github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12370] Cloud model 400 Bad Request: raw mode does not support template, system, or context #70277

New Issue
Closed
opened 2026-05-04 20:55:37 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-04 20:55:37 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Sep 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12370

Originally assigned to: @drifkin on GitHub.

What is the issue?

The cloud model of Ollama, when set with raw: true, returns a 400 Bad Request error: "raw mode does not support template, system, or context." Additionally, setting template: "{{ .Prompt }}" seems ineffective, as it still cannot seamlessly complete text and gets interrupted. The same parameters work fine when called on a local model.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @ghost on GitHub (Sep 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12370 Originally assigned to: @drifkin on GitHub. ### What is the issue? The cloud model of Ollama, when set with `raw: true`, returns a 400 Bad Request error: "raw mode does not support template, system, or context." Additionally, setting `template: "{{ .Prompt }}"` seems ineffective, as it still cannot seamlessly complete text and gets interrupted. The same parameters work fine when called on a local model. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the cloudbug labels 2026-05-04 20:55:37 -05:00
GiteaMirror commented 2026-05-04 20:55:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 22, 2025):

Can you provide examples of the prompts you are sending to the cloud model and the local model?

<!-- gh-comment-id:3320755189 --> @rick-github commented on GitHub (Sep 22, 2025): Can you provide examples of the prompts you are sending to the cloud model and the local model?
GiteaMirror commented 2026-05-04 20:55:49 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 22, 2025):

This looks like a problem with the proxy.

$ prompt='<|start|>system<|message|>Talk like a pirate\n# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>user<|message|>hello<|end|><|start|>assistant'
$ curl -s https://ollama.com/api/generate -H "Authorization: $OLLAMA_API_KEY" -d '{"model":"gpt-oss:20b","prompt":"'"$prompt"'","raw":true,"stream":false}' | jq 
{
  "model": "gpt-oss:20b",
  "created_at": "2025-09-22T18:49:33.835263946Z",
  "response": "<|channel|>analysis<|message|>User says \"hello\". They want to talk like a pirate.",
  "done": true,
  "total_duration": 224292188,
  "prompt_eval_count": 34,
  "eval_count": 16
}
$ curl -s localhost:11434/api/generate -H "Authorization: $OLLAMA_API_KEY" -d '{"model":"gpt-oss:20b-cloud","prompt":"'"$prompt"'","raw":true,"stream":false}' | jq
{
  "error": "400 Bad Request: raw mode does not support template, system, or context"
}
<!-- gh-comment-id:3320822356 --> @rick-github commented on GitHub (Sep 22, 2025): This looks like a problem with the proxy. ```console $ prompt='<|start|>system<|message|>Talk like a pirate\n# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>user<|message|>hello<|end|><|start|>assistant' $ curl -s https://ollama.com/api/generate -H "Authorization: $OLLAMA_API_KEY" -d '{"model":"gpt-oss:20b","prompt":"'"$prompt"'","raw":true,"stream":false}' | jq { "model": "gpt-oss:20b", "created_at": "2025-09-22T18:49:33.835263946Z", "response": "<|channel|>analysis<|message|>User says \"hello\". They want to talk like a pirate.", "done": true, "total_duration": 224292188, "prompt_eval_count": 34, "eval_count": 16 } $ curl -s localhost:11434/api/generate -H "Authorization: $OLLAMA_API_KEY" -d '{"model":"gpt-oss:20b-cloud","prompt":"'"$prompt"'","raw":true,"stream":false}' | jq { "error": "400 Bad Request: raw mode does not support template, system, or context" } ```
GiteaMirror commented 2026-05-04 20:55:51 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Sep 22, 2025):

Can you provide examples of the prompts you are sending to the cloud model and the local model?

I am indeed using the local Ollama to call the cloud model, fetch('http://localhost:11434/api/generate'

<!-- gh-comment-id:3320874599 --> @ghost commented on GitHub (Sep 22, 2025): > Can you provide examples of the prompts you are sending to the cloud model and the local model? I am indeed using the local Ollama to call the cloud model, `fetch('http://localhost:11434/api/generate'`
GiteaMirror commented 2026-05-04 20:55:52 -05:00
Author
Owner
Copy Link

@rylaion commented on GitHub (Nov 19, 2025):

How you guys fix the

Error HTTP 400 Bad Request from http://127.0.0.1:11434/api/generate {"StatusCode":400,"Status":"400 Bad Request","error":"raw mode does not support template, system, or context"}?

Im using the qwen3-coder:480b-cloud for autocomplete to my Continue.dev extension but its not working I already declare the raw: false. Any work around?

<!-- gh-comment-id:3550127939 --> @rylaion commented on GitHub (Nov 19, 2025): How you guys fix the > Error HTTP 400 Bad Request from http://127.0.0.1:11434/api/generate {"StatusCode":400,"Status":"400 Bad Request","error":"raw mode does not support template, system, or context"}? Im using the qwen3-coder:480b-cloud for autocomplete to my Continue.dev extension but its not working I already declare the raw: false. Any work around?
GiteaMirror commented 2026-05-04 20:55:54 -05:00
Author
Owner
Copy Link

@ACheshirov commented on GitHub (Jan 20, 2026):

Will this ever be fixed?

<!-- gh-comment-id:3774335595 --> @ACheshirov commented on GitHub (Jan 20, 2026): Will this ever be fixed?
GiteaMirror commented 2026-05-04 20:55:57 -05:00
Author
Owner
Copy Link

@drifkin commented on GitHub (Jan 20, 2026):

Will this ever be fixed?

apologies, this issue shouldn't have been closed, @rick-github's repro is still valid. I've opened a new, more specific issue at #13801, I'll try to get a fix in soon

<!-- gh-comment-id:3774625467 --> @drifkin commented on GitHub (Jan 20, 2026): > Will this ever be fixed? apologies, this issue shouldn't have been closed, @rick-github's repro is still valid. I've opened a new, more specific issue at #13801, I'll try to get a fix in soon
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug cloud
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#70277
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?