# Qwen3.8 2.4T-A95B - Core.Today AI API

> Qwen3.8 2.4T-A95B served through the OpenRouter aggregator - the open-weight sparse mixture-of-experts variant of Qwen3.8 Max, with 95B active parameters out of 2.4T total. Text-only reasoning model with a 1M-token context and up to 262K output tokens, billed at OpenRouter's actual usage cost.

- **Provider**: Alibaba Qwen
- **Model ID**: qwen/qwen3.8-2.4t-a95b
- **Category**: LLM
- **Credits**: 7 per 1K tokens (avg, estimate)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 262K tokens
- **Training Cutoff**: Not published
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI

### Capabilities
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 3,716 credits ($2.48)
- **Output Tokens**: 11,148 credits ($7.43)
- **Cached Tokens**: 464.5 credits ($0.31)

## Features
- Open-weight sparse MoE - 95B active / 2.4T total parameters
- 1M-token context window with up to 262K output tokens
- OpenAI-compatible API (chat completions) via /llm/openrouter/v1
- Prompt caching with discounted cache reads
- Billed at OpenRouter's actual usage.cost - listed rates are estimates

## Use Cases
- Long-context reasoning over large document sets
- Coding agents and long-running tool-use workflows
- Open-weight alternative to Qwen3.8 Max for text-only workloads

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/openrouter/v1/chat/completions

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **model**: string - Model ID in vendor/model form, e.g. "qwen/qwen3.8-2.4t-a95b".
- **messages**: array - Chat messages in OpenAI format (system/user/assistant roles).

### Optional
- **temperature**: number (default: 0.7) - Sampling temperature (0-2).
- **max_tokens**: integer (default: 2048) - Maximum completion tokens.
- **stream**: boolean (default: false) - Stream the response as server-sent events.

## Examples

### Chat completion
OpenAI-compatible chat completion request via OpenRouter
```json
{
  "model": "qwen/qwen3.8-2.4t-a95b",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the attached report in 5 bullets."
    }
  ],
  "max_tokens": 1024
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openrouter/v1
- Charged at OpenRouter's usage.cost x 1,858 credits/USD - the listed rates are estimates and may lag OpenRouter price changes
- Text-only - it does not accept images; use qwen/qwen3.8-max when you need vision input at the same price point

## Documentation
https://openrouter.ai/qwen/qwen3.8-2.4t-a95b