OpenAI-compatible API for Qwen, DeepSeek, GLM, Kimi and MiniMax. Start for FREE
Access Qwen, DeepSeek, GLM, Kimi, and more through one OpenAI-compatible API.
Start with up to 30M free tokens every month, then unlock more with a top-up.
Kimi K3 Free · Kimi K3 capabilities at zero token cost after at least $10 cumulative net recharge. Only completed recharge principal minus refunds counts; grants and fees do not. Spending your balance keeps access; refunds below $10 block new requests. This free route is especially slow; expect long waits. Qwen allowances and recharge tiers do not apply. Need faster responses? Use paid Kimi K3 →
Scale when you need more
Reserved Inference
Guaranteed capacity for production workloads.
Reserve TPM, RPM and concurrency without managing GPUs.
Explore Reserved →Dedicated Inference
Infrastructure configured around your workload.
Choose your model, throughput, context, region and deployment.
Explore Dedicated →Custom Deployment
Model evaluation, quantization and deployment for your use case.
Fine-tuning, training or bare-metal clusters on request.
Explore Custom →