# AI Large Language Models (LLM) API

> Access leading LLM models — Gemini 3.5, Claude 4.8, GPT 5.5, Grok and more — through a single, credit-based unified MuApi.ai endpoint.

## Overview

MuApi gives you a unified API to query all major Large Language Models (LLMs) in production. Send a message prompt, get back a completion response or a live stream SSE, and control parameters like reasoning depth and web search — all with credit-based pricing on a single, shared credit balance.

- Access Gemini, Claude, GPT, Grok, Qwen, Llama, DeepSeek and more via one endpoint
- Support for standard async execution and real-time streaming
- Credit-based pay-as-you-go pricing with no mandatory monthly commitments
- Unified JSON schema for chat, reasoning, and document parsing

## API Pattern

Every model in this category uses the same submit-then-poll API:

```http
POST https://api.muapi.ai/api/v1/{model}
x-api-key: YOUR_API_KEY
Content-Type: application/json
```

Response: `{ "request_id": "abc123", "status": "processing" }`. Poll `GET https://api.muapi.ai/api/v1/predictions/{request_id}/result` until `status` is `completed` — the result URLs are in the `outputs[]` array. Optionally pass `?webhook=https://your-server` on the submit call to receive a callback instead of polling.

Get an API key at https://muapi.ai/access-keys.

## Quick Start

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gpt-5-5 \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Explain quantum computing in simple terms."}' | jq -r .request_id)

