OpenAI-compatible LLM inference API with x402 or MPP micropayments.
| Method | Path | Price | Description |
|---|---|---|---|
| POST | /v1/chat/completions | dynamic | LLM chat completion (streaming supported via SSE) |
Flat models charge a fixed price per request. Dynamic models charge per token based on input, output, and cache usage. Rates are USD per million tokens.
| Model | Type | Flat | Input | Output |
|---|---|---|---|---|
| moonshotai/kimi-k2.5 | dynamic | - | $0.59/M | $2.86/M |
| minimax/minimax-m2.5 | dynamic | - | $0.26/M | $1.52/M |
| qwen/qwen-2.5-7b-instruct | flat | $0.001 | - | - |
| anthropic/claude-sonnet-4.5 | dynamic | - | $3.9/M | $19.5/M |
| anthropic/claude-sonnet-4.6 | dynamic | - | $3.9/M | $19.5/M |
| anthropic/claude-opus-4.5 | dynamic | - | $6.5/M | $32.5/M |
| anthropic/claude-opus-4.6 | dynamic | - | $6.5/M | $32.5/M |
| minimax/minimax-m2.7 | dynamic | - | $0.39/M | $1.56/M |
| z-ai/glm-5 | dynamic | - | $1.04/M | $3.33/M |
| x-ai/grok-4.1-fast | dynamic | - | $0.26/M | $0.65/M |
| x-ai/grok-4.20-beta | dynamic | - | $2.6/M | $7.8/M |
| x-ai/grok-4.20-multi-agent-beta | dynamic | - | $2.6/M | $7.8/M |
| x-ai/grok-4.1-fast:online | dynamic | - | $1.05/M | $0.75/M |
| x-ai/grok-4.20-beta:online | dynamic | - | $3.75/M | $9/M |
| x-ai/grok-4.20-multi-agent-beta:online | dynamic | - | $3.75/M | $9/M |