BoincAi Inference Service
Scalable, OpenAI-compliant AI inference powered by distributed computing.
Getting Started
- Login: Create an account or sign in to your dashboard.
- API Key: Generate a unique API Key from your profile settings.
- Integrate: Use our endpoint with your favorite OpenAI-compatible client.
OpenAI Compliant API
Our service is fully compliant with the OpenAI API specification. You can use any OpenAI client library
by simply changing the base_url to our service endpoint.
The primary endpoint for chat is: /v1/chat/completions
Billing & Usage
Usage is tracked per API Key and billed monthly. Invoicing is handled securely through Stripe.
- No upfront costs or minimum commitments.
- Pay only for the tokens you consume.
- Detailed usage reports available in your dashboard.
Available Models
IBM: Granite 4.0 Micro
ID: granite4:3b-h
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long context tool calling.
- Context: 128k tokens
-
Pricing:
- $0.06/M input tokens
- $0.11/M output tokens
- Features: tools
Google: Gemma 3 4B
ID: gemma3:4b
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.
- Context: 32k tokens
-
Pricing:
- $0.11/M input tokens
- $0.22/M output tokens
- Features: json_mode structured_outputs reasoning
Ministral 3 8B Instruct 2512
ID: ministral-3:8b
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- Context: 32k tokens
-
Pricing:
- $0.15/M input tokens
- $0.15/M output tokens
- Features: tools json_mode
Qwen3 4B Thinking 2507
ID: qwen3-4b-thinking-2507
- Context: 32k tokens
-
Pricing:
- $0.10/M input tokens
- $0.10/M output tokens
- Features: tools json_mode
Devstral Small - 2 - 24b
ID: devstral-small-2-24b-instruct-2512
- Context: 64k tokens
-
Pricing:
- $0.10/M input tokens
- $0.10/M output tokens
- Features: tools json_mode logprobs