Quick:
venice
Active
DeepSeek V3.2
Model Spec
venice:deepseek-v3.2
Modalities
Input
text
Output
text
Capabilities
Chat
Reasoning
Tools
Streaming
Pricing Components
| Component | Price | Conditions | Source |
|---|---|---|---|
| token.input | $0.33 / 1M tokens | Standard | — |
| token.output | $0.48 / 1M tokens | Standard | — |
| token.cache_read | $0.16 / 1M tokens | Standard | — |
Specifications
Context Window
160,000 tokens
Max Output
32,768 tokens
Input Cost
$0.33/M
Output Cost
$0.48/M
History
Raw JSONTimeline is based on collected llm_db history snapshots and may be incomplete.
2026-07-02
changed
-
extra.description
(add)
— → DeepSeek chat model for instruction following, coding, and analysis
2026-06-11
changed
-
extra.reasoning_options
(add)
— → [1 items]
-
extra.temperature
(remove)
true → —
-
knowledge
(replace)
2025-10 → —
2026-04-20
changed
-
capabilities.rerank
(add)
— → false
2026-03-28
changed
-
capabilities.streaming.text
(remove)
true → —
-
capabilities.streaming.tool_calls
(replace)
false → true
-
capabilities.tools.enabled
(replace)
false → true
2026-03-27
changed
-
execution
(add)
— → {2 fields}
2026-03-20
changed
-
cost.cache_read
(replace)
0.2 → 0.16
-
cost.input
(replace)
0.4 → 0.33
-
cost.output
(replace)
1 → 0.48
2026-03-14
introduced
snapshots 64bf744 -> 98a92b8 • generated 2026-07-29T03:34:55
6020
of 6154 models
1 / 121
Page 1 of 121