Skip to content

fix(deepseek): correct V4 Pro/Flash pricing to the published rate card #6051

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

Open
settingzbot wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

fix(deepseek): correct V4 Pro/Flash pricing to the published rate card #6051

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 8 additions & 5 deletions providers/deepseek/models/deepseek-v4-flash-vision-exp.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
# Prices are DeepSeek's published OFF-PEAK rates, USD per 1M tokens.
# Peak (01:00-04:00 and 06:00-10:00 UTC, Mon-Fri) is exactly double; models.dev
# has no time-of-day pricing, and off-peak covers ~79% of hours.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-09-01)
# DeepSeek-V4-Flash-Vision-Exp is priced the same as DeepSeek V4 Flash.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-08-22)
# https://api-docs.deepseek.com/guides/vision (accessed 2026-08-22)
# OpenAI: `thinking.type = enabled|disabled`, `reasoning_effort = low|high|max`.
# Anthropic: `thinking.type`, `output_config.effort = low|high|max`; budget ignored.
Expand All @@ -17,7 +20,7 @@ values = ["low", "high", "max"]
field = "reasoning_content"

[cost]
input = 0.14
output = 0.28
reasoning = 0.28
cache_read = 0.0028
input = 0.22
output = 0.66
reasoning = 0.66
cache_read = 0.007
13 changes: 8 additions & 5 deletions providers/deepseek/models/deepseek-v4-flash.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
# Prices are DeepSeek's published OFF-PEAK rates, USD per 1M tokens.
# Peak (01:00-04:00 and 06:00-10:00 UTC, Mon-Fri) is exactly double; models.dev
# has no time-of-day pricing, and off-peak covers ~79% of hours.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-09-01)
# Reasoning tokens are billed at the output rate (no separate CoT price).
# `completion_tokens_details.reasoning_tokens` is a subset of completion_tokens.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-07-31)
# OpenAI: `thinking.type = enabled|disabled`, `reasoning_effort = low|high|max`.
# Anthropic: `thinking.type`, `output_config.effort = low|high|max`; budget ignored.
# Flash maps requested low→low (unlike Pro, which maps low→high). xhigh→high.
Expand All @@ -19,7 +22,7 @@ values = ["low", "high", "max"]
field = "reasoning_content"

[cost]
input = 0.14
output = 0.28
reasoning = 0.28
cache_read = 0.0028
input = 0.22
output = 0.66
reasoning = 0.66
cache_read = 0.007
13 changes: 8 additions & 5 deletions providers/deepseek/models/deepseek-v4-pro.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
# Prices are DeepSeek's published OFF-PEAK rates, USD per 1M tokens.
# Peak (01:00-04:00 and 06:00-10:00 UTC, Mon-Fri) is exactly double; models.dev
# has no time-of-day pricing, and off-peak covers ~79% of hours.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-09-01)
# Reasoning tokens are billed at the output rate (no separate CoT price).
# `completion_tokens_details.reasoning_tokens` is a subset of completion_tokens.
# https://api-docs.deepseek.com/quick_start/pricing/ (accessed 2026-08-12)
base_model = "deepseek/deepseek-v4-pro-0813"
name = "DeepSeek V4 Pro"
# OpenAI: `thinking.type = enabled|disabled`, `reasoning_effort = high|max`.
Expand All @@ -18,7 +21,7 @@ values = ["high", "max"]
field = "reasoning_content"

[cost]
input = 0.435
output = 0.87
reasoning = 0.87
cache_read = 0.003625
input = 0.66
output = 1.98
reasoning = 1.98
cache_read = 0.022
Loading