Skip to content
Merged
Changes from all commits
Commits
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
34 changes: 34 additions & 0 deletions providers/wafer/DeepSeek-V4-Flash-0731-Fast.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
costs:
- cache_read_input_token_cost: 7e-8
input_cost_per_token: 2.8e-7
output_cost_per_token: 5.6e-7
region: "*"
features:
- function_calling
- structured_output
- json_output
- tool_choice
- system_messages
- prompt_caching
limits:
context_window: 1048576
modalities:
input:
- text
output:
- text
mode: chat
model: DeepSeek-V4-Flash-0731-Fast

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Invalid Wafer model identifier

High Severity

model is set to DeepSeek-V4-Flash-0731-Fast, which does not appear in Wafer’s catalog. Wafer exposes DeepSeek V4 Flash as deepseek-v4-flash (already present in deepseek-v4-flash.yaml). Gateway tests failed all 10 scenarios, consistent with requests being rejected for an unknown model ID.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 7043913. Configure here.

params:
- key: reasoning_effort
supportedValues:
- low
- high
- max
provisioning: serverless
sources:
- https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
status: active
supportedModes:
- chat
thinking: true
Loading