Which model ids do I use?

The catalog ids, prefixed with blockrun/ in provider mode; in proxy mode use the bare catalog id.

Yes in both modes; the proxy passes SSE through unchanged.

Register BlockRun as a LiteLLM provider, or run it as the proxy

blockrun-litellm adds BlockRun as a LiteLLM provider and ships an OpenAI-compatible proxy that signs x402 payments locally — every model, one wallet, no provider keys.

Get your agent on BlockRun

How it works

LiteLLM is the common adapter layer many Python agent stacks already sit on. blockrun-litellm plugs BlockRun in at that layer: call register() once and any blockrun/<model> id works through LiteLLM's normal completion call, with the payment signed from your wallet per request.

The same package ships a proxy mode that exposes a local OpenAI-compatible endpoint. Anything that can point at an OpenAI base URL — LangChain, an agents SDK, a plain openai client — then pays per request through it without knowing x402 exists.

Behind it is the BlockRun catalog: 78 chat models plus image, video, music and speech generation, search, market data and multi-chain RPC, priced per call. 6 open-weight models are free and need no wallet.

Setup

1. In-process provider

pip install blockrun-litellm
# python
from blockrun_litellm import register; register()
# then: litellm.completion(model="blockrun/openai/gpt-5.4", ...)

2. Proxy mode

pip install 'blockrun-litellm[proxy]'
export BLOCKRUN_WALLET_KEY=0x<base wallet key>
blockrun-litellm-proxy --port 4001

Questions

Which model ids do I use?: The catalog ids, prefixed with blockrun/ in provider mode; in proxy mode use the bare catalog id.
Does streaming work?: Yes in both modes; the proxy passes SSE through unchanged.