Deployments

Model Catalog

All models deploy to a dedicated T4 GPU runtime. Each endpoint is OpenAI-compatible — no SDK changes needed.

Note: Model weights are pulled on first deployment (~2–5 min). Subsequent starts from the same region are faster as the container image is cached.
LLaMA 3 8B InstructPopular
meta-llama/Llama-3-8B-Instruct
Text Generation

Meta's LLaMA 3 8B — fast, capable, OpenAI-compatible. Best balance of quality and speed for production chat APIs.

GPU: T4
CPU: 8 vCPU
Memory: 32 GB
Port: 11434
Model name: llama3:8b
bricqs deploy my-api --model meta-llama/Llama-3-8B-Instruct
Mistral 7B Instruct
mistralai/Mistral-7B-Instruct-v0.3
Text Generation

Mistral 7B — fast, open-weights, great for production. Slightly smaller memory footprint than LLaMA 3.

GPU: T4
CPU: 8 vCPU
Memory: 24 GB
Port: 11434
Model name: mistral:7b
bricqs deploy my-api --model mistralai/Mistral-7B-Instruct-v0.3
Phi-3 Mini InstructLow cost
microsoft/phi-3-mini-4k-instruct
Text Generation

Microsoft Phi-3 Mini — the most capable small model. Very low cost, ideal for high-volume workloads where speed matters more than raw capability.

GPU: T4
CPU: 4 vCPU
Memory: 16 GB
Port: 11434
Model name: phi3:mini
bricqs deploy my-api --model microsoft/phi-3-mini-4k-instruct
Mixtral 8×7B InstructHigh quality
mistralai/Mixtral-8x7B-Instruct
Text Generation

Mixture-of-experts architecture — near GPT-4 quality on many benchmarks. Quantized to run on a single T4.

GPU: T4
CPU: 8 vCPU
Memory: 48 GB
Port: 11434
Model name: mixtral:8x7b
bricqs deploy my-api --model mistralai/Mixtral-8x7B-Instruct
Whisper Large v3
openai/whisper-large-v3
Speech to Text

OpenAI's Whisper — state-of-the-art speech recognition in 99 languages. Returns timestamped transcripts.

GPU: T4
CPU: 4 vCPU
Memory: 16 GB
Port: 8000
bricqs deploy my-api --model openai/whisper-large-v3

OpenAI compatibility

All text-generation models expose an OpenAI-compatible API at /v1/chat/completions. The model name in the request body should match the Ollama model name shown above (e.g. llama3:8b, not the full catalog ID).

Pricing

GPU deployments are billed by uptime at $0.526/hour per GPU replica. Deployments configured with min_replicas: 0 scale to zero when idle and incur no charges. Set a budget cap per deployment from the dashboard to avoid surprises.