Inference
Every frontier model behind one endpoint.
Don't lock your context into one model provider. Always keep your context available to the best model from any provider, in any category.
Providers & models
25% off for a limited time| Model | Context | Input / 1M | Output / 1M |
|---|---|---|---|
| OpenAI | |||
| GPT-5.5 | 400K | $1.25$0.94 | $10.00$7.50 |
| GPT-5.5 mini | 400K | $0.25$0.19 | $2.00$1.50 |
| Anthropic | |||
| Claude Opus 4.6 | 200K | $15.00$11.25 | $75.00$56.25 |
| Claude Sonnet 4.6 | 1M | $3.00$2.25 | $15.00$11.25 |
| Gemini 3 Pro | 1M | $2.50$1.88 | $15.00$11.25 |
| Gemini 3 Flash | 1M | $0.30$0.23 | $2.50$1.88 |
| Meta | |||
| Llama 4 Maverick | 1M | $0.27$0.20 | $0.85$0.64 |
| Llama 4 Scout | 10M | $0.18$0.14 | $0.59$0.44 |
| xAI | |||
| Grok 4.5 | 256K | $3.00$2.25 | $15.00$11.25 |
| Grok 4.5 Fast | 2M | $0.20$0.15 | $0.50$0.38 |
Prices per 1M tokens. The launch discount is applied automatically at the gateway — for a limited time.
More ways to run inference
Private
On-prem inference
Run open-weight models in your own cloud or on your own hardware. Genbase deploys, scales, and monitors them — your data never leaves your network.
0% markup
Bring your own keys
Connect your OpenAI, Anthropic, or Google keys and genbase routes through your accounts at provider cost — with usage visible to your whole team in realtime.
OpenAIAnthropicGoogle
Ready to try genbase?
Every model, every primitive, one workspace for your whole team.