DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
Modalities
In / out per 1M$0.02 / $0.64
Context1M
ReleasedJul 31, 2026
Providers
27 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.02 | $0.53 | $0.01 | 0.82s | 57 tps | 100% | |
| $0.13 | $0.60 | $0.03 | 0.81s | 34 tps | 100% | |
 CoreWeavefp8 | $0.13 | $0.28 | $0.07 | 0.50s | 75 tps | 100% |
| $0.13 | $0.40 | $0.00 | 1.70s | 38 tps | 100% | |
| $0.19 | $0.56 | $0.02 | 1.65s | 88 tps | 100% | |
| $0.29 | $0.86 | $0.01 | 1.72s | 59 tps | 100% | |
| $0.31 | $0.92 | $0.02 | 1.87s | 63 tps | 100% | |
| $0.41 | $1.23 | $0.03 | 2.53s | 63 tps | 100% | |
| $0.13 | $0.23 | $0.08 | 0.47s | 90 tps | 99.95% | |
 SiliconFlowfp8 | $0.22 | $0.66 | $0.03 | 2.11s | 40 tps | 99.95% |
| $0.44 | $1.32 | $0.01 | 0.65s | 121 tps | 99.95% | |
| $0.14 | $0.28 | $0.03 | 0.81s | 41 tps | 99.92% | |
| $0.14 | $0.28 | $0.05 | 0.65s | 78 tps | 99.87% | |
 DeepInfraus · fp8 | $0.06 | $0.18 | $0.01 | 0.79s | 36 tps | 99.86% |
 DigitalOcean | $0.12 | $0.24 | $0.02 | 0.69s | 40 tps | 99.84% |
 Cohere | $0.14 | $0.28 | $0.07 | 0.41s | 112 tps | 99.52% |
 Basetenfp8 | $0.13 | $0.26 | $0.03 | 0.83s | 79 tps | 99.38% |
| Basetenus · fp8 | $0.13 | $0.26 | $0.03 | 0.83s | 89 tps | 99.28% |
| $0.44 | $1.32 | $0.03 | 2.87s | 59 tps | 99.16% | |
| $0.02 | $0.42 | $0.01 | 6.54s | 21 tps | 98.98% | |
| $0.44 | $1.32 | $0.01 | 1.27s | 54 tps | 98.93% | |
| $0.13 | $0.26 | $0.03 | 1.81s | 43 tps | 98.91% | |
| $0.10 | $0.30 | $0.03 | 6.50s | 20 tps | 98.87% | |
| $0.01 | $0.58 | $0.01 | 2.07s | 13 tps | 98.43% | |
| $0.18 | $0.53 | $0.02 | 1.48s | 75 tps | 97.9% | |
| $0.20 | $0.60 | Variable | 1.68s | 41 tps | 97.67% | |
| $0.02 | $0.64 | $0.02 | 0.72s | 36 tps | 97.12% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Flash 0731 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4 Flash 0731 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.02
per 1M tokens
Output
$0.64
per 1M tokens
Cache read
$0.02
per 1M cached tokens
Included in every pass
DeepSeek V4 Flash 0731 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
DigitalOcean Sail Research (us) Together Venice DeepInfra (us) Open Inference Phala Cohere Baidu Qianfan SiliconFlow Baseten (us) AtlasCloud Parasail Inceptron (eu) Alibaba Cloud Int. (us-east-1) Reka AI Wafer Relace Cloudflare Mancer StreamLake GMICloud Sail Research Baseten NovitaAI Alibaba Cloud Int. CoreWeave
0 tok/s1000 tok/s2000 tok/s3000 tok/s4000 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
DigitalOcean Sail Research (us) Together Venice DeepInfra (us) Open Inference Phala Cohere Baidu Qianfan SiliconFlow Baseten (us) AtlasCloud Parasail Inceptron (eu) Alibaba Cloud Int. (us-east-1) Reka AI Wafer Relace Cloudflare Mancer StreamLake GMICloud Sail Research Baseten NovitaAI Alibaba Cloud Int. CoreWeave
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.83%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.85%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V4 Flash 0731, by tokens this week.
Activity
29881.4B tokens processed market-wide in the last month.
0500.0B1000.0B1500.0B2000.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for DeepSeek V4 Flash 0731?
deepseek/deepseek-v4-flash-0731. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V4 Flash 0731 hold?
1,048,576 tokens per request, of which up to 943,718 can be the response.
What can it accept and return?
Input: text. Output: text.
What does DeepSeek V4 Flash 0731 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.02 per 1M input tokens and $0.64 per 1M output tokens.
Who built DeepSeek V4 Flash 0731?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
