Available Models

Explore the AI models available through GonkaGate with transparent pricing.

Available Models

Models are dynamically fetched from the Gonka Network. The list updates as new models become available.

View Live Models — See all currently available models

You can also fetch models programmatically:

list_models.py

import requests

response = requests.get(
    "https://api.gonkagate.com/v1/models",
    headers={"Authorization": "Bearer your-gonkagate-api-key"}
)

models = response.json()["data"]

for model in models:
    price_per_m = float(model["pricing"]["prompt"]) * 1_000_000
    print(f"{model['name']}: ${price_per_m:.2f}/1M tokens")

Model Response Schema

Each model includes the following information:

model-types.ts

interface Model {
  id: string;                    // e.g., "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8"
  name: string;                  // Human-readable name, e.g., "Qwen3 235B A22B Instruct"
  description: string | null;    // Model description (may be null)
  context_length: number | null; // Max context window in tokens
  pricing: Pricing;              // Current pricing per 1M tokens
}

interface Pricing {
  input: number;                 // USD per 1M input tokens
  output: number;                // USD per 1M output tokens
}

Pricing

During Grace Period: ~$0.0032 per 1M tokens for all models. Same price for input and output tokens.

Grace Period Active

All models are currently priced at ~$0.0032/1M tokens. This will transition to on-chain dynamic pricing in the future. Plus our fees: 5% deposit + 10% usage.

models-response.json

{
  "data": [
    {
      "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
      "name": "Qwen3 235B A22B Instruct 2507 FP8",
      "description": "A powerful 235B parameter model for complex reasoning tasks.",
      "context_length": 131072,
      "pricing": {
        "input": 0.35,
        "output": 0.35
      }
    },
    {
      "id": "Qwen/Qwen2.5-7B-Instruct",
      "name": "Qwen2 5 7B Instruct",
      "description": null,
      "context_length": 32768,
      "pricing": {
        "input": 0.02,
        "output": 0.02
      }
    }
  ]
}

Using Models in Requests

Specify the model ID in your API requests:

request-body.json

{
  "model": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  "messages": [
    { "role": "user", "content": "Hello!" }
  ]
}

Model Selection Tips

Choose the right model for your use case:

For complex tasks — Use large models (235B, V3) for coding, analysis, and complex reasoning tasks.
For fast responses — Use small models (7B, 8B) for simple tasks requiring quick, cost-effective responses.
Consider context length — For long conversations, choose models with larger context windows (128K+ tokens).