Anthropic: Claude Opus 4.6

anthropic/claude-opus-4.6 · AnthropicNot yet established
Declared family
Claude
Evidence confidence
Unknown
Declared tokenizer tag
Claude
Entered catalogue
4 February 2026
Last tested
Not yet measured
Measurement
Awaiting measurement

Evidence stack

Signals of different kinds, weighed together
SignalResultReference
Tokenizer signatureNot measured
API surfaceNo other entry shares this exact contractapi_6cc6b678
Context and output1,000,000 context · 128,000 max outputdeclared
Reasoning contractOptional · efforts max, high, medium, low · default highdeclared
Serving providers observedNone recorded yet

Declared record

What the catalogue claims about this model

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Modalities
text+image+file->text
Declared tokenizer
Claude
Prompt price
$5.00 / M tokens
Completion price
$25.0 / M tokens

Supported parameters

include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_pverbosity

defaults: {}

Catalogue entry

History

Every observation, kept as taken
  • 4 February 2026Enters the OpenRouter catalogue declared as Claude.

Cite this page as the evidence record for Anthropic: Claude Opus 4.6: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.