DeepSeek: DeepSeek V4.1 Flash (batch)
deepseek/deepseek-v4-1-flash-batchDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
Modalities
In / out per 1M$0.11 / $0.34
Context1M
ReleasedSep 10, 2026
Providers
32 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.03 | $0.80 | $0.01 | 2.25s | 28 tps | 100% | |
| $0.10 | $0.66 | $0.01 | 0.84s | 75 tps | 100% | |
 DeepInfraus · fp8 | $0.14 | $0.42 | $0.00 | 0.73s | 64 tps | 100% |
| $0.15 | $0.59 | $0.00 | 1.48s | 87 tps | 100% | |
 DeepSeek | $0.15 | $0.60 | $0.00 | 0.94s | 85 tps | 100% |
 DigitalOcean | $0.17 | $0.66 | $0.01 | 0.91s | 153 tps | 100% |
| $0.18 | $0.72 | $0.00 | 2.36s | 91 tps | 100% | |
| $0.20 | $0.78 | $0.00 | 2.74s | 104 tps | 100% | |
 CoreWeavefp8 | $0.20 | $0.65 | $0.02 | 0.49s | 180 tps | 100% |
 Basetenus · fp8 | $0.30 | $1.20 | $0.01 | 0.51s | 148 tps | 100% |
| $0.30 | $1.20 | $0.01 | 0.33s | 209 tps | 100% | |
| $0.30 | $1.20 | $0.03 | 0.53s | 166 tps | 100% | |
| Basetenfp8 | $0.30 | $1.20 | $0.01 | 0.45s | 103 tps | 100% |
 Fireworks | $0.30 | $1.20 | $0.01 | 2.61s | 55 tps | 100% |
| $0.30 | $1.20 | $0.01 | 1.48s | 75 tps | 100% | |
| Fireworksus | $0.45 | $1.80 | $0.01 | 0.75s | 212 tps | 100% |
| $0.30 | $1.20 | $0.01 | 0.75s | 106 tps | 99.97% | |
| $0.09 | $0.18 | $0.02 | 66.72s | 10 tps | 99.95% | |
| $0.10 | $0.99 | $0.03 | 0.84s | 75 tps | 99.95% | |
| $0.27 | $1.15 | $0.01 | 0.70s | 150 tps | 99.95% | |
| $0.21 | $0.84 | $0.00 | 1.78s | 80 tps | 99.92% | |
| $0.29 | $1.20 | $0.01 | 0.64s | 117 tps | 99.92% | |
| Baseten Fastfp32 | $0.60 | $2.40 | $0.01 | 0.57s | 333 tps | 99.36% |
| $0.02 | $0.60 | $0.01 | 1.09s | 91 tps | 99.23% | |
 SiliconFlowfp8 | $0.30 | $1.20 | $0.01 | 2.09s | 76 tps | 99.2% |
| $0.10 | $0.90 | $0.03 | 0.92s | 61 tps | 99.1% | |
| $0.19 | $0.77 | $0.00 | 1.00s | 93 tps | 99.07% | |
| $0.02 | $0.89 | $0.01 | 4.74s | 16 tps | 98.93% | |
| $0.15 | $0.60 | $0.00 | 1.19s | 69 tps | 98.85% | |
| $0.09 | $0.30 | $0.01 | 1.54s | 69 tps | 98.07% | |
| $0.27 | $1.10 | $0.01 | 1.13s | 142 tps | 97.34% | |
| $0.15 | $0.60 | $0.01 | 1.56s | 72 tps | 96.7% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4.1 Flash (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4.1 Flash (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.11
per 1M tokens
Output
$0.34
per 1M tokens
Cache read
$0.00
per 1M cached tokens
Included in every pass
DeepSeek V4.1 Flash (batch) 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
Makora NovitaAI SiliconFlow Baidu Qianfan Alibaba Cloud Int. Wafer Crusoe Phala Ionstream AtlasCloud Baseten Fast Baseten Decart Morph StreamLake Baseten (us) Relace Open Inference Venice Parasail Fireworks (us) Together DeepInfra (us) DeepSeek Modal CoreWeave GMICloud Sail Research DigitalOcean inference.net Fireworks Cloudflare
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 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
Makora NovitaAI SiliconFlow Baidu Qianfan Alibaba Cloud Int. Wafer Crusoe Phala Ionstream AtlasCloud Baseten Fast Baseten Decart Morph StreamLake Baseten (us) Relace Open Inference Venice Parasail Fireworks (us) Together DeepInfra (us) DeepSeek Modal CoreWeave GMICloud Sail Research DigitalOcean inference.net Fireworks Cloudflare
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.9%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.86%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V4.1 Flash (batch), by tokens this week.
Activity
115336.2B tokens processed market-wide in the last month.
02000.0B4000.0B6000.0B8000.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for DeepSeek V4.1 Flash (batch)?
deepseek/deepseek-v4.1-flash:batch. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V4.1 Flash (batch) hold?
1,048,576 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does DeepSeek V4.1 Flash (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.11 per 1M input tokens and $0.34 per 1M output tokens.
Who built DeepSeek V4.1 Flash (batch)?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
