DeepSeek-V3 0324
DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.
text → text · made by DeepSeek
$0.2→$0.6per Mtok in / out
Lambda · 15 sellers
Sold by 22 ways
| Seller | Lane | Rate |
|---|---|---|
| Crusoe cloud | standard | $0.5per Mtok in$1.5per Mtok out$0.25per Mtok cachedmodels.dev · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $1.14per Mtok in$4.56per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Lambda aggregator | standard | $0.2per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| DeepInfra aggregator | standard | $0.24per Mtok in$0.9per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 2 ways | $0.27per Mtok in$1.12per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.24per Mtok in$0.9per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.27per Mtok in$1.12per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregatornot on the seller's list today | novita | $0.27per Mtok in$1.12per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nous Research aggregator | standard | $0.24per Mtok in$0.9per Mtok out$0.14per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 5 ways | $0.25per Mtok in$1per Mtok out$0.11per Mtok cached | |
| OpenRouter aggregator | deepinfra/fp4 | $0.24per Mtok in$0.9per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | standard | $0.25per Mtok in$1per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-09-12 |
| OpenRouter aggregator | siliconflow/fp8 | $0.25per Mtok in$1per Mtok outopenrouter.ai · read 2026-09-09 |
| OpenRouter aggregatornot on the seller's list today | novita/fp8 | $0.27per Mtok in$1.12per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | gmicloud/fp8 | $0.29per Mtok in$1.14per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | crusoe/bf16 | $0.5per Mtok in$1.5per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-08-25 |
| Novita AI aggregator | standard | $0.27per Mtok in$1.12per Mtok out$0.14per Mtok cachedapi.novita.ai · read 2026-08-25 |
| Hyperbolic aggregator | standard | $0.4per Mtok in$0.4per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Requesty aggregator | novita | $0.4per Mtok in$1.3per Mtok out$0.4per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| ElectronHub aggregator | standard | $0.5per Mtok in$1.5per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Baseten aggregator | standard | $0.77per Mtok in$0.77per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Fireworks AI aggregator | standard | $0.9per Mtok in$0.9per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| PPIO aggregator | standard | $2per Mtok in$8per Mtok outapi.ppinfra.com · read 2026-09-16 |
| SambaNova Cloud aggregator | standard | $3per Mtok in$4.5per Mtok outraw.githubusercontent.com · read 2026-09-16 |
Measured 18 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 11thof 54 | Live bench — Epoch AI | Global average | 66.86 |
| 27thof 49 | Lech mazur writing — Epoch AI | Mean score | 7.7 |
| 30thof 69 | Aider polyglot coding leaderboard | Percent correct | 55.1 |
| 32ndof 50 | Metr time horizons — Epoch AI | average_score | 0.496 |
| 35thof 72 | Aider polyglot — Epoch AI | Percent correct | 55.1 |
| 40thof 108 | Math level 5 — Epoch AI | mean_score | 75.548 |
| 85thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.272 |
| 99thof 161 | Dtbench — Epoch AI | Accuracy | 64.8 |
| 101stof 123 | Lmca — Epoch AI | Score | 15.47 |
| 136thof 170 | Weirdml — Epoch AI | Accuracy | 36.08 |
| 137thof 143 | Artificial Analysis · Agentic Index | Index | 0.8 |
| 137thof 168 | Scicode — Epoch AI | Score | 35.764 |
| 147thof 184 | Artificial Analysis · Coding Index | Index | 21.2 |
| 151stof 177 | Critpt — Epoch AI | Accuracy | 0 |
| 153rdof 402 | LMArena · Text | Score (Elo) | 1396 |
| 181stof 313 | GPQA Diamond | mean_score | 67.614 |
| 205thof 290 | OTIS Mock AIME 2024-2025 | mean_score | 37.778 |
| 490thof 656 | Epoch capabilities index — Epoch AI | ECI Score | 135.96 |
About
DeepSeek-V3 0324 — a text model from DeepSeek, sold by 15 companies from $0.2 in and $0.6 out per million tokens, placed 11th of 54 on Live bench — Epoch AI.
It takes text and returns text, with a context window of 163,840 tokens. It was published in December 2024. Its sellers say it can call a tool. The catalogue files it under reasoning, code and agents. Fifteen companies sell it. The cheapest is $0.2 in and $0.6 out per million tokens at Lambda. Beside the standard rate there are separately routed and regional lanes. It has been measured on 18 boards, and stands best at 11th of 54 on Live bench — Epoch AI.
Every current figure
- Maker
- DeepSeek
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 163,840 tokens
- Published
- December 2024
- Parameters
- 685 billion
- Licence
- not read
- Sellers
- 15
- Maker's own price
- not read
- Price
- $0.2 in and $0.6 out per million tokens — Lambda
- Boards
- 18
- Best place
- 11th of 54 — Live bench — Epoch AI
Known as 6 names
V3-0324deepseek-ai/DeepSeek-V3-0324deepseek/deepseek-chat-v3-0324deepseek/deepseek-v3-0324novita/deepseek/deepseek-v3-0324DeepSeek: DeepSeek V3 0324