Back
DeepSeek: DeepSeek V3 0324 (free)
DeepSeek
Input: text
Output: text
Released: Mar 24, 2025•Updated: Mar 28, 2025
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.
163,840 Token Context
Process and analyze large documents and conversations.
Advanced Coding
Improved capabilities in front-end development and full-stack updates.
Agentic Workflows
Autonomously navigate multi-step processes with improved reliability.
Available On
| Provider | Model ID | Context | Max Output | Input Cost | Output Cost | Throughput | Latency |
|---|---|---|---|---|---|---|---|
| DeepInfra | deepInfra | 164K | - | $0.30/M | $0.88/M | 17.8 t/s | 532 ms |
| Novita | novitaAi | 128K | 16K | $0.33/M | $1.30/M | 23.8 t/s | 1251 ms |
| Kluster | klusterAi | 164K | 164K | $0.33/M | $1.40/M | 18.7 t/s | 1403 ms |
| Lambda | lambda | 164K | 164K | $0.34/M | $0.88/M | 31.2 t/s | 738 ms |
| Cent-ML | centMl | 33K | 164K | $0.43/M | $1.40/M | 7.0 t/s | 898 ms |
| InferenceNet | inferenceNet | 128K | 33K | $0.45/M | $1.45/M | 27.2 t/s | 1271 ms |
| Nebius | nebiusAiStudio | 164K | - | $0.50/M | $1.50/M | 26.1 t/s | 759 ms |
| GMICloud | gmiCloud | 131K | - | $0.74/M | $0.90/M | 58.2 t/s | 765 ms |
| BaseTen | baseten | 164K | 131K | $0.77/M | $0.77/M | 117.8 t/s | 367 ms |
| Parasail | parasail | 164K | 164K | $0.79/M | $1.15/M | 81.3 t/s | 747 ms |
| Fireworks | fireworks | 164K | - | $0.90/M | $0.90/M | 57.1 t/s | 933 ms |
| Hyperbolic | hyperbolic | 164K | - | $1.25/M | $1.25/M | 25.3 t/s | 1648 ms |
| Together | together | 131K | 12K | $1.25/M | $1.25/M | 26.5 t/s | 1144 ms |
| SambaNova | sambaNova | 33K | 7K | $3.00/M | $4.50/M | 213.7 t/s | 1914 ms |
| DeepSeek | deepSeek | 64K | 8K | $0.27/M | $1.10/M | 19.4 t/s | 4688 ms |
Standard Pricing