Ollama /v1/systemone errors: 400, 404, 413 explained

curl to /v1/systemone returns 400, 404 or 413 instead of answers

作者 Jakub Rusinowski

错误信息

{"error": "request body must not exceed 64 KiB without images"}

1. 1

   Upgrade Ollama and restart the server

   You need 0.35.0 or later (clef and clef-flash need 0.35.1). On macOS and Windows, quit Ollama from the menu bar or system tray before installing the new version — otherwise the old server keeps answering on port 11434 and the new endpoint seems missing. On Linux, the commands below upgrade it and restart the service.

   bash复制

   ollama -v
   
   # Linux upgrade
   curl -fsSL https://ollama.com/install.sh | sh
   sudo systemctl restart ollama

   生效了吗？ollama -v shows 0.35.0 or later and the same request no longer returns 404. If ollama -v warns that the client and server versions differ, an old server is still running — quit it fully and start Ollama again.
2. 2

   Pull the model

   Model names must match exactly — tev1:0.8b, not tev1-0.8b or tev1:0.8B.

   bash复制

   ollama pull nimble
   ollama list

   生效了吗？ollama list shows the model, and the request returns answers.
3. 3

   Use a System One model

   The endpoint accepts only local models trained for System One, packaged as GGUF with a scoring-capable runner. It rejects chat models (llama3, qwen3, gemma4 …), which weren't trained for this scoring; anything with a :cloud tag, because cloud models are refused on this endpoint; and MLX or Safetensors models imported on a Mac. Switch "model" to nimble, tev1, tev1:0.8b, clef or clef-flash. Ollama also lists MLX tags for Clef, but its System One reference says MLX models are not supported on /v1/systemone, so use the default tag. For open models beyond these, use the model's own server.

   生效了吗？The same request with "model": "tev1" returns answers.
4. 4

   Stay inside the schema limits

   The limits are: 1 to 64 questions per request; a choice criteria object with 2 to 26 keys, none blank; a score criteria array of 2 to 26 strings, lowest first; an optional noul criteria with only the keys "false" and "true"; a type of exactly choice, noul or score, lowercase; and a non-empty state and instructions (a string, or a JSON object or array). A choice with 40 labels needs splitting: first route to a group, then choose within the group, in two requests — or use a runtime that supports up to 255 options (Decider, JevK5).

   生效了吗？Remove questions or options until the request succeeds, then add back one at a time.
5. 5

   Shorten the state最常见的修复方法

   Every question's rendered prompt must fit the loaded context with 2 tokens to spare. Nimble's must fit 8,192 tokens; Tev1's card recommends keeping inputs to roughly 2,000 tokens. First, send only the part of the document the question is about — extract the relevant section in code, which also improves accuracy because irrelevant detail distracts decision models. Second, split one long request into several with shorter states. Third, check usage.input_tokens on a request that works: it is the total across all questions, so divide by your question count to see the size of each prompt.

   生效了吗？The request succeeds and usage.input_tokens ÷ the number of questions is comfortably under the model’s limit.

   检查哪些模型适配你的硬件check that the decision model fits, then build a valid request打开显存检查器 →
6. 6

   PowerShell builds a different JSON than you think

   Two traps. First, in Windows PowerShell 5.1, curl is an alias for Invoke-WebRequest, which doesn't understand curl's flags — call curl.exe explicitly. Second, ConvertTo-Json stops at a depth of 2 by default and turns anything deeper into a type name. Your criteria object sits three levels below the root, so it is silently replaced; PowerShell 7 at least warns that the resulting JSON is truncated as serialization has exceeded the set depth of 2. Always pass -Depth 8, and use [ordered]@{} so options keep their order.

   PowerShell复制

   $body | ConvertTo-Json -Depth 8 | Set-Content -Encoding utf8 request.json
   Get-Content request.json   # inspect before sending

   生效了吗？request.json shows your full criteria objects, not System.Collections.Hashtable.
7. 7

   Keep the body under 64 KiB

   Large states are usually whole documents or long chat histories. Trim them in code, or split the work across requests. Remember that 64 KiB is the whole JSON body, including instructions and option descriptions. A request that carries images may be up to 32 MiB; if an image request is rejected, see Ollama /v1/systemone image errors.

   生效了吗？The file is under 65,536 bytes. In PowerShell the equivalent check is (Get-Item request.json).Length.

   bash复制

   wc -c request.json

8. 8

   Allow your web page’s origin

   A browser calling http://localhost:11434 from a page on another origin gets a console message saying the request "has been blocked by CORS policy". Ollama allows extra browser origins through the OLLAMA_ORIGINS environment variable, set on the server, then restart Ollama. How to set server environment variables differs by OS — on Linux it goes in the systemd unit, not your shell. Allow only the origins you need, not *.

   生效了吗？The browser request succeeds and the console shows no CORS error.