# 2. Poll
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

## Models in This Category

- [gemini-3-5-flash](https://muapi.ai/playground/gemini-3-5-flash): Gemini 3.5 Flash is a high-speed, multimodal language model built for real-time text generation, supporting text and image inputs natively. Token-based pricing…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-3-5-flash`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-3-5-flash/llms.txt
  - Cost: 0.000 credits per call
- [claude-sonnet-4-6](https://muapi.ai/playground/claude-sonnet-4-6): Claude Sonnet 4.6 delivers strong reasoning, advanced coding, and native computer-use functionality. Supports text and image inputs with up to 1M token context…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-sonnet-4-6`
  - Per-model llms.txt: https://muapi.ai/playground/claude-sonnet-4-6/llms.txt
- [gpt-codex](https://muapi.ai/playground/gpt-codex): OpenAI GPT Codex delivers advanced coding capabilities with scalable reasoning depth. Supports multiple model variants (gpt-5-codex through gpt-5.4-codex) and…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-codex`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-codex/llms.txt
- [claude-fable-5](https://muapi.ai/playground/claude-fable-5): Claude Fable 5 is the latest flagship model from Anthropic. Supports text and image inputs with advanced reasoning and creative capabilities. Token-based prici…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-fable-5`
  - Per-model llms.txt: https://muapi.ai/playground/claude-fable-5/llms.txt
- [gemini-3-flash](https://muapi.ai/playground/gemini-3-flash): Gemini 3 Flash is a fast, multimodal language model for real-time text generation. Supports text and image inputs, function calling, and Google Search groundin…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-3-flash`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-3-flash/llms.txt
  - Cost: 0.001 credits per call
- [gemini-2-5-flash](https://muapi.ai/playground/gemini-2-5-flash): Gemini 2.5 Flash is Google's high-speed multimodal language model, optimized for rapid text generation, real-time image understanding, and high-frequency tasks…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-2-5-flash`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-2-5-flash/llms.txt
  - Cost: 0.000 credits per call
- [claude-opus-4-8](https://muapi.ai/playground/claude-opus-4-8): Claude Opus 4.8 is Anthropic's most capable model for complex coding, long-context reasoning, and agentic workflows. Supports text and image inputs. Token-base…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-opus-4-8`
  - Per-model llms.txt: https://muapi.ai/playground/claude-opus-4-8/llms.txt
- [claude-haiku-4-5](https://muapi.ai/playground/claude-haiku-4-5): Claude Haiku 4.5 is Anthropic's fastest and most cost-effective model, designed for high-frequency queries, simple tasks, and near-instant response times. Supp…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-haiku-4-5`
  - Per-model llms.txt: https://muapi.ai/playground/claude-haiku-4-5/llms.txt
- [gpt-5-5](https://muapi.ai/playground/gpt-5-5): GPT 5.5 is OpenAI's state-of-the-art flagship reasoning model for high-complexity problems. Supports image and file uploads, system prompts, web search capabil…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-5-5`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-5-5/llms.txt
- [gpt-5-4](https://muapi.ai/playground/gpt-5-4): GPT-5.4 delivers powerful reasoning, coding, and professional knowledge work. Supports multimodal inputs (text and image) with adjustable reasoning depth. Toke…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-5-4`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-5-4/llms.txt
- [claude-opus-4-6](https://muapi.ai/playground/claude-opus-4-6): Claude Opus 4.6 is Anthropic's most capable model for complex coding, long-context reasoning, and agentic workflows. Supports text and image inputs. Token-base…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-opus-4-6`
  - Per-model llms.txt: https://muapi.ai/playground/claude-opus-4-6/llms.txt
- [claude-sonnet-4-5](https://muapi.ai/playground/claude-sonnet-4-5): Claude Sonnet 4.5 is Anthropic's state-of-the-art model offering high intelligence, speed, and efficiency for code generation, writing, and logical analysis. S…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-sonnet-4-5`
  - Per-model llms.txt: https://muapi.ai/playground/claude-sonnet-4-5/llms.txt
- [claude-opus-4-5](https://muapi.ai/playground/claude-opus-4-5): Claude Opus 4.5 is Anthropic's highly capable model for complex coding, long-context reasoning, and agentic workflows. Supports text and image inputs. Token-ba…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-opus-4-5`
  - Per-model llms.txt: https://muapi.ai/playground/claude-opus-4-5/llms.txt
- [gemini-2-5-pro](https://muapi.ai/playground/gemini-2-5-pro): Gemini 2.5 Pro is Google's advanced multimodal reasoning model, optimized for complex coding, logical tasks, and deep analysis. Supports text and image inputs.…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-2-5-pro`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-2-5-pro/llms.txt
  - Cost: 0.000 credits per call
- [gpt-5-2](https://muapi.ai/playground/gpt-5-2): GPT 5.2 is a lightweight reasoning model with fast response times and deep coding capabilities. Supports image inputs, system prompts, web search capabilities,…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gpt-5-2`
  - Per-model llms.txt: https://muapi.ai/playground/gpt-5-2/llms.txt
- [gemini-3-5-flash-openai](https://muapi.ai/playground/gemini-3-5-flash-openai): Gemini 3.5 Flash (OpenAI-compatible) is a high-speed, multimodal language model built for real-time text generation, supporting text and image inputs natively.…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-3-5-flash-openai`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-3-5-flash-openai/llms.txt
  - Cost: 0.000 credits per call
- [gemini-3-pro](https://muapi.ai/playground/gemini-3-pro): Gemini 3 Pro is Google's powerful multimodal reasoning model, designed for complex problem solving, coding, and logical tasks. Supports text and image inputs.…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-3-pro`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-3-pro/llms.txt
  - Cost: 0.001 credits per call
- [claude-opus-4-7](https://muapi.ai/playground/claude-opus-4-7): Claude Opus 4.7 is Anthropic's highly capable model for complex coding, long-context reasoning, and agentic workflows. Supports text and image inputs. Token-ba…
  - Endpoint: `POST https://api.muapi.ai/api/v1/claude-opus-4-7`
  - Per-model llms.txt: https://muapi.ai/playground/claude-opus-4-7/llms.txt
- [generate-social-video-script](https://muapi.ai/playground/generate-social-video-script): Generate viral short-form video scripts for social media based on a topic and niche.
  - Endpoint: `POST https://api.muapi.ai/api/v1/generate-social-video-script`
  - Per-model llms.txt: https://muapi.ai/playground/generate-social-video-script/llms.txt
  - Cost: 0.100 credits per call
- [gemini-3-1-pro](https://muapi.ai/playground/gemini-3-1-pro): Gemini 3.1 Pro is Google's next-generation multimodal model, optimized for complex reasoning, planning, coding, and multi-turn conversation. Supports text and…
  - Endpoint: `POST https://api.muapi.ai/api/v1/gemini-3-1-pro`
  - Per-model llms.txt: https://muapi.ai/playground/gemini-3-1-pro/llms.txt
  - Cost: 0.001 credits per call

## FAQ

**Which LLM model is best?**

GPT 5.5 and Claude Opus 4.8 are the best for deep logic, complex coding, and multi-step reasoning. Gemini 3.5 Flash is highly optimized for rapid, real-time, low-latency applications. MuApi hosts all of them so you can benchmark quality vs. cost dynamically.

**Do you support streaming?**

Yes! Every LLM model has a streaming endpoint (e.g. `POST /api/v1/{model}/stream`) that pushes Server-Sent Events (SSE) for near-instant rendering in chat bubbles.

## Agent Integration

MuApi ships an MCP server so agents (Claude Code, Cursor, custom) can call every model in this category as a tool:

```bash
npm install -g muapi-cli
muapi auth login
muapi mcp serve  # exposes all MuApi models as MCP tools
```

## Resources

- Category page: https://muapi.ai/playground/group/llm
- Global llms.txt: https://muapi.ai/llms.txt
- API docs: https://muapi.ai/docs
- OpenAPI spec: https://api.muapi.ai/openapi.json