Quick:
venice
Active
Grok 4.1 Fast
Model Spec
venice:grok-41-fast
Modalities
Input
text
image
Output
text
Capabilities
Chat
Reasoning
Tools
Vision
Specifications
Context Window
1,000,000 tokens
Max Output
30,000 tokens
Input Cost
$0.25/M
Output Cost
$0.63/M
History
Raw JSONTimeline is based on collected llm_db history snapshots and may be incomplete.
2026-03-09
changed
-
cost.cache_read
(replace)
0.125 → 0.0625
-
cost.input
(replace)
0.5 → 0.25
-
cost.output
(replace)
1.25 → 0.625
2026-02-09
changed
-
retired
(add)
— → false
2026-01-30
changed
-
last_updated
(replace)
2025-12-29 → 2026-01-28
-
limits.context
(replace)
262144 → 256000
-
limits.output
(replace)
65536 → 64000
2026-01-28
changed
-
base_url
(add)
— → —
2026-01-28
changed
-
pricing
(add)
— → —
2026-01-04
changed
-
last_updated
(replace)
2025-12-23 → 2025-12-29
-
release_date
(replace)
2025-04-29 → 2025-12-01
2025-12-25
changed
-
cost.cache_read
(add)
— → 0.125
-
last_updated
(replace)
2025-12-18 → 2025-12-23
2025-12-21
changed
-
extra.structured_output
(add)
— → true
-
last_updated
(replace)
2025-11-19 → 2025-12-18
-
limits.output
(replace)
8192 → 65536
2025-12-16
changed
-
extra.family
(add)
— → grok
2025-12-04
introduced
snapshots 59223aa -> 2a3e431 • generated 2026-03-14T20:28:04
4012
of 4015 models
1 / 81
Page 1 of 81