Skip to content

feat: Add AI/ML API provider integration #93

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
D1m7asis wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: Add AI/ML API provider integration #93

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
128 changes: 128 additions & 0 deletions internal/providers/configs/aimlapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,128 @@
{
"name": "AI/ML API",
"id": "aimlapi",
"api_key": "$AIMLAPI_API_KEY",
"api_endpoint": "https://api.aimlapi.com/v1",
"type": "openai-compat",
"default_large_model_id": "openai/gpt-5-chat-latest",
"default_small_model_id": "deepseek/deepseek-chat-v3.1",
"models": [
{
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek V3.1",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 8000,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "openai/gpt-5-chat-latest",
"name": "GPT-5 Chat Latest",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 400000,
"default_max_tokens": 16384,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "deepseek/deepseek-reasoner-v3.1",
"name": "DeepSeek Reasoner V3.1",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 64000,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "openai/gpt-4o",
"name": "GPT 4o",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 16384,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "gpt-4o-mini",
"name": "GPT 4o mini",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 16384,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "google/gemini-2.0-flash-exp",
"name": "Gemini 2.0 Flash Experimental",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 1000000,
"default_max_tokens": 8192,
"can_reason": true,
"supports_attachments": true,
"options": {}
},
{
"id": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
"name": "Meta Llama 3.1 70B Instruct Turbo",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 127000,
"can_reason": true,
"supports_attachments": false,
"options": {}
},
{
"id": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"name": "Meta Llama 3.1 8B Instruct Turbo",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 128000,
"default_max_tokens": 127000,
"can_reason": true,
"supports_attachments": false,
"options": {}
},
{
"id": "Qwen/Qwen2.5-72B-Instruct-Turbo",
"name": "Qwen2.5 72B Instruct Turbo",
"cost_per_1m_in": 0,
"cost_per_1m_out": 0,
"cost_per_1m_in_cached": 0,
"cost_per_1m_out_cached": 0,
"context_window": 32000,
"default_max_tokens": 31000,
"can_reason": true,
"supports_attachments": false,
"options": {}
}
]
}
8 changes: 8 additions & 0 deletions internal/providers/providers.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,9 @@ var huggingFaceConfig []byte
//go:embed configs/aihubmix.json
var aiHubMixConfig []byte

//go:embed configs/aimlapi.json
var aiMLAPIConfig []byte

// ProviderFunc is a function that returns a Provider.
type ProviderFunc func() catwalk.Provider

Expand All @@ -77,6 +80,7 @@ var providerRegistry = []ProviderFunc{
deepSeekProvider,
huggingFaceProvider,
aiHubMixProvider,
aiMLAPIProvider,
}

// GetAll returns all registered providers.
Expand Down Expand Up @@ -160,3 +164,7 @@ func huggingFaceProvider() catwalk.Provider {
func aiHubMixProvider() catwalk.Provider {
return loadProviderFromConfig(aiHubMixConfig)
}

func aiMLAPIProvider() catwalk.Provider {
return loadProviderFromConfig(aiMLAPIConfig)
}
2 changes: 2 additions & 0 deletions pkg/catwalk/provider.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ const (
InferenceProviderChutes InferenceProvider = "chutes"
InferenceProviderHuggingFace InferenceProvider = "huggingface"
InferenceAIHubMix InferenceProvider = "aihubmix"
InferenceProviderAIMLAPI InferenceProvider = "aimlapi"
)

// Provider represents an AI provider configuration.
Expand Down Expand Up @@ -95,6 +96,7 @@ func KnownProviders() []InferenceProvider {
InferenceProviderChutes,
InferenceProviderHuggingFace,
InferenceAIHubMix,
InferenceProviderAIMLAPI,
}
}

Expand Down