Seedream 5.0 Pro is LIVE | Try in Image Generator →

Dashboard Explore AI GeneratorHot Desktop App

LLM

Settings

Models

Featured

All Models (93)

Agent setup

New

openai/gpt-5.6-sol

Input$5.0/Mt

Output$30.0/Mt

Context1,050,000

LLMVisionTool Use

New5% off

anthropic/claude-opus-4.8

Input$5.0/Mt$4.8/Mt

Output$25.0/Mt$23.8/Mt

Context1,000,000

LLMVisionTool Use

New5% off

anthropic/claude-opus-4.7

Input$5.0/Mt$4.8/Mt

Output$25.0/Mt$23.8/Mt

Context1,000,000

LLMVisionTool Use

New5% off

anthropic/claude-opus-4.6

Input$5.0/Mt$4.8/Mt

Output$25.0/Mt$23.8/Mt

Context1,000,000

LLMVisionTool Use

New

anthropic/claude-fable-5

Input$10.0/Mt

Output$50.0/Mt

Context1,000,000

LLMVisionTool Use

New

anthropic/claude-sonnet-5

Input$2.0/Mt

Output$10.0/Mt

Context1,000,000

LLMVisionTool Use

New5% off

anthropic/claude-sonnet-4.6

Input$3.0/Mt$2.8/Mt

Output$15.0/Mt$14.3/Mt

Context1,000,000

LLMVisionTool Use

New5% off

anthropic/claude-opus-4.5

Input$5.0/Mt$4.8/Mt

Output$25.0/Mt$23.8/Mt

Context200,000

LLMVisionTool Use

New5% off

anthropic/claude-sonnet-4.5

Input$3.0/Mt$2.8/Mt

Output$15.0/Mt$14.3/Mt

Context1,000,000

LLMVisionTool Use

New5% off

anthropic/claude-haiku-4.5

Input$1.0/Mt$0.95/Mt

Output$5.0/Mt$4.8/Mt

Context200,000

LLMVisionTool Use

New

moonshotai/kimi-k3

Input$3.0/Mt

Output$15.0/Mt

Context1,048,576

LLMVisionTool Use

New

z-ai/glm-5.2

Input$1.4/Mt

Output$4.4/Mt

Context1,048,576

LLMTool Use

New

openai/gpt-5.6-terra

Input$2.5/Mt

Output$15.0/Mt

Context1,050,000

LLMVisionTool Use

New

openai/gpt-5.6-luna

Input$1.0/Mt

Output$6.0/Mt

Context1,050,000

LLMVisionTool Use

NewTiered pricing

openai/gpt-5.5

Input$5.0/Mt

Output$30.0/Mt

Context1,050,000

LLMVisionTool Use

NewTiered pricing

openai/gpt-5.4-pro

Input$30.0/Mt

Output$180.0/Mt

Context1,050,000

LLMVisionTool Use

NewTiered pricing

openai/gpt-5.4

Input$2.5/Mt

Output$15.0/Mt

Context1,050,000

LLMVisionTool Use

New

openai/gpt-5.3-chat

Input$1.8/Mt

Output$14.0/Mt

Context128,000

LLMVisionTool Use

New

openai/gpt-5.4-nano

Input$0.20/Mt

Output$1.3/Mt

Context400,000

LLMVisionTool Use

New

openai/gpt-5.4-mini

Input$0.75/Mt

Output$4.5/Mt

Context400,000

LLMVisionTool Use

New

openai/gpt-5.1

Input$1.3/Mt

Output$10.0/Mt

Context400,000

LLMVisionTool Use

NewTiered pricing

google/gemini-3.1-pro-preview

Input$2.0/Mt

Output$12.0/Mt

Context1,048,576

LLMVisionAudio InTool Use

New

google/gemini-3.5-flash

Input$1.5/Mt

Output$9.0/Mt

Context1,048,576

LLMVisionAudio InTool Use

New

google/gemini-3.1-flash-lite

Input$0.25/Mt

Output$1.5/Mt

Context1,048,576

LLMVisionAudio InTool Use

New

google/gemini-3-pro-image-preview

Input$2.0/Mt

Output$12.0/Mt

Context65,536

LLMVisionImage Out

New

google/gemini-2.5-flash

Input$0.30/Mt

Output$2.5/Mt

Context1,048,576

LLMVisionAudio InTool Use

NewTiered pricing

google/gemini-2.5-pro

Input$1.3/Mt

Output$10.0/Mt

Context1,048,576

LLMVisionAudio InTool Use

New

qwen/qwen3.7-max

Input$2.5/Mt

Output$7.5/Mt

Context1,000,000

LLMTool Use

New

deepseek/deepseek-v4-flash

Input$0.17/Mt

Output$0.34/Mt

Context1,048,576

LLMTool Use

New

deepseek/deepseek-v4-pro

Input$1.8/Mt

Output$3.7/Mt

Context1,048,576

LLMTool Use

New

deepseek/deepseek-v3.2

Input$0.26/Mt

Output$0.38/Mt

Context163,840

LLMTool Use

NewTiered pricing

minimax/minimax-m3

Input$0.60/Mt

Output$2.4/Mt

Context1,048,576

LLMVisionTool Use

New

minimax/minimax-m2.7

Input$0.30/Mt

Output$1.2/Mt

Context204,800

LLMTool Use

LLM API — Access 90+ 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

90+ 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.

Agent setup guides

Copy-ready configs for Codex, Claude Code, OpenCode, etc.

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?+

WaveSpeedAI supports the OpenAI-compatible Chat Completions interface. Optional fields such as tools, vision, JSON mode, and reasoning depend on the selected model.

What models are available?+

We offer 90+ 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.