DeepSeek
DeepSeek V4.1 Flash
Released 2026-09-10
DeepSeek 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. It activates 8B parameters on input and 16B on...
You send / 1M
$0.140
tokens in
It replies / 1M
$0.420
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0004
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Decart · fp4 | $0.090 | $0.180 | 98% | Read |
| Sail Research · fp4 | $0.090 | $0.250 | 100% | Read |
| Sail Research · fp4 | $0.090 | $0.250 | 100% | Read |
| DeepInfra · fp8 | $0.112 | $0.336 | 100% | Read |
| Morph · fp8 | $0.103 | $0.339 | 100% | Read |
| DeepInfra · fp8 | $0.140 | $0.420 | 100% | Read |
| Relace | $0.070 | $0.500 | 100% | Read |
| InferenceNet · fp8 | $0.103 | $0.600 | 100% | Read |
| InferenceNet · fp8 | $0.103 | $0.600 | 100% | Read |
| DeepInfra · fp8 | $0.210 | $0.630 | 81% | Read |
| CoreWeave · fp8 | $0.130 | $0.650 | 99% | Read |
| Wafer · mxfp4 | $0.190 | $0.650 | 100% | Read |
| ModelRun · fp4 | $0.170 | $0.670 | 100% | Read |
| Novita · fp8 | $0.195 | $0.780 | 100% | Read |
| Fireworks | $0.210 | $0.840 | 100% | Read |
| Reka | $0.105 | $0.840 | 99% | Read |
| Phala | $0.210 | $0.840 | 100% | Read |
| DigitalOcean | $0.225 | $0.900 | 100% | Read |
| Mancer 2 · fp8 | $0.200 | $1.00 | 95% | Read |
| Makora · fp8 | $0.260 | $1.17 | 100% | n/a |
| $0.300 | $1.20 | 100% | Read | |
| Nebius · fp8 | $0.300 | $1.20 | 99% | Read |
| PrimeIntellect | $0.300 | $1.20 | 100% | n/a |
| Cohere | $0.300 | $1.20 | 99% | Read |
| Crusoe · fp8 | $0.290 | $1.20 | 100% | Read |
| BaseTen | $0.300 | $1.20 | 100% | Read |
| Together | $0.300 | $1.20 | 100% | Read |
| SiliconFlow · fp8 | $0.300 | $1.20 | 100% | Read |
| Modal | $0.300 | $1.20 | 100% | Read |
| BaseTen | $0.300 | $1.20 | 100% | Read |
| Parasail · fp8 | $0.300 | $1.20 | 100% | Read |
| Fireworks | $0.300 | $1.20 | 100% | Read |
| Venice · fp8 | $0.300 | $1.20 | 100% | Read |
| Fireworks | $0.450 | $1.80 | 100% | Read |
| OpenInference · fp4 | $0.013 | $1.80 | 100% | Read |
| BaseTen | $0.600 | $2.40 | 56% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 131K tokens
- Repeated text is billed at $0.0042 per 1M (prompt caching)
- Intelligence score: 24.7 / 100 (Artificial Analysis)
Similar models
- Gemma 4 31BGoogle · $0.200 in / $0.400 out per 1M
- Seed-2.0-MiniBytedance Seed · $0.100 in / $0.400 out per 1M
- GPT-5 NanoOpenAI · $0.050 in / $0.400 out per 1M
- Gemini 2.5 Flash LiteGoogle · $0.100 in / $0.400 out per 1M
- Qwen3.8 Omni FlashQwen · $0.150 in / $0.470 out per 1M
- Qwen3.8 FlashQwen · $0.150 in / $0.470 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Cheap AI Models