Skip to content

feat(deepinfra): update model YAMLs [bot] #368

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
LordGameleo merged 1 commit into from
Mar 19, 2026
Merged

feat(deepinfra): update model YAMLs [bot] #368

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: 4 additions & 0 deletions providers/deepinfra/BAAI/bge-base-en-v1.5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,10 @@ costs:
region: "*"
limits:
max_input_tokens: 512
output_vector_size: 768
modalities:
input:
- text
mode: embedding
model: BAAI/bge-base-en-v1.5
sources:
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/BAAI/bge-en-icl.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,11 @@
costs:
- input_cost_per_token: 1.e-8
region: "*"
modalities:
input:
- text
output:
- text
mode: embedding
model: BAAI/bge-en-icl
sources:
Expand Down
4 changes: 2 additions & 2 deletions providers/deepinfra/BAAI/bge-large-en-v1.5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,10 @@ costs:
region: "*"
limits:
max_input_tokens: 512
max_tokens: 512
output_vector_size: 1024
modalities:
input:
- image
- text
mode: embedding
model: BAAI/bge-large-en-v1.5
sources:
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/BAAI/bge-m3-multi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,12 @@ costs:
region: "*"
limits:
max_input_tokens: 8192
output_vector_size: 1024
modalities:
input:
- text
mode: embedding
model: BAAI/bge-m3-multi
sources:
- https://deepinfra.com/BAAI/bge-m3-multi/api
- https://huggingface.co/BAAI/bge-m3
3 changes: 3 additions & 0 deletions providers/deepinfra/BAAI/bge-m3.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,9 @@ costs:
limits:
max_input_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
mode: embedding
model: BAAI/bge-m3
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/Bria-3.2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@ costs:
region: "*"
modalities:
input:
- text
output:
- image
mode: image
model: Bria/Bria-3.2
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/blur_background.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Bria/blur_background
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/enhance.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Bria/enhance
sources:
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/Bria/erase.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,11 @@
costs:
- input_cost_per_image: 0.04
region: "*"
modalities:
input:
- image
output:
- image
mode: image
model: Bria/erase
sources:
Expand Down
8 changes: 8 additions & 0 deletions providers/deepinfra/Bria/erase_foreground.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,11 @@
costs:
- input_cost_per_image: 0.04
region: "*"
modalities:
input:
- image
output:
- image
mode: image
model: Bria/erase_foreground
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/expand.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Bria/expand
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/fibo.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
modalities:
input:
- text
output:
- image
mode: image
model: Bria/fibo
Expand Down
3 changes: 3 additions & 0 deletions providers/deepinfra/Bria/fibo_edit.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
modalities:
input:
- text
- image
output:
- image
mode: image
model: Bria/fibo_edit
Expand Down
6 changes: 6 additions & 0 deletions providers/deepinfra/Bria/gen_fill.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,11 @@
costs:
- input_cost_per_image: 0.04
region: "*"
modalities:
input:
- text
- image
output:
- image
mode: image
model: Bria/gen_fill
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/Bria/remove_background.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,11 @@
costs:
- input_cost_per_image: 0
region: "*"
modalities:
input:
- image
output:
- image
mode: image
model: Bria/remove_background
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Bria/replace_background.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Bria/replace_background
sources:
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/ByteDance/Seed-1.8.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,18 @@ costs:
- cost_per_token: 0.000004
from: 128000
features:
- function_calling
- prompt_caching
limits:
context_window: 256000
max_output_tokens: 256000
max_tokens: 256000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: ByteDance/Seed-1.8
sources:
Expand Down
6 changes: 5 additions & 1 deletion providers/deepinfra/ByteDance/Seed-2.0-mini.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,17 @@ costs:
- cost_per_token: 8.e-7
from: 128000
features:
- function_calling
- prompt_caching
- structured_output
limits:
context_window: 256000
max_tokens: 256000
Copy link

@cursor cursor bot Mar 19, 2026

Choose a reason for hiding this comment

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

Seed-2.0-mini lost max_tokens without adding max_output_tokens

Medium Severity

The max_tokens: 256000 field was removed from limits without adding a max_output_tokens value, leaving only context_window: 256000. The sibling model ByteDance/Seed-1.8 retains both max_output_tokens: 256000 and max_tokens: 256000. This data loss removes output token limit information for this model.

