One key · 338 models · 52 labs
One key to every AI model.
One OpenAI-compatible endpoint for every major model. You pay the model's price plus a flat 3% — and the math is printed next to every price on this site.
curl https://api.openkey.ai/v1/chat/completions -H "Authorization: Bearer ***" -d '{"model": "anthropic/claude-sonnet-4.5", "messages": [{"role": "user", "content": "Hello"}]}'Per 1M input tokens
anthropic/claude-sonnet-4.5
$3.00 + 3% $0.090 $3.09
openai/gpt-5.2
$1.75 + 3% $0.052 $1.80
deepseek/deepseek-v3.2
$0.229 + 3% $0.0069 $0.236
Fee — flat, every model 3%
Hidden charges $0.00
- 338
- Models
- 52
- Labs
- 25
- Free models
- 3%
- Flat fee
The fee
It's arithmetic, not a pricing page.
- One rule for every model
- Every model costs its provider price plus 3%. No tiers, no negotiated rates, no exceptions.
- No credit games
- No purchase fee when you top up, no expiring balances, no spread hidden in the token price.
- The math is printed
- Every price on this site shows the provider price beside it. Check our arithmetic anywhere.
Worked example
anthropic/claude-sonnet-4.5
Input · 1M tokens
$3.00 + 3% $3.09
Output · 1M tokens
$15.00 + 3% $15.45
Provider price sourced live. The 3% is our entire margin.
Catalog
Just added
AnthropicNewClaude Sonnet 5
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
ctx 1M in $2.06 out $10.30
GoogleNewNano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...
ctx 66K in $0.258 out $1.54
Sakana AINewFugu Ultra
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
ctx 1M in $5.15 out $30.90
GoogleNewNano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
ctx 66K in $2.06 out $12.36
GoogleNewNano Banana 2 (Gemini 3.1 Flash Image)
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
ctx 131K in $0.515 out $3.09
CohereFreeNorth Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
ctx 256K in Free out Free
Workhorses
AnthropicClaude Opus 4.5
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
ctx 200K in $5.15 out $25.75
OpenAIGPT-5.2
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
ctx 400K in $1.80 out $14.42
DeepSeekDeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
ctx 131K in $0.236 out $0.353
QwenQwen3 Max
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
ctx 262K in $0.803 out $4.02
Moonshot AIKimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
ctx 262K in $0.386 out $2.09
Z.aiGLM 5.2
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
ctx 1.0M in $0.958 out $3.09
One door to every model
Plug in once. We handle reliability, cost, safety, and the receipts.