Save your premium tokens for what matters.

Point Claude Code, Codex, or your agent framework at Ambient for refactoring and routine work: top open models at competitive rates, and it doesn't count against your other providers' quotas.

Developer quickstart

From request to proof.

Inference request

Your API call is routed to an open GPU node on the Ambient network, compatible with OpenAI and Anthropic SDKs.

Proof of Logits

The node generates a cryptographic proof over the output logits, verifying the exact model produced the exact output.

Verify

Anyone can independently re-check the proof.

Drop in: just change the base URL.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ambient.xyz/v1",
    api_key="AMB_…",
)
resp = client.chat.completions.create(
    model="ambient/large",       # GLM, or pick any of 15 models
    messages=[{"role": "user", "content": "Hello"}],
)

Works with your existing stack.

Point your base URL at Ambient, authenticate with an Ambient key, and your current SDKs and agents get verified inference, no code changes.