Skip to content

Venice: Update model configs with refreshed pricing and limits #1399

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

Merged
rekram1-node merged 1 commit into from
Apr 10, 2026
Merged

Venice: Update model configs with refreshed pricing and limits #1399

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
4 changes: 2 additions & 2 deletions providers/venice/models/google.gemma-4-26b-a4b-it.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ tool_call = true
structured_output = true
temperature = true
release_date = "2026-04-02"
last_updated = "2026-04-04"
last_updated = "2026-04-09"
open_weights = true

[cost]
Expand All @@ -15,7 +15,7 @@ output = 0.5

[limit]
context = 256_000
output = 12_288
output = 8_192

[modalities]
input = ["text", "image", "video"]
Expand Down
4 changes: 2 additions & 2 deletions providers/venice/models/google.gemma-4-31b-it.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ tool_call = true
structured_output = true
temperature = true
release_date = "2026-04-03"
last_updated = "2026-04-04"
last_updated = "2026-04-09"
open_weights = true

[cost]
Expand All @@ -15,7 +15,7 @@ output = 0.5

[limit]
context = 256_000
output = 12_288
output = 8_192

[modalities]
input = ["text", "image", "video"]
Expand Down
14 changes: 7 additions & 7 deletions providers/venice/models/grok-4-20-beta.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,18 +6,18 @@ tool_call = true
structured_output = true
temperature = true
release_date = "2026-03-12"
last_updated = "2026-03-16"
last_updated = "2026-04-09"
open_weights = false

[cost]
input = 2.5
output = 7.5
cache_read = 0.25
input = 2.27
output = 6.8
cache_read = 0.23

[cost.context_over_200k]
input = 5
output = 15
cache_read = 0.25
input = 4.53
output = 13.6
cache_read = 0.23

[limit]
context = 2_000_000
Expand Down
14 changes: 7 additions & 7 deletions providers/venice/models/grok-4-20-multi-agent-beta.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,18 +6,18 @@ tool_call = false
structured_output = true
temperature = true
release_date = "2026-03-12"
last_updated = "2026-03-16"
last_updated = "2026-04-09"
open_weights = false

[cost]
input = 2.5
output = 7.5
cache_read = 0.25
input = 2.27
output = 6.8
cache_read = 0.23

[cost.context_over_200k]
input = 5
output = 15
cache_read = 0.25
input = 4.53
output = 13.6
cache_read = 0.23

[limit]
context = 2_000_000
Expand Down
8 changes: 4 additions & 4 deletions providers/venice/models/grok-41-fast.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,13 +7,13 @@ structured_output = true
temperature = true
knowledge = "2025-07"
release_date = "2025-12-01"
last_updated = "2026-03-12"
last_updated = "2026-04-09"
open_weights = false

[cost]
input = 0.25
output = 0.625
cache_read = 0.0625
input = 0.23
output = 0.57
cache_read = 0.06

[limit]
context = 1_000_000
Expand Down
8 changes: 6 additions & 2 deletions providers/venice/models/qwen-3-6-plus.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
name = "Qwen 3.6 Plus"
name = "Qwen 3.6 Plus Uncensored"
family = "qwen"
attachment = true
reasoning = true
tool_call = true
structured_output = true
temperature = true
release_date = "2026-04-06"
last_updated = "2026-04-07"
last_updated = "2026-04-09"
open_weights = false

[cost]
Expand All @@ -15,6 +15,10 @@ output = 3.75
cache_read = 0.0625
cache_write = 0.78

[cost.context_over_200k]
input = 2.5
output = 7.5

[limit]
context = 1_000_000
output = 65_536
Expand Down
Loading