Model Library Matrix

Point your standard SDK payloads to our absolute endpoint gateway. Swap capabilities instantly by matching strings mapped below.

Endpoint: https://helyxai.space/v1/chat/completions
Model Info Model Slug (API String) Max In / Out Free Plan Limit Dev Plan Limit Market Rate / 1M Action
DeepSeek-V4-Flash
1,049,000 / 384,000 50,000 tokens / day 10,000,000 tokens / day
In: $0.1400 Out: $0.2800
Specs
gemini-3.1-flash-lite
1,048,576 / 65,536 10,000 tokens / day 10,000,000 tokens / day
In: $0.2500 Out: $1.5000
Specs
Gemma4 31B by Google
gemma-4-31B-it
262,000 / 8,192 500,000 tokens / day 100,000,000 tokens / day
In: $0.1200 Out: $0.3500
Specs
GPT 5.6 Luna by Open AI
gpt-5.6-luna
1,050,000 / 128,000 5,000 tokens / day 100,000,000 tokens / day
In: $1.2000 Out: $6.0000
Specs
GPT OSS 120b by Open AI
gpt-oss-120b
128,000 / 8,192 25,000 tokens / day 100,000,000 tokens / day
In: $0.1000 Out: $0.5000
Specs
llama-3.1-8b-instruct
16,384 / 16,384 500,000 tokens / day 100,000,000 tokens / day
In: $0.1000 Out: $0.2500
Specs
MiniMax M3 by MiniMax
MiniMax-M3
131,072 / 1,048,576 25,000 tokens / day 100,000,000 tokens / day
In: $0.3000 Out: $1.2000
Specs
Qwen3 32b by Qwen
Qwen3-32B
131,072 / 8,192 50,000 tokens / day 10,000,000 tokens / day
In: $0.1000 Out: $0.3000
Specs

Unified Payload Interface

Helyx aggregates all distinct text and generation parameters into one single API configuration schema. Swap routes inside code setups instantly without changing payload trees.

payload.py
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://helyxai.space/v1",
    api_key=os.environ.get("HELYX_API_KEY")
)

response = client.chat.completions.create(
    model="DeepSeek-V4-Flash",
    messages=[{"role": "user", "content": "Matrix test."}]
)