YFarmX

Anthropic: Claude Opus 4

anthropic/claude-opus-4 · AnthropicUnmeasurable
Declared family
Claude
Evidence confidence
Unknown
Declared tokenizer tag
Claude
Entered catalogue
22 May 2025
Last tested
Not yet measured
Measurement
Deferred: measurement cost above the per-model cap

Evidence stack

Signals of different kinds, weighed together
SignalResultReference
Tokenizer signatureNot measured
API surfaceNo other entry shares this exact contractapi_ef0b5b0d
Context and output200,000 context · 32,000 max outputdeclared
Reasoning contractOptionaldeclared
Serving providers observedNone recorded yet

Declared record

What the catalogue claims about this model

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Modalities
text+image+file->text
Declared tokenizer
Claude
Prompt price
$15.0 / M tokens
Completion price
$75.0 / M tokens

Supported parameters

include_reasoningmax_tokensreasoningstoptemperaturetool_choicetoolstop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken
  • 22 May 2025Enters the OpenRouter catalogue declared as Claude.

Cite this page as the evidence record for Anthropic: Claude Opus 4: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.