Providers

Sign Up

Phala

United States

Compare

Performance

Models

Browse models available through Phala.

13 models

Phala: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

Modalities

Input

Text

Output

Text

Supported Parameters

-

Pricing

-

Phala: GLM 5.2

zai-org/GLM-5.2

Modalities

Input

Text

Output

Text

Supported Parameters

-

Pricing

-

Phala: DeepSeek V4 Flash

deepseek/deepseek-v4-flash

Modalities

Input

Text

Output

Text

Supported Parameters

-

Pricing

Input Text Tokens: $0.2 / 1M tokens

Output Text Tokens: $0.4 / 1M tokens

Phala: Qwen 3.6 27B

qwen/qwen3.6-27b

Modalities

Input

ImageText

Output

Text

Supported Parameters

-

Pricing

-

Phala: Kimi K2.6

moonshotai/kimi-k2.6

Modalities

Input

ImageTextVideo

Output

Text

Supported Parameters

-

Pricing

-

Phala: Qwen 3.6 35B A3B

qwen/qwen3.6-35b-a3b

Modalities

Input

ImageTextVideo

Output

Text

Supported Parameters

-

Pricing

-

Phala: GLM 5.1

z-ai/glm-5.1

Modalities

Input

-

Output

-

Supported Parameters

-

Pricing

-

Phala: Qwen 3.5 27B

qwen/qwen3.5-27b

Modalities

Input

ImageTextVideo

Output

Text

Supported Parameters

-

Pricing

-

Phala: Qwen 3.5 397B A17B

qwen/qwen3.5-397b-a17b

Modalities

Input

ImageTextVideo

Output

Text

Supported Parameters

-

Pricing

-

Phala: Kimi K2.5

moonshotai/kimi-k2.5

Modalities

Input

ImageTextVideo

Output

Text

Supported Parameters

-

Pricing

-

Phala: DeepSeek V3.2

deepseek/deepseek-v3.2

Modalities

Input

-

Output

-

Supported Parameters

-

Pricing

-

Phala: GPT OSS 120b

openai/gpt-oss-120b

Modalities

Input

Text

Output

Text

Supported Parameters

-

Pricing

-

Phala: GPT OSS 20b

openai/gpt-oss-20b

Modalities

Input

Text

Output

Text

Supported Parameters

-

Pricing

-

Throughput

—

Latency

—

E2E latency

—

Performance metrics will appear after this provider serves gateway traffic.

Token Usage

No Token Usage Yet

Usage over time will appear once this provider receives gateway traffic.