DeepSeek: DeepSeek V3.2
deepseek/deepseek-v3-2DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
Modalities
In / out per 1M$0.26 / $0.80
Context160K
ReleasedDec 1, 2025
Providers
12 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.50 | $1.50 | $0.25 | 0.77s | 42 tps | 100% | |
| $0.21 | $0.31 | $0.02 | 1.22s | 51 tps | 99.87% | |
 DigitalOcean | $0.30 | $0.96 | $0.09 | 0.92s | 56 tps | 99.84% |
| $1.00 | $1.00 | $0.50 | 2.40s | 13 tps | 99.83% | |
 SiliconFlowfp8 | $0.26 | $0.80 | $0.14 | 2.41s | 13 tps | 99.79% |
 Google Vertex | $0.56 | $1.68 | Variable | 2.95s | 22 tps | 99.48% |
| $0.28 | $0.42 | $0.03 | 1.29s | 30 tps | 99.18% | |
 DeepInfraus · fp4 | $0.26 | $0.38 | $0.13 | 3.03s | 7 tps | 98.35% |
| $0.27 | $0.39 | $0.13 | 3.87s | 7 tps | 95.57% | |
| $3.00 | $4.50 | Variable | 3.51s | 47 tps | 88.52% | |
| $0.26 | $0.38 | $0.13 | 3.83s | 20 tps | 82.62% | |
| $3.00 | $4.50 | Variable | 5.41s | 29 tps | 81.63% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V3.2 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V3.2 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.26
per 1M tokens
Output
$0.80
per 1M tokens
Cache read
$0.14
per 1M cached tokens
Included in every pass
DeepSeek V3.2 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Friendli Venice DigitalOcean GMICloud DeepInfra (us) MARA Baidu Qianfan SiliconFlow Phala Google Vertex AtlasCloud SambaNova
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Friendli Venice DigitalOcean GMICloud DeepInfra (us) Baidu Qianfan SiliconFlow Phala Google Vertex AtlasCloud SambaNova MARA
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.14%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.23%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V3.2, by tokens this week.
Activity
1582.7B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for DeepSeek V3.2?
deepseek/deepseek-v3.2. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V3.2 hold?
163,840 tokens per request, of which up to 147,456 can be the response.
What can it accept and return?
Input: text. Output: text.
What does DeepSeek V3.2 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.26 per 1M input tokens and $0.80 per 1M output tokens.
Who built DeepSeek V3.2?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
