Models

BlockRun provides access to models from multiple providers through a unified API.

List Models

GET https://blockrun.ai/api/v1/models

Returns a list of available models with pricing information. The response now includes extended metadata for each model.

Response Fields

Each model object in the response includes:

Example Response

{
  "models": [
    {
      "id": "openai/gpt-5.5",
      "name": "GPT-5.5",
      "description": "OpenAI's flagship — first fully retrained base since GPT-4.5; 1M context, 128K output, native agent + computer use",
      "provider": "openai",
      "inputPrice": 5.00,
      "outputPrice": 30.00,
      "context_window": 1050000,
      "max_output": 128000,
      "categories": ["chat", "coding", "vision"],
      "available": true
    }
  ]
}

Available Models (33 visible)

All prices shown are provider rates. BlockRun adds a 5% platform fee to cover infrastructure costs.

OpenAI GPT-5.5 Family

Released 2026-04-23 — first fully retrained base since GPT-4.5.

OpenAI GPT-5.4 Family

OpenAI GPT-5 Family

OpenAI O-Series (Reasoning)

Anthropic Claude

Google Gemini

DeepSeek

Z.AI

Moonshot

K2.6 is multi-modal (vision + text input) and returns reasoning_content on completions. K2.5 is still routable but superseded.

MiniMax

NVIDIA (Free Tier)

Apache 2.0 licensed open-weight models, hosted free by NVIDIA.

Image Generation

Video Generation

Model Categories

Each model includes a categories array in the API response. Categories indicate model capabilities:

• chat - General conversation
• reasoning - Complex problem-solving
• coding - Code generation and analysis
• vision - Image understanding

Filter models by category:

models = client.list_models()
reasoning_models = [m for m in models if "reasoning" in m.get("categories", [])]

Pricing

Prices are per 1 million tokens. Your actual cost depends on:

1. Input tokens - Length of your prompt and context
2. Output tokens - Length of the model's response
3. Platform fee - 5% added to provider rates

The SDK calculates the exact price before each request.

Want to save 78% automatically? ClawRouter routes each request to the cheapest model that can handle it.

Example

Python:

from blockrun_llm import LLMClient

client = LLMClient()
models = client.list_models()

for model in models:
    print(f"{model['id']}: ${model['inputPrice']}/M input, context: {model['context_window']}")
    print(f"  Categories: {', '.join(model.get('categories', []))}")

TypeScript:

import { LLMClient } from '@blockrun/llm';

const client = new LLMClient({ privateKey: '0x...' });
const models = await client.listModels();

for (const model of models) {
  console.log(`${model.id}: $${model.inputPrice}/M input, context: ${model.contextWindow}`);
  console.log(`  Categories: ${model.categories.join(', ')}`);
}