Skip to content

feat(together-ai): update model YAMLs [bot] #1971

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
models-bot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(together-ai): update model YAMLs [bot] #1971

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
1 change: 1 addition & 0 deletions providers/together-ai/Lykon/DreamShaper.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
costs:
- input_cost_per_image: 0.0006
region: "*"
isDeprecated: true
modalities:
input:
- text
Expand Down
6 changes: 3 additions & 3 deletions providers/together-ai/Qwen/Qwen2-1.5B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -8,11 +9,10 @@ modalities:
mode: chat
model: Qwen/Qwen2-1.5B-Instruct
provisioning: provisioned
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://docs.together.ai/docs/dedicated-models
status: active
status: retired
supportedModes:
- chat

# costs: not found in official docs (model is documented only in fine-tuning and dedicated-endpoint model lists; not listed in Together AI's serverless pricing tables)
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2-1.5B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
deprecationDate: "2026-07-29"
isDeprecated: true
limits:
context_window: 131072
modalities:
Expand All @@ -11,6 +13,6 @@ provisioning: serverless
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://www.together.ai/pricing
status: active
status: deprecated
supportedModes:
- chat
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2-7B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 131072
modalities:
Expand All @@ -10,9 +11,10 @@ model: Qwen/Qwen2-7B
provisioning: serverless
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://www.together.ai/pricing
status: active
status: retired
supportedModes:
- completion
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-1.5B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
features:
- function_calling
isDeprecated: true
limits:
context_window: 32768
max_output_tokens: 8192
Expand All @@ -14,10 +15,11 @@ model: Qwen/Qwen2.5-1.5B-Instruct
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct
- https://docs.together.ai/docs/dedicated-models
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- chat
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-1.5B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 131072
modalities:
Expand All @@ -8,8 +9,9 @@ modalities:
mode: completion
model: Qwen/Qwen2.5-1.5B
provisioning: serverless
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- completion
6 changes: 4 additions & 2 deletions providers/together-ai/Qwen/Qwen2.5-32B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
features:
- function_calling
- system_messages
isDeprecated: true
limits:
context_window: 32768 # from fine-tuning supported models page (SFT context length)
context_window: 32768
modalities:
input:
- text
Expand All @@ -13,9 +14,10 @@ model: Qwen/Qwen2.5-32B-Instruct
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/dedicated-models
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- chat
6 changes: 3 additions & 3 deletions providers/together-ai/Qwen/Qwen2.5-32B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 131072
max_output_tokens: 8000
Expand All @@ -12,11 +13,10 @@ model: Qwen/Qwen2.5-32B
provisioning: serverless
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://huggingface.co/Qwen/Qwen2.5-32B
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- completion

