DeepSeek-V3 is an open-weight language model published by DeepSeek.

Token context
164K tokens
Inputs
Text
Outputs
Text
Released
Dec 26, 2024

Providers & Pricing

Estimate workload cost →
ProviderInput / 1MOutput / 1MCache read / 1MCache write / 1MObservedEvidence
$0.32$0.89——Oct 19, 2026Provider-reported
$0.2574$1.0287——Aug 29, 2026Provider-reported
LMArena Text Arenatext-2026-10-15-a64ca3b12b6e1,332.46rating—21,770deepseek-v3; 95% CI [1327.72698428, 1337.19353550]; votes 21770; rank 224unknownOriginal sourcewinner eligibleThird-party benchmark

At a Glance

Model Facts

Identity

Status
active
Developer ID
deepseek-ai/DeepSeek-V3
Released
Dec 26, 2024
Version
DeepSeek-V3
License
Unknown

Capacity

Token context
164K tokens
Maximum output
Unknown
Total parameters
684.5B
Active parameters
37B
Knowledge cutoff
Not reported

Interface and Access

Inputs
Text
Outputs
Text
API available
Yes
Open weights
Yes
Self-hostable
Yes
Reasoning
No
Vision
No
Tool calling
No
Capabilities
chat, generation

This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.

Version Lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesdeepseek-ai/DeepSeek-V3, deepseek-ai/DeepSeek-V3

Explicit Unknowns

  • Maximum output
  • Knowledge cutoff

Primary Evidence

Sources and Observation Date

Comparable Peers

Related Model Comparisons

All comparisons →
APairBContext
vscross-developer peerstext
vsfamily variantstext
vsfamily variantstext
vsfamily variantstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext

Questions

DeepSeek V3 FAQs

What is DeepSeek V3?+

DeepSeek-V3 is an open-weight language model published by DeepSeek. It is developed by DeepSeek and its current sourced lifecycle status is active.

What inputs and outputs does DeepSeek V3 support?+

DeepSeek V3's current record lists Text as input and Text as output.

How much context does DeepSeek V3 support?+

The current record lists a 164K-token context window and does not report a maximum output length.

Is DeepSeek V3 available through an API?+

DeepSeek V3 is marked as API-available. The directly sourced provider records currently include Deepinfra, Hugging Face, and Openrouter.

How large is DeepSeek V3?+

The current record lists 684.5B total parameters and 37B active parameters. Its architecture is DeepseekV3ForCausalLM.

What capabilities and tasks does DeepSeek V3 support?+

DeepSeek V3's recorded capabilities are chat and generation. Its supported tasks are text.

How much does DeepSeek V3 cost through an API?+

The lowest directly sourced prices currently attached to DeepSeek V3 are $0.2574 per million input tokens through Openrouter and $0.89 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.

Can DeepSeek V3 be self-hosted?+

DeepSeek V3 is an open-weight model. Self-hosting is supported, with no license recorded.

Does DeepSeek V3 have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are deepseek-ai/DeepSeek-V3.

Which models can DeepSeek V3 be compared with?+

The current compatible peer set includes Sonar Pro, DeepSeek V4 Flash Base, DeepSeek R1, DeepSeek V3.2, and Llama 3.1 405B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →

Send Feedback