added two new models - #18
Merged
Merged
Conversation
📝 WalkthroughWalkthroughTwo models, ChangesModel documentation coverage
Estimated code review effort: 2 (Simple) | ~15 minutes Possibly related PRs
Suggested labels: Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs.json`:
- Around line 137-138: Add backing MDX pages for the model slugs referenced in
docs.json: create api-reference/models/glm-5-2.mdx and
api-reference/models/deepseek-v4-flash.mdx using the repository’s existing
model-page structure and metadata conventions, so both navigation links resolve
successfully.
In `@docs/text-generation.mdx`:
- Line 259: Update the DeepSeek-V4-Flash description in the documentation to
hyphenate the compound modifier as “well-suited for analyzing,” leaving the
surrounding model details unchanged.
- Around line 204-250: Update the Chat Completions OpenAPI definition to match
the documented examples: add the request max_tokens property and define a
response-specific message schema containing reasoning and tool_calls with the
exact types and nullability shown. Apply the same alignment to the related
schema section referenced by the comment, rather than removing these fields from
the examples.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: f45de434-1c47-4655-974b-2d7790203599
📒 Files selected for processing (4)
api-reference/openapi/zerogpu.openapi.jsondocs.jsondocs/model-catalog.mdxdocs/text-generation.mdx
Comment on lines
+137
to
+138
| "api-reference/models/glm-5-2", | ||
| "api-reference/models/deepseek-v4-flash", |
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/usr/bin/env bash
for slug in glm-5-2 deepseek-v4-flash; do
echo "=== ${slug} ==="
fd -a -t f "${slug}" . || true
rg -n -F "api-reference/models/${slug}" . || true
doneRepository: zerogpu/docs
Length of output: 2158
🏁 Script executed:
#!/usr/bin/env bash
set -euo pipefail
echo "=== files matching api-reference/models ==="
fd -a . 'api-reference' . || true
echo
echo "=== route/content files mentioning model slugs ==="
rg -n -S 'api-reference/models/(glm-5-2|deepseek-v4-flash)|glm-5-2|deepseek-v4-flash' docs . \
-g '!**/node_modules/**' -g '!**/.git/**' || true
echo
echo "=== docs.json around the referenced lines ==="
sed -n '120,155p' docs.jsonRepository: zerogpu/docs
Length of output: 18154
🏁 Script executed:
#!/usr/bin/env bash
set -euo pipefail
for slug in glm-5-2 deepseek-v4-flash; do
echo "=== $slug: matching files ==="
fd -a -t f "$slug" . || true
echo
done
echo "=== docs directory tree (shallow) ==="
find docs -maxdepth 3 \( -type d -o -type f \) | sort | sed -n '1,220p'
echo
echo "=== possible route/page definitions for api-reference/models ==="
rg -n -S 'api-reference/models|models/' docs . \
-g '!**/node_modules/**' -g '!**/.git/**' -g '!docs/model-catalog.mdx' -g '!docs/text-generation.mdx' || trueRepository: zerogpu/docs
Length of output: 17633
🏁 Script executed:
#!/usr/bin/env bash
set -euo pipefail
echo "=== docs.json top-level structure ==="
python3 - <<'PY'
import json
from pathlib import Path
data = json.loads(Path("docs.json").read_text())
print(type(data).__name__)
if isinstance(data, dict):
print("top-level keys:", list(data.keys()))
for k in ("pages", "navigation", "navbar", "sidebar", "links"):
if k in data:
v = data[k]
print(f"{k}: {type(v).__name__}")
PY
echo
echo "=== docs.json excerpt around api-reference ==="
rg -n -C 4 '"api-reference"|glm-5-2|deepseek-v4-flash' docs.json || true
echo
echo "=== candidate source files for api-reference routes ==="
fd -a -t f 'api-reference' . || true
fd -a -t f 'models' docs . | sed -n '1,120p' || trueRepository: zerogpu/docs
Length of output: 1070
Add backing pages for these model links. docs.json:137-138 points to api-reference/models/glm-5-2 and api-reference/models/deepseek-v4-flash, but the repo has no matching api-reference/models/*.mdx files for either slug.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs.json` around lines 137 - 138, Add backing MDX pages for the model slugs
referenced in docs.json: create api-reference/models/glm-5-2.mdx and
api-reference/models/deepseek-v4-flash.mdx using the repository’s existing
model-page structure and metadata conventions, so both navigation links resolve
successfully.
