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 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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "reasoning": false,
  "priority": "latency",
  "model": "google/gemini-2.5-flash"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/any-llm" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters