Skip to content

vercel: add new models and interleaved support #770

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 5 commits into from
Feb 5, 2026
Merged

vercel: add new models and interleaved support #770

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e7e8af6
vercel: add 5 new models from Vercel AI Gateway
jerilynzheng Jan 30, 2026
008c521
Merge branch 'dev' into feat/add-vercel-models-jan-30
rekram1-node Jan 30, 2026
3985ee8
vercel: add Claude Opus 4.6
jerilynzheng Feb 5, 2026
ed96ac7
fix: update Claude Opus 4.6 knowledge cutoff to 2025-05
jerilynzheng Feb 5, 2026
f0854ab
vercel: add interleaved = true for confirmed models
jerilynzheng Feb 5, 2026
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
23 changes: 23 additions & 0 deletions providers/vercel/models/alibaba/qwen3-max-thinking.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
name = "Qwen 3 Max Thinking"
family = "qwen"
release_date = "2025-01"
last_updated = "2025-01"
attachment = false
reasoning = true
temperature = true
knowledge = "2025-01"
tool_call = true
open_weights = true

[cost]
input = 1.20
output = 6.00
cache_read = 0.24

[limit]
context = 256_000
output = 65_536

[modalities]
input = ["text"]
output = ["text"]
2 changes: 2 additions & 0 deletions providers/vercel/models/anthropic/claude-haiku-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
knowledge = "2025-02-28"
open_weights = false

interleaved = true

[cost]
input = 1.00
output = 5.00
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/anthropic/claude-opus-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
knowledge = "2025-03-31"
open_weights = false

interleaved = true

[cost]
input = 5.00
output = 25.00
Expand Down
26 changes: 26 additions & 0 deletions providers/vercel/models/anthropic/claude-opus-4.6.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
name = "Claude Opus 4.6"
family = "claude-opus"
release_date = "2026-02"
last_updated = "2026-02"
attachment = true
reasoning = true
temperature = true
tool_call = true
knowledge = "2025-05"
open_weights = false

interleaved = true

[cost]
input = 5.00
output = 25.00
cache_read = 0.50
cache_write = 6.25

[limit]
context = 1_000_000
output = 128_000

[modalities]
input = ["text", "image", "pdf"]
output = ["text"]
22 changes: 22 additions & 0 deletions providers/vercel/models/arcee-ai/trinity-large-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
name = "Trinity Large Preview"
family = "trinity"
release_date = "2025-01"
last_updated = "2025-01"
attachment = false
reasoning = false
temperature = true
tool_call = true
open_weights = false
knowledge = "2024-10"

[cost]
input = 0.25
output = 1.00

[limit]
context = 131_000
output = 131_000

[modalities]
input = ["text"]
output = ["text"]
2 changes: 2 additions & 0 deletions providers/vercel/models/deepseek/deepseek-v3.2-thinking.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
open_weights = false
knowledge = "2024-07"

interleaved = true

[cost]
input = 0.28
output = 0.42
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/minimax/minimax-m2.1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
open_weights = false
knowledge = "2024-10"

interleaved = true

[cost]
input = 0.3
output = 1.2
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/minimax/minimax-m2.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
knowledge = "2024-10"
open_weights = true

interleaved = true

[cost]
input = 0.27
output = 1.15
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/moonshotai/kimi-k2-thinking-turbo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
open_weights = false
knowledge = "2024-08"

interleaved = true

[cost]
input = 1.15
output = 8
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/moonshotai/kimi-k2-thinking.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
open_weights = false
knowledge = "2024-08"

interleaved = true

[cost]
input = 0.47
output = 2
Expand Down
3 changes: 1 addition & 2 deletions providers/vercel/models/moonshotai/kimi-k2.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,7 @@ tool_call = true
knowledge = "2025-01"
open_weights = true

[interleaved]
field = "reasoning_details"
interleaved = true

[cost]
input = 0.60
Expand Down
23 changes: 23 additions & 0 deletions providers/vercel/models/openai/gpt-4o-mini-search-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
name = "GPT 4o Mini Search Preview"
family = "gpt-mini"
release_date = "2025-01"
last_updated = "2025-01"
attachment = false
reasoning = false
temperature = true
knowledge = "2023-09"
tool_call = false
structured_output = false
open_weights = false

[cost]
input = 0.15
output = 0.60

[limit]
context = 128_000
output = 16_384

[modalities]
input = ["text"]
output = ["text"]
2 changes: 2 additions & 0 deletions providers/vercel/models/zai/glm-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ knowledge = "2025-07"
tool_call = true
open_weights = true

interleaved = true

[cost]
input = 0.6
output = 2.2
Expand Down
2 changes: 2 additions & 0 deletions providers/vercel/models/zai/glm-4.6.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ knowledge = "2025-04"
tool_call = true
open_weights = true

interleaved = true

[cost]
input = 0.45
output = 1.8
Expand Down
25 changes: 25 additions & 0 deletions providers/vercel/models/zai/glm-4.7-flashx.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
name = "GLM 4.7 FlashX"
family = "glm-flash"
release_date = "2025-01"
last_updated = "2025-01"
attachment = false
reasoning = true
temperature = true
knowledge = "2025-01"
tool_call = true
open_weights = true

interleaved = true

[cost]
input = 0.06
output = 0.40
cache_read = 0.01

[limit]
context = 200_000
output = 128_000
Comment on lines 9 to 21
Copy link
Contributor

@rekram1-node rekram1-node Jan 30, 2026

Choose a reason for hiding this comment

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

believe this is an interleaved reasoning model?

Copy link
Contributor Author

@jerilynzheng jerilynzheng Feb 5, 2026

Choose a reason for hiding this comment

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

updated! added interleaved reasoning field to the other ones that support as well


[modalities]
input = ["text"]
output = ["text"]
2 changes: 2 additions & 0 deletions providers/vercel/models/zai/glm-4.7.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ tool_call = true
open_weights = false
knowledge = "2024-10"

interleaved = true

[cost]
input = 0.43
output = 1.75
Expand Down