DeepSeek
DeepSeek V4.1 Flash
Launched 2026-09-10 · Knowledge up to 2025-05 · Listed on OpenRouter 2026-09-10
Prices updated . Benchmarks updated .
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
Context
1M
tokens it can read at once
Typical request
$0.0004
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 156.1 | Independent | 2026-09-09 | Epoch AI |
| GPQA DiamondMax effort | 89.8% | Independent | 2026-10-09 | Epoch AI |
| OTIS Mock AIMEMax effort | 98.3% | Independent | 2026-10-08 | Epoch AI |
| SimpleQA VerifiedMax effort | 42.9% | Independent | 2026-10-13 | Epoch AI |
| ARC-AGI-2Max effort | 72.9% | Independent | 2026-09-09 | ARC Prize, republished by Epoch AI |
| GDP.pdfMax effort | 19.8% | Independent | 2026-09-09 | Surge AI GDP.pdf, republished by Epoch AI |
| CritPtMax effort | 14.3% | Independent | 2026-09-09 | CritPt, republished by Epoch AI |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
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 |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.112 | $0.336 | 100% | Read |
| River | $0.096 | $0.384 | 100% | Read |
| DeepInfra · fp8 | $0.140 | $0.420 | 100% | Read |
| Novita · fp8 | $0.120 | $0.480 | 100% | Read |
| Relace · fp4 | $0.120 | $0.500 | 100% | Read |
| Wafer · mxfp4 | $0.051 | $0.567 | 100% | Read |
| InferenceNet · fp8 | $0.103 | $0.600 | 100% | Read |
| InferenceNet · fp8 | $0.103 | $0.600 | 100% | Read |
| DeepInfra · fp8 | $0.210 | $0.630 | 100% | Read |
| Reka | $0.120 | $0.640 | 99% | Read |
| CoreWeave · fp8 | $0.130 | $0.650 | 100% | Read |
| Wafer · mxfp4 | $0.190 | $0.650 | 100% | Read |
| Cohere · fp8 | $0.195 | $0.660 | 100% | Read |
| Mancer 2 · fp8 | $0.212 | $0.750 | 100% | Read |
| Fireworks | $0.210 | $0.840 | 100% | Read |
| Cloudflare | $0.100 | $0.900 | 100% | Read |
| DigitalOcean | $0.225 | $0.900 | 100% | Read |
| Makora · fp8 | $0.260 | $1.17 | 100% | n/a |
| $0.300 | $1.20 | 96% | Read | |
| Crusoe · fp8 | $0.290 | $1.20 | 100% | Read |
| OpenInference · fp4 | $0.090 | $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 |
| Parasail · fp8 | $0.450 | $1.80 | 100% | Read |
| Fireworks | $0.450 | $1.80 | 100% | Read |
| Venice · fp8 | $3.00 | $12.00 | 100% | 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
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 384K tokens
- Repeated text is billed at $0.0042 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with DeepSeek V4.1 Flash
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
