NVIDIA NIM
aix402 v2POST /llm/nim
usage-based (provider cost + 10%)
OpenAI-compatible chat completions on frontier models (Claude Fable 5, Gemini 3.5 Flash, GPT-5.2 via Replicate; Nemotron 3 Ultra, Kimi K2.6, DeepSeek V4 Pro, GLM-5.1 via NVIDIA NIM with OpenRouter fallback). Pricing is usage-based: input + output tokens at the provider rate + 10%. On the x402 door the per-call charge is quoted up front as an upper bound (set max_tokens to lower it). Also available drop-in at POST /v1/chat/completions with an API key + prepaid credits (billed exactly per token).
Run Request
Fill in the parameters and execute the request

Model to run. Price is per-token (input + output) at the rate shown + 10%.

The user prompt (or use messages)

Optional system prompt

Optional cap on output tokens

Optional sampling temperature (0–2)

Connect wallet to make payments
Transaction History
Recent requests to this resource

No transactions yet. Run your first request!