Any Llm

Any Llm

Playground

Any LLM is a versatile large language model for text generation, comprehension, and diverse NLP tasks such as chat and summarization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Any LLM

Any LLM is a unified large language model gateway that provides access to multiple state-of-the-art AI models through a single interface. Chat, reason, and generate text using models from Google, OpenAI, Anthropic, and more — all in one place.

Why It Stands Out

• Multi-model access: Choose from a variety of leading AI models including Gemini, GPT, Claude, and more.
• Unified interface: One consistent API and playground for all supported models.
• System prompt support: Customize model behavior with custom instructions.
• Reasoning mode: Enable step-by-step reasoning for complex problem-solving tasks.
• Priority control: Choose between latency-optimized or quality-optimized responses.
• Flexible parameters: Fine-tune temperature, max tokens, and other settings.
• Prompt Enhancer: Built-in AI-powered prompt optimization for better results.

Parameters

Supported Models

• google/gemini-2.5-flash
• anthropic/claude-3.5-sonnet
• openai/gpt-5-chat
• And more…

How to Use

1. Write your prompt — enter your question or instruction. Use the Prompt Enhancer for AI-assisted optimization.
2. Add a system prompt (optional) — provide custom instructions to guide the model’s behavior.
3. Enable reasoning (optional) — turn on for step-by-step explanations.
4. Select priority — choose “latency” for faster responses or “quality” for better outputs.
5. Adjust parameters (optional) — set temperature and max_tokens as needed.
6. Select a model — choose from available LLMs.
7. Click Run and receive your response.

Best Use Cases

• General Q&A — Get answers to questions across any topic.
• Writing Assistance — Draft emails, articles, reports, and creative content.
• Code Generation — Write, debug, and explain code in multiple languages.
• Research & Analysis — Summarize documents, analyze data, and extract insights.
• Reasoning Tasks — Solve math problems, logic puzzles, and complex reasoning challenges.
• Brainstorming — Generate ideas, outlines, and creative concepts.

Pro Tips for Best Quality

• Use system prompts to define the model’s role, tone, and output format.
• Enable reasoning for math, logic, and multi-step problems.
• Lower temperature (0.1–0.3) for factual, consistent answers.
• Higher temperature (0.7–1.0) for creative, varied responses.
• Choose “latency” priority for quick interactions, “quality” for important tasks.
• Experiment with different models to find the best fit for your use case.

Notes

• Processing time varies based on model selection and prompt complexity.
• Please ensure your prompts comply with usage guidelines.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/any-llm" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "reasoning": false,
    "priority": "latency",
    "model": "google/gemini-2.5-flash",
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"