpenAI-compatible connection guide; prices are on the Models page.
Create your accountMore guides: How can you use an AI API from Turkey without a credit card? · How do you connect an OpenAI-compatible API to a tool you already use? · How do you calculate the cost of an AI API? · What should I do if my AI API key has leaked? · How do you generate images with an AI API, and what does one image cost? · How much does a speech-to-text API cost, and how is it billed per minute? · Why does my AI API return a 429 error, and how do I fix it? · Why do long AI API requests time out: streaming or non-streaming? · Anthropic Messages API or OpenAI Chat Completions: which one should I use? · What is a context window, and what is a 1 million token context good for? · Which AI model should I choose: deciding by price, context and quality · Why does a reasoning model return an empty answer, and why are thinking tokens charged? · Why is my API balance running out faster than expected? Tracking spend request by request · How do you convert a web page to Markdown to feed it to an AI model? · How do you get AI to write and publish articles in WordPress automatically? · How do you find blog topics from RSS feeds and Google Trends? · Does AI-written content show up on Google and in AI answers? · How do you get internal links into AI-written WordPress articles? · How do you get AI to generate a different featured image for every WordPress post? · How do you write a content brief when an AI writes your blog posts? · What should you watch for when an AI writes recipes for your food blog? · How do you fix errors when connecting a WordPress plugin to your AI API account? · Why does my AI article bot stop halfway in WordPress? "Run is stuck" and LiteSpeed · Why are my scheduled WordPress posts late? WP-Cron and a real server cron · How do I get an AI article bot to write blog posts in English or another language? · What does "Content Bot cannot generate articles" mean? Reading the bot's log · If I delete the WordPress AI article plugin, are the articles it wrote deleted? · How do you do function calling (tool use) with an AI API? · How do I check my AI API balance from code and get a low-balance alert? · Can I use the same AI article plugin on several WordPress sites with one account and one balance? · How do you run Claude Code with a different API address and key? · Do AI-written WordPress posts get an FAQ section and FAQ structured data (schema)? · My AI API returns "401 Invalid API key": why isn't my key accepted? · Is there a free trial for an AI API? How much credit Wiozen API gives and what it covers · Claude Haiku vs Claude Sonnet via API: price per million tokens and when to use each · How much does a Claude Code session cost with an API key? · Can you use Claude Code without a subscription and pay only for what you use? · How much does prompt caching cut API costs? Cache read and cache write prices · When is the DeepSeek API cheaper? Peak and off-peak hour pricing · Which model should you use in Cline, Cursor, OpenCode and Aider? · How much does an AI-written WordPress post cost? Text, image and research · Why didn't the AI bot publish its post, and why is it stuck in drafts? · How many AI-written posts a day should you publish, and how do you set the frequency? · Who should be the author of AI-written WordPress posts? · What to watch for when AI writes posts for a loan, crypto or energy website · How do I add web search to my AI app, and what does a search cost?