wehub-resource-sync
18 lines
598 B
TOML
18 lines
598 B
TOML
# Direct endpoint: POST /models/chat/completions?api-version=2024-05-01-preview.
|
|
# Its published request schema documents no toggle, effort, or reasoning budget.
|
|
# https://learn.microsoft.com/en-us/rest/api/microsoftfoundry/model-inference/get-chat-completions/get-chat-completions (accessed 2026-06-25)
|
|
base_model = "deepseek/deepseek-v4-flash"
|
|
name = "DeepSeek-V4-Flash"
|
|
tool_call = false
|
|
|
|
reasoning_options = []
|
|
|
|
[cost]
|
|
input = 0.19
|
|
output = 0.51
|
|
|
|
[provider]
|
|
shape = "completions"
|
|
npm = "@ai-sdk/openai-compatible"
|
|
api = "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
|