Comment on lines
+204
to
+250
| ```bash Chat Completions | ||
| curl https://api.zerogpu.ai/v1/chat/completions \ | ||
| -H "content-type: application/json" \ | ||
| -H "x-api-key: YOUR_API_KEY" \ | ||
| -d '{ | ||
| "model": "glm-5.2", | ||
| "messages": [ | ||
| { | ||
| "role": "system", | ||
| "content": "You are a precise code-review assistant. Be brief." | ||
| }, | ||
| { | ||
| "role": "user", | ||
| "content": "Review this function name: getUserDataAndSendEmailAndLog(). What does it tell you about the function, and how would you refactor it? 3 bullets max." | ||
| } | ||
| ], | ||
| "max_tokens": 800 | ||
| }' | ||
| ``` | ||
|
|
||
| The model reasons before it answers and returns the trace alongside the final text as a `reasoning` field on the message. | ||
|
|
||
| ```json Response | ||
| { | ||
| "id": "id-1784840133815", | ||
| "object": "chat.completion", | ||
| "created": 1784840133, | ||
| "model": "glm-5.2", | ||
| "choices": [ | ||
| { | ||
| "index": 0, | ||
| "finish_reason": "stop", | ||
| "message": { | ||
| "role": "assistant", | ||
| "content": "**1. The name confesses the crime** – \"And\" in a function name means it violates single responsibility: fetching, emailing, and logging are three separate concerns.\n\n**2. Split it** – Extract `getUserData()`, `sendEmail()`, and `logActivity()`, each independently testable and reusable.\n\n**3. Orchestrate at the edge** – If the sequence matters, compose them in a thin workflow function named for the *why* (e.g. `onUserSignup()`), not the *how*.", | ||
| "reasoning": "The name reveals the function does three unrelated things — fetch data, send email, log — a single-responsibility violation. Recommend splitting into three functions plus a thin orchestrator. Keep to 3 bullets.", | ||
| "tool_calls": [] | ||
| } | ||
| } | ||
| ], | ||
| "usage": { | ||
| "prompt_tokens": 58, | ||
| "completion_tokens": 151, | ||
| "total_tokens": 209 | ||
| } | ||
| } | ||
| ``` |
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
Align the OpenAPI contract with these examples.
Both samples use max_tokens and show message.reasoning/message.tool_calls, but the supplied Chat Completions schema documents none of those fields. Add the request property and a response-specific message schema (with exact field types/nullability), or remove them from the examples.
Also applies to: 263-309
🧰 Tools
🪛 Betterleaks (1.6.1)
[high] 205-207: Discovered a potential authorization token provided in a curl command header, which could compromise the curl accessed resource.
(curl-auth-header)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/text-generation.mdx` around lines 204 - 250, Update the Chat Completions
OpenAPI definition to match the documented examples: add the request max_tokens
property and define a response-specific message schema containing reasoning and
tool_calls with the exact types and nullability shown. Apply the same alignment
to the related schema section referenced by the comment, rather than removing
these fields from the examples.
| (`/v1/responses`) is not available for this model. | ||
| </Note> | ||
|
|
||
| > DeepSeek's DeepSeek-V4-Flash is an open-weight Mixture-of-Experts model built for efficient reasoning, coding, and agentic workflows, with 284B total parameters activating only 13B per token, served on ZeroGPU for general text generation. It sustains a 1,048,576-token (1M) context well suited for analyzing large codebases, long documents, extensive conversations, and complex research tasks, and supports fast non-thinking responses as well as higher-effort reasoning modes for planning, problem-solving, and multi-step automation. MIT-licensed with no usage restrictions. |
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Hyphenate the compound modifier.
Use “well-suited for analyzing” here.
🧰 Tools
🪛 LanguageTool
[grammar] ~259-~259: Use a hyphen to join words.
Context: ...ains a 1,048,576-token (1M) context well suited for analyzing large codebases, lo...
(QB_NEW_EN_HYPHEN)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@docs/text-generation.mdx` at line 259, Update the DeepSeek-V4-Flash
description in the documentation to hyphenate the compound modifier as
“well-suited for analyzing,” leaving the surrounding model details unchanged.
Source: Linters/SAST tools
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit
New Features
glm-5.2anddeepseek-v4-flashmodels in Chat Completions.Documentation