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

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

Yes — deprecated. Retired 2026-03-31 — 169 days ago. Requests to this identifier are expected to fail.

DEPRECATED

Retired 2026-03-31 — 169 days ago. Requests to this identifier are expected to fail.

state=dead sunset=2026-03-31 days_remaining=-169 severity=critical sources=litellm evidence_tier=catalog confirmed_by_endpoint=false documented_by_provider=false replacement=none corroborated=single-source divergent_fields=none checked=2026-09-16 03:02Z

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

Vendor: meta. 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	azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8	1,000,000	16,384	$1.41	$0.35	2026-03-31

Change history

Severity	Change	What	Detected
low	added	new model watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 (131,072 ctx)	2026-09-06
medium	repriced	deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: input_price_per_mtok $0.15/Mtok to $0.20/Mtok	2026-08-28
medium	repriced	deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: output_price_per_mtok $0.60/Mtok to $0.80/Mtok	2026-08-28
low	modified	novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8: capabilities gained response_schema	2026-08-28
info	deprecated	together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: deprecation announced for 2026-03-31 (date already passed)	2026-08-26
info	deprecated	together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: retires 2026-03-31 (148 days ago)	2026-08-26