Identity
- Status
- active
- Developer ID
deepseek-ai/DeepSeek-V3- Released
- Dec 26, 2024
- Version
- DeepSeek-V3
- License
- Unknown
DeepSeek-V3 is an open-weight language model published by DeepSeek.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
DeepinfraAvailable | $0.32 | $0.89 | — | — | Oct 19, 2026 | Provider-reported |
OpenrouterAvailable | $0.2574 | $1.0287 | — | — | Aug 29, 2026 | Provider-reported |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,332.46 | — | 21,770 | deepseek-v3; 95% CI [1327.72698428, 1337.19353550]; votes 21770; rank 224unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
deepseek-ai/DeepSeek-V3This 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.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
DeepSeek V3DeepSeek | vs | Sonar ProPerplexity | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | DeepSeek V4 Flash BaseDeepSeek | family variantstext |
DeepSeek V3DeepSeek | vs | DeepSeek R1DeepSeek | family variantstext |
DeepSeek V3DeepSeek | vs | DeepSeek V3.2DeepSeek | family variantstext |
DeepSeek V3DeepSeek | vs | Llama 3.1 405BMeta | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | cross-developer peerstext | |
DeepSeek V3DeepSeek | vs | cross-developer peerstext | |
DeepSeek V3DeepSeek | vs | MiniMax M2.5MiniMax | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | Mistral Large 3Mistral AI | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | Kimi K2 InstructMoonshot AI | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | GLM 5Z.ai | cross-developer peerstext |
DeepSeek V3DeepSeek | vs | GLM 5.1Z.ai | cross-developer peerstext |
Questions
DeepSeek-V3 is an open-weight language model published by DeepSeek. It is developed by DeepSeek and its current sourced lifecycle status is active.
DeepSeek V3's current record lists Text as input and Text as output.
The current record lists a 164K-token context window and does not report a maximum output length.
DeepSeek V3 is marked as API-available. The directly sourced provider records currently include Deepinfra, Hugging Face, and Openrouter.
The current record lists 684.5B total parameters and 37B active parameters. Its architecture is DeepseekV3ForCausalLM.
DeepSeek V3's recorded capabilities are chat and generation. Its supported tasks are text.
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.
DeepSeek V3 is an open-weight model. Self-hosting is supported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are deepseek-ai/DeepSeek-V3.
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 →