Is meta.llama-4-maverick-17b-128e-instruct-fp8 deprecated?

Q: Is meta.llama-4-maverick-17b-128e-instruct-fp8 deprecated?

No — still supported. Listed by litellm. No retirement date announced. Neither the provider's API nor its documentation has been checked for this model.

NOT DEPRECATED

Listed by litellm. No retirement date announced. Neither the provider's API nor its documentation has been checked for this model.

state=alive sunset=none days_remaining=n/a severity=low sources=litellm evidence_tier=catalog confirmed_by_endpoint=false documented_by_provider=false replacement=none corroborated=single-source divergent_fields=none checked=2026-08-02 01:41Z

oci/meta.llama-4-maverick-17b-128e-instruct-fp8

Vendor: oci. Tracked by 1 of 5 sources.

What each source reports

**endpoint** = the provider's own machine-readable API, the strongest evidence. **provider docs** = the provider's own documentation, read by a model — first-party content, inferred reading. Unlabelled rows are third-party catalogs. Where sources disagree both values are shown rather than silently reconciled.
Source	ID	Context	Max out	In $/Mtok	Out $/Mtok	Sunset
litellm	oci/meta.llama-4-maverick-17b-128e-instruct-fp8	1,048,576	8,192	$0.72	$0.72	—

Change history

Severity	Change	What	Detected
low	modified	oci/meta.llama-4-maverick-17b-128e-instruct-fp8: context_tokens raised 512,000 to 1,048,576	2026-05-23
low	modified	oci/meta.llama-4-maverick-17b-128e-instruct-fp8: max_output_tokens raised 4,000 to 8,192	2026-05-23
low	modified	oci/meta.llama-4-maverick-17b-128e-instruct-fp8: capabilities gained native_streaming, vision	2026-05-23