Models

Available models, capabilities, and specifications

Models

PolarGrid serves open-weight models on GPU-accelerated edge infrastructure. All models are available via our OpenAI-compatible API.

PolarGrid runs open-source models optimized for low-latency edge inference. These models are selected for speed and efficiency in real-time applications like voice AI. For workloads that require large cloud-hosted reasoning models (e.g., GPT-4, Gemini, Claude), use those providers directly — PolarGrid does not proxy requests to third-party APIs.

LLM Models

Qwen 3.5 27B

Parameters	27B
Quantization	FP8
Max context	8,192 tokens
License	Apache 2.0
Pricing	$0.165 / 1M input tokens,$0.255 / 1M output tokens

General-purpose large language model with strong performance across reasoning, coding, and multilingual tasks. Our largest LLM offering, suitable for complex workloads where quality is the priority.

Endpoint: POST /v1/chat/completions with "model": "qwen-3.5-27b"

---

Qwen 3.5 9B

Parameters	9B
Quantization	FP8
Max context	8,192 tokens
License	Apache 2.0
Pricing	$0.055 / 1M input tokens,$0.085 / 1M output tokens

Fast, cost-efficient model for tasks where latency and throughput matter more than peak quality. Strong for classification, extraction, summarization, and simple generation.

Endpoint: POST /v1/chat/completions with "model": "qwen-3.5-9b"

---

Speech-to-Text Models

Whisper Large V3 Turbo

Parameters	809M
License	Apache 2.0
Pricing	$0.004 / min

OpenAI’s Whisper model optimized for speed. Supports multilingual transcription with high accuracy.

Endpoint: POST /v1/audio/transcriptions with "model": "whisper-large-v3-turbo"

---

Cohere Transcribe

Parameters	2B
License	Apache 2.0
Supported languages	English, French, German, Italian, Spanish, Portuguese, Greek, Dutch, Polish, Chinese, Japanese, Korean, Vietnamese, Arabic
Pricing	$0.004 / min

High-accuracy multilingual transcription with support for 14 languages. Supports punctuation toggling.

Endpoint: POST /v1/audio/transcriptions with "model": "cohere-transcribe-03-2026"

---

Text-to-Speech Models

Hume AI TADA

Parameters	3B
License	CC-BY-NC-4.0
Output	24 kHz mono — caller picks the container via response_format (pcm, wav, or mp3)
Supported languages	English, French, German, Spanish, Italian, Portuguese, Polish, Japanese, Arabic, Chinese
Capabilities	Voice cloning, speed control
Streaming	✓ chunked HTTP, pcm + opus (per-token via decoupled Triton handler; speed not honored in streaming mode)
Pricing	$0.008 / min

Expressive text-to-speech with voice cloning support. Generates natural-sounding speech across 10 languages.

Endpoint: POST /v1/audio/speech with "model": "tada-3b-ml"

---

Kokoro 82M

Parameters	82M
License	Apache 2.0
Streaming	✓ chunked HTTP, pcm + opus
Pricing	$0.008 / min

Lightweight, fast text-to-speech model. Ideal for low-latency voice applications where speed is critical.

Endpoint: POST /v1/audio/speech with "model": "kokoro-82m"

---

Voice Pipeline

PersonaPlex

Parameters	7B
Pipeline	STT + LLM + TTS (end-to-end)
Pricing	$0.070 / min

Integrated voice-to-voice pipeline that combines speech recognition, language model reasoning, and speech synthesis into a single low-latency stream. Billed by wall-clock duration.

See the PersonaPlex guide for setup details.

---

Performance

Latency benchmarks per model and region are actively being measured. Performance depends on:

• Client proximity to the nearest edge region
• Model size — smaller models have lower TTFT and higher throughput
• Request complexity — token count, audio length, streaming vs. batch

The autorouter optimizes for the lowest-latency region automatically. For detailed performance data, contact us.

Custom Models

Enterprise customers can deploy custom fine-tuned models on PolarGrid infrastructure. PolarGrid handles provisioning and loading — contact us to discuss your model requirements.

For custom model deployments, contact [e-mail].

Pricing

See full pricing details and volume discounts

API Reference

Full endpoint documentation