Skip to content

Open weight models 1 #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
maddy-a merged 2 commits into from
Jul 28, 2026
+466 −0
Merged

Open weight models 1 #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f335a44
added api ref only for chat completion
maddy-a Jul 28, 2026
ce0ff24
Merge branch 'main' into open-weight-models-1
maddy-a Jul 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions api-reference/models/deepseek-v4-flash.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
---
title: "deepseek-v4-flash"
sidebarTitle: "deepseek-v4-flash"
description: "Model details for deepseek-v4-flash. Reasoning, coding, and agentic workflows with a 1M-token context window."
openapi: "api-reference/openapi/playgrounds/deepseek-v4-flash.openapi.json POST /chat/completions"
---

<Note>
This model supports the Chat Completions API only. Send requests to
`/v1/chat/completions` — the Responses endpoint (`/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.

**References:** [Model docs](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
16 changes: 16 additions & 0 deletions api-reference/models/glm-5-2.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
---
title: "glm-5.2"
sidebarTitle: "glm-5.2"
description: "Model details for glm-5.2. Reasoning, function calling, and batch tasks with a 1M-token context window."
openapi: "api-reference/openapi/playgrounds/glm-5_2.openapi.json POST /chat/completions"
---

<Note>
This model supports the Chat Completions API only. Send requests to
`/v1/chat/completions` — the Responses endpoint (`/v1/responses`) is not
available for this model.
</Note>

> Z.ai's GLM-5.2 is an open-weight Mixture-of-Experts flagship built for long-horizon tasks, with 753B total parameters activating 8 of 256 experts per token, served on ZeroGPU for general text generation. It sustains a solid 1,048,576-token (1M) context, reasons through a problem with flexible thinking effort before answering, and supports function calling and batch tasks. MIT-licensed with no usage restrictions. When the work spans entire repos, day-long agent sessions, or million-token documents, this is the model.
Comment on lines +4 to +14

@coderabbitai coderabbitai Bot Jul 28, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win

Do not advertise API capabilities this page cannot expose.

Lines 4 and 14 promise function calling and batch tasks, but the linked playground defines only Chat Completions; it also lacks tools, tool_choice, tool messages, and tool_call_id. Add the supported tool-calling/Batch API contracts, or remove/qualify these claims to avoid sending users to unsupported flows.

🤖 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 `@api-reference/models/glm-5-2.mdx` around lines 4 - 14, Update the GLM-5.2
page’s description and model overview to remove or qualify the claims about
function calling and batch tasks unless the linked OpenAPI playground is
expanded to expose those contracts. Keep the advertised capabilities consistent
with the Chat Completions schema referenced by the page, including its lack of
tools, tool_choice, tool messages, and tool_call_id support.


**References:** [Model docs](https://huggingface.co/zai-org/GLM-5.2) • [Terms](https://zerogpu.ai/terms) • [Privacy](https://zerogpu.ai/privacy-policy)
217 changes: 217 additions & 0 deletions api-reference/openapi/playgrounds/deepseek-v4-flash.openapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,217 @@
{
"openapi": "3.1.0",
"info": {
"title": "deepseek-v4-flash playground",
"version": "1.0",
"description": "Interactive playground for **deepseek-v4-flash**.\nModel is always `deepseek-v4-flash` on this page (shown in the form, not editable).\nUse the **request example** selector to switch use cases (JSON, NER, PII, etc.).\nAuthentication: `x-api-key` (required) and `x-project-id` (optional)."

@coderabbitai coderabbitai Bot Jul 28, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win

Make the request-example guidance match the available examples.

Lines 61-79 define only default, so the selector cannot offer the advertised JSON, NER, or PII workflows. Remove that claim or add the corresponding examples.

🤖 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 `@api-reference/openapi/playgrounds/deepseek-v4-flash.openapi.json` at line 6,
Update the description in the deepseek-v4-flash playground OpenAPI definition to
match the examples declared under the request-example configuration: either
remove the claim that the selector supports JSON, NER, and PII workflows, or add
corresponding example entries alongside default.

