DeepSeek: DeepSeek V3.1
deepseek/deepseek-chat-v3-1DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
Modalities
In / out per 1M$0.25 / $0.95
Context160K
ReleasedAug 21, 2025
Providers
5 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 CoreWeavefp8 | $0.55 | $1.65 | $0.55 | 0.23s | 77 tps | 100% |
 DeepInfraus · fp4 | $0.25 | $0.95 | $0.13 | 1.05s | 9 tps | 99.92% |
| $0.60 | $1.70 | Variable | 0.97s | 116 tps | 96.41% | |
| $0.65 | $1.50 | Variable | 2.96s | 60 tps | 94.97% | |
 SiliconFlowfp8 | $0.27 | $1.00 | Variable | 1.91s | 15 tps | 92.56% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V3.1 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V3.1 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.25
per 1M tokens
Output
$0.95
per 1M tokens
Cache read
$0.13
per 1M cached tokens
Included in every pass
DeepSeek V3.1 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.
0.0s5.0s10.0s15.0s20.0s
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
MARA SiliconFlow DeepInfra (us) CoreWeave SambaNova
0 tok/s100 tok/s200 tok/s300 tok/s400 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
MARA SiliconFlow DeepInfra (us) CoreWeave SambaNova
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.86%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.77%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V3.1, by tokens this week.
Activity
220.1B tokens processed market-wide in the last month.
02.5B5.0B7.5B10.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for DeepSeek V3.1?
deepseek/deepseek-chat-v3.1. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V3.1 hold?
163,840 tokens per request, of which up to 32,768 can be the response.
What can it accept and return?
Input: text. Output: text.
What does DeepSeek V3.1 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.25 per 1M input tokens and $0.95 per 1M output tokens.
How current is its knowledge?
Training data runs to Mar 2025. Anything later has to come from your prompt or a tool call.
Who built DeepSeek V3.1?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
