Skip to content

feat(venice): add additional models to Venice.ai provider #112

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

feat(venice): add additional models to Venice.ai provider #112

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
102 changes: 99 additions & 3 deletions internal/providers/configs/venice.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"api_key": "$VENICE_API_KEY",
"api_endpoint": "https://api.venice.ai/api/v1",
"default_large_model_id": "qwen3-235b:strip_thinking_response=true",
"default_small_model_id": "mistral-31-24b",
"default_small_model_id": "llama-3.2-3b",
"models": [
{
"id": "qwen3-235b:strip_thinking_response=true",
Expand Down Expand Up @@ -43,11 +43,47 @@
"can_reason": false,
"supports_attachments": true
},
{
"id": "llama-3.1-405b",
"name": "Llama 3.1 405B",
"cost_per_1m_in": 0.5,
"cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "llama-3.1-70b",
"name": "Llama 3.1 70B",
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "llama-3.1-8b",
"name": "Llama 3.1 8B",
"cost_per_1m_in": 0.1,
"cost_per_1m_out": 0.1,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
Comment on lines +71 to +79
Copy link

Copilot AI Nov 24, 2025

Choose a reason for hiding this comment

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

All newly added Llama 3.1 models (8B, 70B, 405B) have 'can_reason' set to true, but the existing Llama 3.2 3B and Llama 3.3 70B models have 'can_reason' set to false. This inconsistency is unclear - verify whether the reasoning capability designation is correct across all Llama model versions, as Llama 3.1 and 3.2 are similar model families.

Copilot uses AI. Check for mistakes.
"supports_attachments": false
},
{
"id": "llama-3.2-3b",
"name": "Llama 3.2 3B",
"cost_per_1m_in": 0.15,
"cost_per_1m_out": 0.6,
"cost_per_1m_in": 0.05,
"cost_per_1m_out": 0.05,
Comment on lines +85 to +86
Copy link

Copilot AI Nov 24, 2025

Choose a reason for hiding this comment

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

The pricing for Llama 3.2 3B has been reduced from 0.15/0.6 to 0.05/0.05. This represents a 3x reduction in input costs and 12x reduction in output costs. Verify this significant pricing change is accurate with Venice.ai's current pricing, as such a substantial decrease could impact cost calculations for users.

Suggested change
"cost_per_1m_in": 0.05,
"cost_per_1m_out": 0.05,
"cost_per_1m_in": 0.15,
"cost_per_1m_out": 0.6,

Copilot uses AI. Check for mistakes.
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 131072,
Expand All @@ -66,6 +102,66 @@
"default_max_tokens": 32000,
"can_reason": false,
"supports_attachments": false
},
{
"id": "deepseek-coder-v2",
"name": "Deepseek Coder V2",
"cost_per_1m_in": 0.3,
"cost_per_1m_out": 0.3,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "qwen-32b",
"name": "Qwen 32B",
"cost_per_1m_in": 0.2,
"cost_per_1m_out": 0.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "qwen-72b",
"name": "Qwen 72B",
"cost_per_1m_in": 0.4,
"cost_per_1m_out": 0.4,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "mistral-nemo",
"name": "Mistral Nemo",
"cost_per_1m_in": 0.2,
"cost_per_1m_out": 0.2,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
},
{
"id": "hermes-3-405b",
"name": "Hermes 3 405B",
"cost_per_1m_in": 0.5,
"cost_per_1m_out": 0.5,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 4096,
"can_reason": true,
"supports_attachments": false
}
]
}