/inferences/model/claude-haiku-4-5

claude-haiku-4-5

Measured by 4 nodes on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 27 Oct 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises

context declared2,00,000what the runtime reported. A node attests it was told this; nobody attests it is true.

context proved by recall4,096the largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.

Advertises 48.8× the context any machine here could make it use.Not an accusation — it is what happened here, and it is signed.

recalled 4k⌐ declared 200k · unsignedadvertises 49× what it proved

Capabilities, measured

Tool callingpassed

The node asked the model to call a function and checked whether it produced a valid call. Passing here is not the same as reasoning correctly over what the tools returned — a smaller model can do the first and fail the second silently.

signed by this network

What machines here proved

context proved by recall4,096

peak throughput ever signed77.34 tok/s · did:epn:002408…9e3c79

machines that measured it4

samples behind those numbers1

regions it was proved in4

Every line traces to a node signature.

from the public record · unsigned

What the runtime says about it

context declared2,00,000

the provider's own model metadata, relayed by the CLI; the node attests to what the provider declared, not that it is true. Attested by did:epn:002408…d68672.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.