Baseten
99.95%Context1M
Max output32.8K
p50 latency1,397 ms
Throughput364.0 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
deepseek/deepseek-v4.1-flash
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal interactions. It combines native multimodal capabilities with a new architecture focused on stronger performance, faster responses, and lower computational cost.
Input / 1M tokens$0.15
Output / 1M tokens$0.6
Maximum context1M
Inference providers10
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Deepinfra
99.70%Context1M
Max output1M
p50 latency16,632 ms
Throughput12.0 t/s
Input price$0.2
Output price$0.6
Zero retentionNo trainingCaching
Deepseek
99.87%Context1M
Max output384K
p50 latency1,791 ms
Throughput241.0 t/s
Input price$0.15
Output price$0.6
Caching
Fireworks
100.00%Context1M
Max output1M
p50 latency2,463 ms
Throughput104.0 t/s
Input price$0.22
Output price$0.66
Zero retentionNo trainingCaching
Gmicloud
98.61%Context1M
Max output1M
p50 latency1,659 ms
Throughput206.0 t/s
Input price$0.3
Output price$1.2
Caching
Modal
99.95%Context1M
Max output1M
p50 latency1,970 ms
Throughput41.5 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
Morph
99.92%Context1M
Max output1M
p50 latency1,832 ms
Throughput7.0 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
Novita
100.00%Context1M
Max output393.2K
p50 latency2,755 ms
Throughput238.0 t/s
Input price$0.3
Output price$1.2
No trainingCaching
Parasail
92.99%Context1M
Max output1M
p50 latency2,405 ms
Throughput122.5 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
Wafer
99.85%Context1M
Max output1M
p50 latency1,799 ms
Throughput22.0 t/s
Input price$0.3
Output price$1.2
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 1M | 32.8K | 1,397 ms | 364.0 t/s | 99.948% | $0.3 | $1.2 | |
Deepinfra | 1M | 1M | 16,632 ms | 12.0 t/s | 99.697% | $0.2 | $0.6 | |
Deepseek | 1M | 384K | 1,791 ms | 241.0 t/s | 99.871% | $0.15 | $0.6 | |
Fireworks | 1M | 1M | 2,463 ms | 104.0 t/s | 99.997% | $0.22 | $0.66 | |
Gmicloud | 1M | 1M | 1,659 ms | 206.0 t/s | 98.609% | $0.3 | $1.2 | |
Modal | 1M | 1M | 1,970 ms | 41.5 t/s | 99.955% | $0.3 | $1.2 | |
Morph | 1M | 1M | 1,832 ms | 7.0 t/s | 99.915% | $0.3 | $1.2 | |
Novita | 1M | 393.2K | 2,755 ms | 238.0 t/s | 99.997% | $0.3 | $1.2 | |
Parasail | 1M | 1M | 2,405 ms | 122.5 t/s | 92.985% | $0.3 | $1.2 | |
Wafer | 1M | 1M | 1,799 ms | 22.0 t/s | 99.852% | $0.3 | $1.2 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningTool useAutomatic cachingVisionTools
Technical profile
- Model type
- Language model
- Release date
- Sep 8, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
deepseek/deepseek-v4.1-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.