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$0.05 / $0.15
Context1M
ReleasedSep 10, 2026
Providers
34 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 DigitalOcean | $0.20 | $0.78 | $0.01 | 0.83s | 165 tps | 100% |
| $0.10 | $0.71 | $0.01 | 0.41s | 118 tps | 100% | |
| $0.10 | $0.65 | $0.01 | 0.52s | 84 tps | 100% | |
| $0.27 | $0.75 | $0.01 | 1.19s | 98 tps | 100% | |
| $0.30 | $1.20 | $0.01 | 0.31s | 202 tps | 100% | |
 Baseten | $0.30 | $1.20 | $0.01 | 0.37s | 199 tps | 100% |
 DeepInfraus · fp8 | $0.14 | $0.42 | $0.00 | 0.90s | 65 tps | 100% |
| $0.10 | $0.15 | $0.01 | 0.75s | 52 tps | 100% | |
| $0.29 | $1.20 | $0.01 | 0.54s | 101 tps | 100% | |
| $0.21 | $0.84 | $0.00 | 2.09s | 89 tps | 100% | |
| $0.30 | $1.20 | $0.03 | 0.41s | 140 tps | 100% | |
| $0.14 | $0.54 | $0.01 | 0.93s | 49 tps | 100% | |
| $0.33 | $1.32 | $0.03 | 1.33s | 68 tps | 100% | |
 SiliconFlowfp8 | $0.30 | $1.20 | $0.01 | 1.77s | 51 tps | 100% |
| $0.20 | $0.10 | $0.02 | 0.52s | 156 tps | 100% | |
| DeepInfraus · fp8 | $0.21 | $0.63 | $0.01 | 0.55s | 52 tps | 100% |
| $0.30 | $1.20 | $0.01 | 0.74s | 82 tps | 100% | |
| Basetenus | $0.30 | $1.20 | $0.01 | 0.20s | 177 tps | 100% |
 Fireworksus | $0.45 | $1.80 | $0.01 | 0.26s | 169 tps | 100% |
| $0.15 | $0.60 | $0.00 | 1.40s | 51 tps | 99.97% | |
| $0.27 | $1.15 | $0.01 | 0.40s | 155 tps | 99.97% | |
| $0.20 | $0.78 | $0.00 | 1.89s | 104 tps | 99.94% | |
| $0.09 | $0.18 | $0.02 | 1.12s | 74 tps | 99.92% | |
| $0.30 | $1.20 | $0.01 | 0.48s | 128 tps | 99.92% | |
| $0.04 | $0.08 | $0.00 | 1.41s | 23 tps | 99.89% | |
| Baseten | $0.60 | $2.40 | $0.01 | 0.28s | 151 tps | 99.74% |
| $0.18 | $0.72 | $0.00 | 2.34s | 93 tps | 99.72% | |
| $0.30 | $1.20 | $0.03 | 0.45s | 155 tps | 99.69% | |
| $0.05 | $0.60 | $0.01 | 0.69s | 78 tps | 99.66% | |
| $0.30 | $1.20 | $0.01 | 0.71s | 120 tps | 99.47% | |
| $0.30 | $1.20 | Variable | 0.68s | 70 tps | 99.23% | |
| Fireworks | $0.30 | $1.20 | $0.01 | 1.10s | 90 tps | 96.71% |
 CoreWeavefp8 | $0.15 | $0.65 | $0.00 | 0.46s | 204 tps | 96.46% |
| DeepInfraus · fp8 | $0.11 | $0.34 | $0.00 | 8.57s | 19 tps | 89.32% |
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
$0.05
per 1M tokens
Output
$0.15
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.
0.0s50.0s100.0s150.0s200.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Makora NovitaAI SiliconFlow Baidu Qianfan Alibaba Cloud Int. Wafer Crusoe Phala Ionstream Prime Intellect AtlasCloud Baseten Baseten Decart Morph StreamLake Baseten (us) Relace Open Inference Venice Parasail Fireworks (us) Together DeepInfra (us) Modal CoreWeave GMICloud Sail Research DigitalOcean inference.net Fireworks DeepInfra (us) DeepInfra (us) Nebius Token Factory
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Makora NovitaAI SiliconFlow Baidu Qianfan Alibaba Cloud Int. Wafer Crusoe Phala Ionstream Prime Intellect AtlasCloud Baseten Baseten Decart Morph StreamLake Baseten (us) Relace Open Inference Venice Parasail Fireworks (us) Together DeepInfra (us) Modal CoreWeave GMICloud Sail Research DigitalOcean inference.net Fireworks DeepInfra (us) DeepInfra (us) Nebius Token Factory
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.86%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 99.88%
100% 98% 97% 95%
Oct 18, 11:40 AMNow
Apps
Tools that most often run DeepSeek V4.1 Flash (batch), by tokens this week.
Activity
125636.4B tokens processed market-wide in the last month.
02000.0B4000.0B6000.0B8000.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
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 384,000 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 $0.05 per 1M input tokens and $0.15 per 1M output tokens.
Who built DeepSeek V4.1 Flash (batch)?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
