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$0.12 / $0.24
Context1M
ReleasedJul 31, 2026
Providers
27 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.06 | $0.30 | $0.04 | 0.34s | 131 tps | 100% | |
 CoreWeavefp8 | $0.13 | $0.28 | $0.07 | 0.45s | 120 tps | 100% |
| $0.14 | $0.23 | $0.14 | 0.23s | 126 tps | 100% | |
| $0.14 | $0.28 | $0.05 | 0.80s | 82 tps | 100% | |
 DeepInfraus · fp8 | $0.06 | $0.18 | $0.01 | 0.59s | 46 tps | 100% |
| $0.15 | $0.30 | $0.04 | 0.83s | 50 tps | 100% | |
| $0.15 | $0.30 | $0.04 | 0.66s | 48 tps | 100% | |
| $0.09 | $0.26 | $0.00 | 2.05s | 37 tps | 100% | |
| $0.07 | $0.14 | $0.01 | 0.94s | 26 tps | 100% | |
| $0.31 | $0.92 | $0.02 | 1.95s | 65 tps | 100% | |
| $0.44 | $1.32 | $0.01 | 2.21s | 48 tps | 100% | |
| $0.44 | $1.32 | $0.03 | 1.70s | 68 tps | 100% | |
 Baseten (fp32)fp32 | $0.13 | $0.26 | $0.03 | 0.29s | 117 tps | 100% |
| $0.44 | $1.32 | $0.04 | 1.62s | 90 tps | 100% | |
 DigitalOcean | $0.12 | $0.24 | $0.02 | 0.72s | 138 tps | 99.97% |
| $0.10 | $0.28 | $0.04 | 0.66s | 122 tps | 99.97% | |
| Baseten (fp8)us · fp8 | $0.13 | $0.26 | $0.03 | 0.33s | 142 tps | 99.97% |
| $0.19 | $0.56 | $0.02 | 2.11s | 94 tps | 99.96% | |
 Cohere | $0.14 | $0.28 | $0.07 | 0.43s | 166 tps | 99.95% |
| $0.13 | $0.49 | $0.03 | 0.94s | 62 tps | 99.95% | |
| $0.44 | $1.32 | $0.01 | 1.12s | 65 tps | 99.95% | |
 SiliconFlowfp8 | $0.22 | $0.66 | $0.03 | 1.68s | 21 tps | 99.94% |
| $0.13 | $0.26 | $0.03 | 0.57s | 107 tps | 99.9% | |
| $0.20 | $0.60 | Variable | 1.11s | 59 tps | 99.88% | |
| $0.41 | $1.23 | $0.03 | 0.95s | 59 tps | 99.87% | |
| $0.29 | $0.86 | $0.01 | 3.45s | 48 tps | 99.85% | |
| $0.18 | $0.53 | $0.02 | 2.19s | 77 tps | 99.44% |
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
$0.12
per 1M tokens
Output
$0.24
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.
0.0s10.0s20.0s30.0s40.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
DigitalOcean Sail Research (us) Venice DeepInfra (us) Phala Cohere Baidu Qianfan SiliconFlow Baseten (fp8) (us) AtlasCloud Parasail Inceptron (eu) Alibaba Cloud Int. (us-east-1) Reka AI Wafer Relace Cloudflare Mancer StreamLake GMICloud Sail Research Baseten (fp32) NovitaAI Alibaba Cloud Int. CoreWeave Wafer (us)
0 tok/s1000 tok/s2000 tok/s3000 tok/s4000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
DigitalOcean Sail Research (us) Venice DeepInfra (us) Phala Cohere Baidu Qianfan SiliconFlow Baseten (fp8) (us) AtlasCloud Parasail Inceptron (eu) Alibaba Cloud Int. (us-east-1) Reka AI Wafer Relace Cloudflare Mancer StreamLake GMICloud Sail Research Baseten (fp32) NovitaAI Alibaba Cloud Int. CoreWeave Wafer (us)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.83%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.84%
100% 98% 97% 95%
Oct 31, 6:10 PMNow
Apps
Tools that most often run DeepSeek V4 Flash 0731, by tokens this week.
Activity
19609.2B tokens processed market-wide in the last month.
0250.0B500.0B750.0B1000.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
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 https://minuykh.app/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 $0.12 per 1M input tokens and $0.24 per 1M output tokens.
Who built DeepSeek V4 Flash 0731?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