# costs not found in official Together AI docs — Qwen/Qwen2.5-32B is offered as a fine-tuning base model only, with no published per-token inference pricing
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-3B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
deprecationDate: "2026-07-29"
features:
- function_calling
- system_messages
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -15,6 +17,6 @@ removeParams:
- reasoning_effort
sources:
- https://docs.together.ai/docs/dedicated-models
status: active
status: deprecated
supportedModes:
- chat
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-3B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -10,8 +11,9 @@ model: Qwen/Qwen2.5-3B
provisioning: serverless
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- completion
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-7B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ features:
- function_calling
- structured_output
- json_output
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -18,8 +19,9 @@ model: Qwen/Qwen2.5-7B-Instruct
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://www.together.ai/models/qwen2-5-7b-instruct-turbo
status: active
status: retired
supportedModes:
- chat
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen2.5-7B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 131072
modalities:
Expand All @@ -8,9 +9,10 @@ modalities:
mode: completion
model: Qwen/Qwen2.5-7B
provisioning: provisioned
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://docs.together.ai/docs/dedicated-models
status: active
status: retired
supportedModes:
- completion
1 change: 1 addition & 0 deletions providers/together-ai/Qwen/Qwen3-0.6B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
features:
- function_calling
- system_messages
- tool_choice
limits:
context_window: 32768
max_output_tokens: 32768
Expand Down
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen3-1.7B-Base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -10,8 +11,9 @@ model: Qwen/Qwen3-1.7B-Base
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://www.together.ai/models/qwen3-1-7b-base
status: active
status: retired
supportedModes:
- completion
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen3-1.7B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
features:
- function_calling
- system_messages
isDeprecated: true
limits:
context_window: 32768
max_output_tokens: 32768
Expand All @@ -15,10 +16,11 @@ model: Qwen/Qwen3-1.7B
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://www.together.ai/models/qwen3-1-7b
- https://huggingface.co/Qwen/Qwen3-1.7B
status: active
status: retired
supportedModes:
- chat
thinking: true
4 changes: 3 additions & 1 deletion providers/together-ai/Qwen/Qwen3-8B-Base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,5 @@
deprecationDate: "2026-07-29"
isDeprecated: true
limits:
context_window: 32768
modalities:
Expand All @@ -13,6 +15,6 @@ removeParams:
sources:
- https://huggingface.co/Qwen/Qwen3-8B-Base
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: deprecated
supportedModes:
- completion
2 changes: 2 additions & 0 deletions providers/together-ai/RunDiffusion/Juggernaut-pro-flux.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@ modalities:
mode: image
model: RunDiffusion/Juggernaut-pro-flux
provisioning: serverless
removeParams:
- reasoning_effort
sources:
- https://www.together.ai/models/juggernaut-pro-flux
status: active
Expand Down
6 changes: 3 additions & 3 deletions providers/together-ai/Wan-AI/Wan2.2-T2V-A14B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,10 @@ modalities:
mode: video
model: Wan-AI/Wan2.2-T2V-A14B
provisioning: serverless
removeParams:
- reasoning_effort
sources:
- https://docs.together.ai/docs/videos-overview
- https://docs.together.ai/reference/create-videos
- https://docs.together.ai/docs/serverless-models
- https://www.together.ai/models/wan-2-2-t2v
status: active
supportedModes:
- video
2 changes: 2 additions & 0 deletions providers/together-ai/deepcogito/cogito-v1-preview-qwen-14B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,8 @@ modalities:
mode: chat
model: deepcogito/cogito-v1-preview-qwen-14B
provisioning: provisioned
removeParams:
- reasoning_effort
sources:
- https://www.together.ai/models/cogito-v1-preview-qwen-14b
- https://huggingface.co/deepcogito/cogito-v1-preview-qwen-14B
Expand Down
2 changes: 2 additions & 0 deletions providers/together-ai/deepcogito/cogito-v1-preview-qwen-32B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ modalities:
mode: chat
model: deepcogito/cogito-v1-preview-qwen-32B
provisioning: provisioned
removeParams:
- reasoning_effort
sources:
- https://www.together.ai/models/cogito-v1-preview-qwen-32b
status: active
Expand Down
4 changes: 3 additions & 1 deletion providers/together-ai/deepseek-ai/DeepSeek-V3-Base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
isDeprecated: true
limits:
context_window: 65536
modalities:
Expand All @@ -10,10 +11,11 @@ model: deepseek-ai/DeepSeek-V3-Base
provisioning: serverless
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://docs.together.ai/docs/inference-models
- https://www.together.ai/pricing
status: active
status: retired
supportedModes:
- completion
6 changes: 4 additions & 2 deletions providers/together-ai/deepseek-ai/DeepSeek-V3.1-Base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
costs:
- input_cost_per_token: 6e-7
output_cost_per_token: 0.0000017
output_cost_per_token: 1.7e-6
region: "*"
isDeprecated: true
limits:
context_window: 131072
modalities:
Expand All @@ -12,10 +13,11 @@ modalities:
mode: completion
model: deepseek-ai/DeepSeek-V3.1-Base
provisioning: provisioned
retirementDate: "2026-07-29"
sources:
- https://together.ai/pricing
- https://docs.together.ai/docs/deepseek-3-1-quickstart
- https://docs.together.ai/docs/fine-tuning-models
status: active
status: retired
supportedModes:
- completion
1 change: 1 addition & 0 deletions providers/together-ai/deepseek-ai/DeepSeek-V3.2-Exp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
features:
- json_output
isDeprecated: true

@cursor cursor Bot Jul 31, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Contradictory model lifecycle status

Medium Severity

These models set isDeprecated: true but leave status: active, which conflicts. In this same PR, peer models also get status set to deprecated or retired with a matching date. Consumers that key off status will still treat these as fully supported.

Additional Locations (2)
Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 1cc823b. Configure here.

limits:
context_window: 163840
modalities:
Expand Down
6 changes: 3 additions & 3 deletions providers/together-ai/google/gemma-3-270m-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
features:
- system_messages
isDeprecated: true
limits:
context_window: 32768
max_input_tokens: 32768
Expand All @@ -13,11 +14,10 @@ model: google/gemma-3-270m-it
provisioning: provisioned
removeParams:
- reasoning_effort
retirementDate: "2026-07-29"
sources:
- https://docs.together.ai/docs/fine-tuning-models
- https://docs.together.ai/docs/dedicated-endpoints/models
status: active
status: retired
supportedModes:
- chat

# costs: not found in official docs — model is offered as a dedicated endpoint / fine-tuning base on Together AI, billed by GPU-hour rather than per-token
1 change: 1 addition & 0 deletions providers/together-ai/kwaivgI/kling-1.6-pro.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
costs:
- input_cost_per_request: 0.32
region: "*"
isDeprecated: true
modalities:
input:
- text
Expand Down
2 changes: 2 additions & 0 deletions providers/together-ai/meta-llama/Llama-3.2-1B-Instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ modalities:
mode: chat
model: meta-llama/Llama-3.2-1B-Instruct
provisioning: provisioned
removeParams:
- reasoning_effort
sources:
- https://www.together.ai/pricing
- https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct
Expand Down
Loading
Loading