Fix in Cursor Fix in Web

modalities:
input:
- text
- image
output:
- text
mode: chat
model: ByteDance/Seed-2.0-mini
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/ByteDance/Seedream-4.5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,8 @@ costs:
region: "*"
modalities:
input:
- text
output:
- image
mode: image
model: ByteDance/Seedream-4.5
Expand Down
3 changes: 3 additions & 0 deletions providers/deepinfra/ClarityAI/creative.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,9 @@ costs:
modalities:
input:
- image
- text
output:
- image
mode: image
model: ClarityAI/creative
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/ClarityAI/crystal.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: ClarityAI/crystal
sources:
Expand Down
3 changes: 2 additions & 1 deletion providers/deepinfra/ClarityAI/flux.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,10 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: ClarityAI/flux
sources:
- https://deepinfra.com/ClarityAI/flux
- https://deepinfra.com/ClarityAI/flux/api
- https://deepinfra.com/flux
4 changes: 3 additions & 1 deletion providers/deepinfra/MiniMaxAI/MiniMax-M2.1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,12 @@ costs:
region: "*"
features:
- prompt_caching
- function_calling
- structured_output
limits:
context_window: 196608
max_output_tokens: 131072
max_tokens: 196608
max_tokens: 131072
mode: chat
model: MiniMaxAI/MiniMax-M2.1
sources:
Expand Down
11 changes: 8 additions & 3 deletions providers/deepinfra/MiniMaxAI/MiniMax-M2.5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,19 @@
costs:
- cache_read_input_token_cost: 2.99999997e-8
- cache_read_input_token_cost: 3.e-8
input_cost_per_token: 2.7e-7
output_cost_per_token: 9.5e-7
region: "*"
features:
- function_calling
- prompt_caching
- structured_output
limits:
context_window: 196608
max_output_tokens: 131072
max_tokens: 196608
Copy link

@cursor cursor bot Mar 19, 2026

Choose a reason for hiding this comment

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

MiniMax-M2.5 lost max_output_tokens and max_tokens limits

High Severity

The max_output_tokens and max_tokens fields were removed from the limits section, leaving only context_window: 196608. The sibling model MiniMax-M2.1 retains both max_output_tokens: 131072 and max_tokens: 131072. This data loss means consumers of this config have no information about the model's output token limits, which could lead to incorrect request sizing or validation failures.

Fix in Cursor Fix in Web

modalities:
input:
- text
output:
- text
mode: chat
model: MiniMaxAI/MiniMax-M2.5
sources:
Expand Down
5 changes: 4 additions & 1 deletion providers/deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,10 +7,13 @@ features:
limits:
context_window: 16384
max_output_tokens: 8192
max_tokens: 16384
max_tokens: 8192
modalities:
input:
- text
- image
output:
- text
mode: chat
model: PaddlePaddle/PaddleOCR-VL-0.9B
sources:
Expand Down
9 changes: 9 additions & 0 deletions providers/deepinfra/PrunaAI/p-image-Edit.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,12 @@
costs:
- output_cost_per_image: 0.01
region: "*"
modalities:
input:
- text
- image
output:
- image
mode: image
model: PrunaAI/p-image-Edit
sources:
Expand Down
5 changes: 5 additions & 0 deletions providers/deepinfra/PrunaAI/p-image.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,10 @@
costs:
- output_cost_per_image: 0.005
region: "*"
modalities:
input:
- text
output:
- image
mode: image
model: PrunaAI/p-image
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Qwen/Qwen-Image-Edit-Max.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Qwen/Qwen-Image-Edit-Max
sources:
Expand Down
2 changes: 2 additions & 0 deletions providers/deepinfra/Qwen/Qwen-Image-Edit.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,8 @@ costs:
modalities:
input:
- image
output:
- image
mode: image
model: Qwen/Qwen-Image-Edit
sources:
Expand Down
3 changes: 3 additions & 0 deletions providers/deepinfra/Qwen/Qwen-Image-Max.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,9 @@ costs:
region: "*"
modalities:
input:
- text
- image
output:
- image
mode: image
model: Qwen/Qwen-Image-Max
Expand Down
4 changes: 4 additions & 0 deletions providers/deepinfra/Qwen/Qwen3-Embedding-0.6B-batch.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@ costs:
limits:
context_window: 32768
max_input_tokens: 8192
output_vector_size: 1024
modalities:
input:
- text
mode: embedding
model: Qwen/Qwen3-Embedding-0.6B-batch
sources:
Expand Down
4 changes: 3 additions & 1 deletion providers/deepinfra/Qwen/Qwen3-Embedding-0.6B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,12 @@ costs:
region: "*"
limits:
context_window: 32768
output_vector_size: 1024
modalities:
input:
- image
- text
mode: embedding
model: Qwen/Qwen3-Embedding-0.6B
sources:
- https://deepinfra.com/Qwen/Qwen3-Embedding-0.6B/api
- https://huggingface.co/Qwen/Qwen3-Embedding-0.6B
4 changes: 3 additions & 1 deletion providers/deepinfra/Qwen/Qwen3-Embedding-4B-batch.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,12 @@ costs:
region: "*"
limits:
max_input_tokens: 32768
output_vector_size: 2560
modalities:
input:
- image
- text
mode: embedding
model: Qwen/Qwen3-Embedding-4B-batch
sources:
- https://deepinfra.com/Qwen/Qwen3-Embedding-4B-batch/api
- https://huggingface.co/Qwen/Qwen3-Embedding-4B
Loading
Loading