One key. Every API shape.
Drop-in OpenAI /v1/chat/completions and Anthropic /v1/messages compatibility. Frontier open models, image generation, and speech-to-text — behind one key.
Keep your SDK. Change one line.
from openai import OpenAI
client = OpenAI(api_key="sk-svp-YOUR_KEY", base_url="https://api.genon.ai/v1")
r = client.chat.completions.create(
model="zai-org/glm-5.2",
messages=[{"role": "user", "content": "Hello"}],
extra_body={"thinking_token_budget": 2048}, # reasoning cap — honored by e.g. Qwen3
)
print(r.choices[0].message.content)Live models & pricing
Prices come straight from the billing database — what you see is what you are billed.
Chat
- anthropic/claude-opus-5$5.00 in · $25.00 out / 1M tokens · 1M ctx
- google/gemma-4-26b-a4b-it$0.07 in · $0.34 out / 1M tokens · 262K ctx
- meta/muse-spark-1.3-contributor$0.10 in · $0.20 out / 1M tokens · 1M ctx
- microsoft/phi-4$0.07 in · $0.14 out / 1M tokens · 16K ctx
- minimax/minimax-m3$0.30 in · $1.20 out / 1M tokens · 1M ctx
- minimaxai/minimax-m3$0.30 in · $1.20 out / 1M tokens · 1M ctx
- moonshotai/kimi-k2.6$0.95 in · $4.00 out / 1M tokens · 262K ctx
- openai/gpt-5.5$5.00 in · $30.00 out / 1M tokens · 1M ctx
- openai/gpt-5.6-luna$0.20 in · $1.20 out / 1M tokens · 1.1M ctx
- openai/gpt-5.6-sol$5.00 in · $30.00 out / 1M tokens · 1M ctx
- openai/gpt-5.6-terra$2.50 in · $15.00 out / 1M tokens · 1M ctx
- openai/gpt-oss-20b$0.03 in · $0.13 out / 1M tokens · 131K ctx
- qwen/qwen3.5-397b-a17b-fp8$0.50 in · $3.60 out / 1M tokens · 262K ctx
- qwen/qwen3.6-35b-a3b$0.14 in · $1.00 out / 1M tokens · 262K ctx
- qwen/qwen3.8-27b$0.425 in · $2.55 out / 1M tokens · 1M ctx
- qwen/qwen3.8-flash$0.16 in · $0.47 out / 1M tokens · 1M ctx
- z-ai/glm-5.3-flash$0.075 in · $0.25 out / 1M tokens · 1.3M ctx
- zai-org/glm-5.2$1.19 in · $3.74 out / 1M tokens · 1M ctx
Image
- boogu/boogu-image-0.1-base$0.0200 / image
- boogu/boogu-image-0.1-edit$0.0400 / image
Speech-to-text
- openai/whisper-large-v3$0.0060 / audio min
Embedding
- baai/bge-m3$0.01 in / 1M tokens · 8K ctx
Per-key budgets & limits
Issue virtual keys with monthly budgets, model allowlists, and per-key rate limits.
Usage dashboard
Per-key spend and request analytics in the console, exportable as CSV.
Playground
Try every live model in the browser before you write a line of code.
Streaming & tools
SSE streaming, function calling, JSON mode, and vision inputs on supported models.