DeepSeek: DeepSeek V4 Flash Latest
deepseek/deepseek-v4-flash-latestThis model always redirects to the latest model in the DeepSeek V4 Flash family.
Modalities
In / out per 1M$0.01 / $0.58
Context1M
ReleasedAug 1, 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 | 0.89s | 58 tps | 100% | |
 CoreWeavefp8 | $0.13 | $0.28 | $0.07 | 0.50s | 79 tps | 100% |
| $0.13 | $0.40 | $0.00 | 1.68s | 38 tps | 100% | |
| $0.19 | $0.56 | $0.02 | 1.65s | 84 tps | 100% | |
| $0.29 | $0.86 | $0.01 | 1.71s | 59 tps | 100% | |
| $0.31 | $0.92 | $0.02 | 2.09s | 55 tps | 100% | |
| $0.41 | $1.23 | $0.03 | 2.51s | 60 tps | 100% | |
| $0.13 | $0.60 | $0.03 | 0.94s | 46 tps | 99.95% | |
| $0.13 | $0.23 | $0.08 | 0.48s | 87 tps | 99.95% | |
 SiliconFlowfp8 | $0.22 | $0.66 | $0.03 | 2.13s | 42 tps | 99.95% |
| $0.44 | $1.32 | $0.01 | 0.67s | 120 tps | 99.95% | |
| $0.14 | $0.28 | $0.03 | 0.93s | 31 tps | 99.92% | |
| $0.14 | $0.28 | $0.05 | 0.64s | 83 tps | 99.87% | |
 DeepInfraus · fp8 | $0.06 | $0.18 | $0.01 | 0.80s | 36 tps | 99.86% |
 DigitalOcean | $0.12 | $0.24 | $0.02 | 0.73s | 37 tps | 99.84% |
 Cohere | $0.14 | $0.28 | $0.07 | 0.41s | 106 tps | 99.52% |
 Basetenfp8 | $0.13 | $0.26 | $0.03 | 0.84s | 76 tps | 99.39% |
| Basetenus · fp8 | $0.13 | $0.26 | $0.03 | 0.86s | 90 tps | 99.28% |
| $0.44 | $1.32 | $0.03 | 2.87s | 57 tps | 99.16% | |
| $0.02 | $0.42 | $0.01 | 5.54s | 22 tps | 98.98% | |
| $0.44 | $1.32 | $0.01 | 1.05s | 57 tps | 98.93% | |
| $0.13 | $0.26 | $0.03 | 2.01s | 45 tps | 98.91% | |
| $0.10 | $0.30 | $0.03 | 5.60s | 21 tps | 98.88% | |
| $0.01 | $0.58 | $0.01 | 2.06s | 13 tps | 98.25% | |
| $0.18 | $0.53 | $0.02 | 1.58s | 80 tps | 97.91% | |
| $0.20 | $0.60 | Variable | 1.53s | 40 tps | 97.69% | |
| $0.02 | $0.64 | $0.02 | 0.69s | 37 tps | 97.13% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Flash Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4 Flash Latest costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.01
per 1M tokens
Output
$0.58
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
DeepSeek V4 Flash Latest 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
Share of requests that at least one provider served successfully.
Last 3 days
Oct 11, 2:00 PMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V4 Flash Latest, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for DeepSeek V4 Flash Latest?
~deepseek/deepseek-v4-flash-latest. 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 Latest 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 Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.01 per 1M input tokens and $0.58 per 1M output tokens.
Who built DeepSeek V4 Flash Latest?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
