mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-05 04:13:25 +00:00
Alex
b77561288d
Rename the unused *_cost_per_token capability fields to USD per 1M tokens, add prompt-cache read/write rates, and ship list prices for the hosted catalogs. The old per-token keys still load, scaled, with a warning. docsgpt/pricing.py turns a call's token bins into a USD cost. Models with no declared rate cost $0 unless QUOTA_UNPRICED_RATE_PER_MILLION is set.
23 lines
734 B
YAML
23 lines
734 B
YAML
provider: openai_compatible
|
|
display_provider: deepseek
|
|
api_key_env: DEEPSEEK_API_KEY
|
|
base_url: https://api.deepseek.com/v1
|
|
|
|
defaults:
|
|
supports_tools: true
|
|
supports_structured_output: true
|
|
context_window: 1048576
|
|
|
|
models:
|
|
- id: deepseek-v4-flash
|
|
display_name: DeepSeek V4 Flash
|
|
description: Cost-efficient 1M-context model with hybrid thinking / non-thinking modes, tool calling and FIM completion
|
|
input_cost_per_million: 0.14
|
|
output_cost_per_million: 0.28
|
|
|
|
- id: deepseek-v4-pro
|
|
display_name: DeepSeek V4 Pro
|
|
description: Frontier 1M-context model with hybrid thinking / non-thinking modes for advanced reasoning and agentic coding
|
|
input_cost_per_million: 0.435
|
|
output_cost_per_million: 0.87
|