Models
anthropic/claude-opus-4.7anthropic/claude-opus-4.6anthropic/claude-sonnet-4.6anthropic/claude-opus-4.5anthropic/claude-sonnet-4.5anthropic/claude-haiku-4.5anthropic/claude-sonnet-4anthropic/claude-3.5-haiku
openai/gpt-5.5openai/gpt-5.4-proopenai/gpt-5.4openai/gpt-5.3-chatopenai/gpt-5.4-nanoopenai/gpt-5.4-miniopenai/gpt-5.1
google/gemini-3.1-pro-previewgoogle/gemini-3.1-flash-lite-previewgoogle/gemini-3-pro-image-previewgoogle/gemini-2.5-flashgoogle/gemini-2.5-pro
z-ai/glm-5.1
deepseek/deepseek-v4-flashdeepseek/deepseek-v4-prodeepseek/deepseek-v3.2
minimax/minimax-m2.7
moonshotai/kimi-k2.5LLM API — Access 290+ AI Models
Compare pricing, speed, and performance for GPT-5.5, Claude Opus 4.7, Gemini 3, Qwen 3, DeepSeek R1, Llama 4, Grok 4, and more. Unified OpenAI-compatible API with no cold starts and transparent per-token pricing.
Why Choose WaveSpeedAI for LLMs
290+ Models
GPT, Claude, Gemini, Qwen, DeepSeek, Llama, Grok, Mistral — all in one unified API.
OpenAI Compatible
Drop-in replacement for OpenAI SDK. Switch models with one line of code.
No Cold Starts
Models are always warm. First-token latency measured in milliseconds.
Pay Per Token
Transparent pricing with no subscriptions. Only pay for what you use.
Frequently Asked Questions
How does pricing work?+
You pay per token — input and output tokens are priced separately. No subscriptions, no minimum commitments. Check the pricing table above for per-model rates.
Is the API compatible with OpenAI?+
Yes. Our API is fully OpenAI-compatible. Use the OpenAI SDK and just change the base URL and API key.
What models are available?+
We offer 290+ models from 30+ providers including OpenAI GPT-5.5 & GPT-5.4, Anthropic Claude Opus 4.7, Google Gemini 3, Qwen 3, DeepSeek R1 & V3, Meta Llama 4, xAI Grok 4, Mistral, and many more.
Are there rate limits?+
Rate limits depend on your plan. Free tier includes generous limits for testing. Paid plans offer higher throughput.