fix(providers): refresh DeepSeek catalog per vendor retirement and docs - #7223
fix(providers): refresh DeepSeek catalog per vendor retirement and docs#7223valeriiD wants to merge 1 commit into
Conversation
Verified against the live vendor API (GET api.deepseek.com/models) and the official Models & Pricing table (api-docs.deepseek.com): - remove deepseek-chat / deepseek-reasoner — retired by vendor, no longer served (live /models returns only the v4 family) - deepseek-v4-flash / deepseek-v4-pro: correct context window 128k -> 1M (pricing table: CONTEXT LENGTH 1M, MAX OUTPUT 384K) - add deepseek-v4-flash-vision-exp — live-served, 1M context, image input - bump catalog_version to 2026.08.23
|
Hi @valeriiD, thank you for your first Pull Request! 🎉 🙌 Join Developer CommunityThanks so much for your contribution! We'd love to invite you to join the official QwenPaw developer group! You can find the Discord and DingTalk group links under the "Developer Community" section on our docs page: We truly appreciate your enthusiasm—and look forward to your future contributions! 😊 We'll review your PR soon. |
There was a problem hiding this comment.
Pull request overview
Refreshes the built-in DeepSeek model catalog to reflect vendor retirements and updated published specifications, keeping provider metadata aligned with current DeepSeek API/docs.
Changes:
- Bumped
catalog_version/published_atto2026.08.23. - Removed retired DeepSeek model IDs (
deepseek-chat,deepseek-reasoner) and updated remaining v4 family entries. - Increased DeepSeek v4 context window metadata to 1,000,000 and added
deepseek-v4-flash-vision-exp(image-capable).
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| "DEEPSEEK_MODELS": [ | ||
| { | ||
| "id": "deepseek-chat", | ||
| "name": "DeepSeek Chat", | ||
| "supports_image": false, | ||
| "supports_video": false, | ||
| "probe_source": "documentation", | ||
| "is_free": false, | ||
| "is_recommended": true, | ||
| "source": "builtin", | ||
| "availability_status": "unverified", | ||
| "availability_retryable": true, | ||
| "config_overrides": [], | ||
| "max_tokens": 8192, | ||
| "max_input_length": 131072, | ||
| "max_input_length_configured": false, | ||
| "generate_kwargs": {}, | ||
| "relay_reasoning": true | ||
| }, | ||
| { | ||
| "id": "deepseek-reasoner", | ||
| "name": "DeepSeek Reasoner", | ||
| "id": "deepseek-v4-flash", | ||
| "name": "DeepSeek V4 Flash", | ||
| "supports_image": false, |
| "id": "deepseek-v4-flash-vision-exp", | ||
| "name": "DeepSeek V4 Flash Vision Exp", | ||
| "supports_image": true, | ||
| "supports_video": false, | ||
| "probe_source": "documentation", |
|
@valeriiD Thanks for updating the DeepSeek model catalog! Could you please help confirm two points before we proceed?
Thank you! |


Verified against the live vendor API (GET api.deepseek.com/models) and the official Models & Pricing table (api-docs.deepseek.com):
Description
[Describe what this PR does and why]
Related Issue: Fixes #(issue_number) or Relates to #(issue_number)
Security Considerations: [If applicable, e.g. channel auth, env/config handling]
Type of Change
Component(s) Affected
Checklist
pre-commit run --all-fileslocally and it passespytestor as relevant) and they passFor Channel Changes (DingTalk, Lark, QQ, Console, etc.)
./scripts/check-channels.sh(or./scripts/check-channels.sh --changed) and it passestests/contract/channels/test_<channel>_contract.py(REQUIRED)create_instance()with proper channel initializationtests/contract/channels/__init__.py)tests/unit/channels/test_<channel>.pyfor complex internal logicTesting
[How to test these changes]
Evidence
Examples of valid evidence:
pytest tests/unit/app/chats/ -qoutput)pre-commit run --all-filessummaryAdditional Notes
[Optional: any other context]