},
"servers": [
{
"url": "https://api.zerogpu.ai/v1",
"description": "Production"
}
],
"security": [
{
"ApiKey": []
}
],
"paths": {
"/chat/completions": {
"post": {
"operationId": "createChatCompletion_deepseek-v4-flash",
"summary": "deepseek-v4-flash: Chat completions",
"tags": [
"deepseek-v4-flash"
],
"parameters": [
{
"name": "x-project-id",
"in": "header",
"required": false,
"schema": {
"type": "string"
},
"description": "Optional project identifier. Scopes the request to a specific project when provided."
}
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/CreateChatCompletionRequest"
},
{
"type": "object",
"properties": {
"model": {
"type": "string",
"const": "deepseek-v4-flash",
"default": "deepseek-v4-flash",
"example": "deepseek-v4-flash",
"description": "Model identifier (fixed for this playground). Use request examples to change use cases."
}
}
}
]
},
"examples": {
"default": {
"summary": "Default",
"value": {
"model": "deepseek-v4-flash",
"messages": [
{
"role": "system",
"content": "You are a pragmatic staff engineer. Be concise."
},
{
"role": "user",
"content": "Plan the migration of a nightly cron-based ETL job to an event-driven pipeline. 4 steps max."
}
],
"max_tokens": 800
}
}
}
}
}
},
"responses": {
"200": {
"description": "Success",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionResponse"
},
"examples": {
"default": {
"summary": "Default",
"value": {
"id": "id-1785523944762",
"object": "chat.completion",
"created": 1785523944,
"model": "deepseek-v4-flash",
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "**1. Inventory the job** – Document inputs, outputs, schedule, and every downstream consumer of the cron ETL so nothing breaks silently.\n\n**2. Define the events** – Pick the real trigger (file landing, DB change, message) and publish it to a queue or event bus with a versioned schema.\n\n**3. Run in parallel** – Build the event-driven consumer alongside cron, write to a shadow table, and diff outputs until they match.\n\n**4. Cut over with a rollback path** – Point consumers at the new output, keep cron paused (not deleted) for one cycle, then decommission.",
"reasoning": "Cron ETL to event-driven: inventory the current job first, define the trigger events, run the new pipeline in parallel against a shadow output, then cut over with a rollback path. Four steps, each actionable.",
"tool_calls": []
}
}
],
"usage": {
"prompt_tokens": 52,
"completion_tokens": 158,
"total_tokens": 210
}
}
}
}
}
}
},
"400": {
"description": "Bad request"
},
"401": {
"description": "Unauthorized"
},
"403": {
"description": "Forbidden"
},
"420": {
"description": "Insufficient quota"
},
"500": {
"description": "Internal server error"
}
}
}
}
},
"components": {
"securitySchemes": {
"ApiKey": {
"type": "apiKey",
"in": "header",
"name": "x-api-key"
}
},
"schemas": {
"CreateChatCompletionRequest": {
"type": "object",
"required": [
"model",
"messages"
],
"properties": {
"model": {
"type": "string",
"const": "deepseek-v4-flash",
"default": "deepseek-v4-flash",
"example": "deepseek-v4-flash",
"description": "Model identifier (fixed for this playground). Use request examples to change use cases."
},
"messages": {
"type": "array",
"minItems": 1,
"items": {
"$ref": "#/components/schemas/ChatMessage"
}
},
"max_tokens": {
"type": "integer",
"minimum": 1,
"example": 800,
"description": "Maximum number of tokens to generate in the response."
},
"metadata": {
"type": "object",
"additionalProperties": true
}
}
},
"ChatMessage": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"type": "string",
"enum": [
"system",
"user",
"assistant"
]
},
"content": {
"type": "string",
"minLength": 1,
"format": "textarea",
"maxLength": 131072,
"description": "Message text."
}
}
},
"ChatCompletionResponse": {
"type": "object",
"additionalProperties": true
},
"ErrorResponse": {
"type": "object",
"additionalProperties": true
}
}
}
}
Loading