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.

Available Models

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

OpenAI GPT-5 Family

OpenAI GPT-4 Family

OpenAI O-Series (Reasoning)

OpenAI GPT-OSS (Open-Weight)

Apache 2.0 licensed open-weight models, hosted on NVIDIA.

Anthropic Claude

Google Gemini

DeepSeek

Qwen

xAI (Grok)

Coming Soon

These models are configured but not yet available (no API keys):

• Mistral: Mistral Large 2, Mistral Medium 3, Codestral, Pixtral Large
• Cohere: Command R+, Command R
• Perplexity: Sonar Pro, Sonar
• Meta: Llama 3.3 70B, Llama 3.1 405B

Image Generation

Model Categories

Models are tagged with capabilities:

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

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.

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")

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`);
}