DeepSeek V3.2 Exp
DeepSeek V3.2 Exp is a model by DeepSeek for writing code and agentic, it stands 1st of 16 on The agent company — Epoch AI, and 9 sellers in the catalogue publish a price for it.
text → text · made by DeepSeek
Sold by 11 ways
| Seller | Lane | Rate |
|---|---|---|
| OpenRouter 2 ways | $0.27per Mtok in$0.41per Mtok out$0.067per Mtok cached | |
| OpenRouter aggregatornot on the seller's list today | atlas-cloud/fp8 | $0.13per Mtok in$0.2per Mtok out$0.067per Mtok cachedopenrouter.ai · read 2026-09-29 |
| OpenRouter aggregator | standard | $0.27per Mtok in$0.41per Mtok out$0.067per Mtok cachedopenrouter.ai · read 2026-09-30 |
| OpenRouter aggregator | siliconflow/fp8 | $0.27per Mtok in$0.41per Mtok outopenrouter.ai · read 2026-09-29 |
| DeepInfra aggregator | standard | $0.21per Mtok in$0.32per Mtok outapi.deepinfra.com · read 2026-08-25 |
| AtlasCloud aggregator | standard | $0.26per Mtok in$0.38per Mtok out$0.13per Mtok cachedapi.atlascloud.ai · read 2026-09-29 |
| ElectronHub aggregator | standard | $0.27per Mtok in$0.41per Mtok outapi.electronhub.ai · read 2026-10-31 |
| Hugging Face Inference Providers 0 ways | $0.27per Mtok in$0.41per Mtok out | |
| Hugging Face Inference Providers aggregatornot on the seller's list today | novita | $0.27per Mtok in$0.41per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nous Research aggregator | standard | $0.27per Mtok in$0.41per Mtok out$0.067per Mtok cachedinference-api.nousresearch.com · read 2026-10-01 |
| Novita AI 0 ways | $0.27per Mtok in$0.41per Mtok out | |
| Novita AI aggregatornot on the seller's list today | standard | $0.27per Mtok in$0.41per Mtok outapi.novita.ai · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.27per Mtok in$0.41per Mtok outmodels.dev · read 2026-10-31 |
| PPIO 0 ways | $2per Mtok in$3per Mtok out | |
| PPIO aggregatornot on the seller's list today | standard | $2per Mtok in$3per Mtok outapi.ppinfra.com · read 2026-09-28 |
Measured 15 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 1stof 16 | The agent company — Epoch AI | % Score | 0.524 |
| 12thof 69 | Aider polyglot coding leaderboard | Percent correct | 74.2 |
| 17thof 111 | Vectara Hallucination Leaderboard | Hallucination Rate | 5.3 |
| 21stof 72 | Aider polyglot — Epoch AI | Percent correct | 70.2 |
| 57thof 71 | Vending bench 2 — Epoch AI | Score | 1034.004 |
| 91stof 150 | Design Arena · 3d (models) | Elo | 1145 |
| 98thof 163 | Design Arena · codecategories (models) | Elo | 1170 |
| 100thof 157 | Design Arena · uicomponent (models) | Elo | 1161 |
| 104thof 162 | Design Arena · gamedev (models) | Elo | 1144 |
| 104thof 169 | Design Arena · website (models) | Elo | 1177 |
| 105thof 114 | Design Arena · svg (models) | Elo | 1028 |
| 109thof 154 | Design Arena · dataviz (models) | Elo | 1152 |
| 122ndof 135 | Webdev arena — Epoch AI | Arena Score | 1271.75 |
| 124thof 141 | LMArena · WebDev | Score (Elo) | 1272 |
| 128thof 414 | LMArena · Text | Score (Elo) | 1421 |
About
DeepSeek V3.2 Exp — a text model from DeepSeek, sold by 6 companies from $0.21 in and $0.32 out per million tokens, placed 1st of 16 on The agent company — Epoch AI.
It takes text and returns text, with a context window of 163,840 tokens. It was published in September 2025, trained on material up to July 2025. Its sellers say it can call a tool. The catalogue files it under code and agents. Six companies sell it. The cheapest is $0.21 in and $0.32 out per million tokens at DeepInfra. Beside the standard rate there is a regional lane. It has been measured on 15 boards, and stands best at 1st of 16 on The agent company — Epoch AI.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 163,840 tokens
- Published
- September 2025
- Knowledge to
- July 2025
- Parameters
- 685 billion
- Licence
- not read
- Sellers
- 6
- Maker's own price
- not read
- Price
- $0.21 in and $0.32 out per million tokens — DeepInfra
- Boards
- 15
- Best place
- 1st of 16 — The agent company — Epoch AI
Known as 7 names
DeepSeek-V3.2-Exp (Chat)DeepSeek-V3.2-Exp (Reasoner)DeepSeek-v3.2-Exp (Think)DeepSeek-V3.2-Exp (FC)DeepSeek-V3.2-Exp (Prompt + Thinking)deepseek-ai/DeepSeek-V3.2-Expdeepseek/deepseek-v3.2-exp