DeepSeek
DeepSeek V4.1 Flash 1017
Launched 2026-10-17 · Knowledge up to 2025-05 · Listed on OpenRouter 2026-10-17
Prices updated . Benchmarks updated .
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...
You send / 1M
$0.036
tokens in
It replies / 1M
$0.500
tokens out
Context
1M
tokens it can read at once
Typical request
$0.0003
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 158.8 | Independent | 2026-10-17 | Epoch AI |
| GPQA DiamondMax effort | 93.2% | Independent | 2026-10-19 | Epoch AI |
| OTIS Mock AIMEMax effort | 99.4% | Independent | 2026-10-19 | Epoch AI |
| SimpleQA VerifiedMax effort | 42.5% | Independent | 2026-10-19 | Epoch AI |
| ARC-AGI-2Max effort | 78.1% | Independent | 2026-10-17 | ARC Prize, republished by Epoch AI |
| CritPtMax effort | 24.0% | Independent | 2026-10-17 | 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 |
|---|---|---|---|---|
| Sail Research · fp4 | $0.040 | $0.070 | 91% | Read |
| Sail Research · fp4 | $0.040 | $0.070 | 71% | Read |
| Ionstream | $0.077 | $0.233 | 100% | Read |
| DeepInfra · fp8 | $0.078 | $0.235 | 44% | Read |
| DeepInfra · fp8 | $0.098 | $0.294 | 100% | Read |
| Particle AI | $0.040 | $0.300 | 100% | Read |
| River | $0.086 | $0.346 | 100% | Read |
| Makora · fp8 | $0.120 | $0.400 | 100% | n/a |
| StepFun · fp8 | $0.105 | $0.420 | 100% | n/a |
| DeepInfra · fp8 | $0.147 | $0.441 | 99% | Read |
| Novita · fp8 | $0.120 | $0.480 | 100% | Read |
| Cohere · fp8 | $0.150 | $0.500 | 100% | Read |
| Wafer · mxfp4 | $0.036 | $0.500 | 100% | Read |
| Wafer · mxfp4 | $0.070 | $0.500 | 100% | Read |
| Relace · fp4 | $0.120 | $0.500 | 100% | Read |
| Morph · fp8 | $0.059 | $0.520 | 100% | Read |
| SiliconFlow · fp8 | $0.300 | $0.550 | 100% | Read |
| Particle AI | $0.080 | $0.600 | 100% | Read |
| Cloudflare | $0.100 | $0.600 | 100% | Read |
| InferenceNet · fp8 | $0.080 | $0.605 | 100% | Read |
| InferenceNet · fp8 | $0.080 | $0.605 | 100% | Read |
| Ionstream | $0.210 | $0.620 | 100% | Read |
| ModelRun · fp4 | $0.170 | $0.670 | 100% | Read |
| DekaLLM | $0.180 | $0.680 | 98% | Read |
| PrimeIntellect | $0.044 | $0.700 | 98% | Read |
| DigitalOcean | $0.180 | $0.720 | 100% | Read |
| Fireworks | $0.210 | $0.840 | 88% | Read |
| PrimaLabs | $0.240 | $0.960 | 98% | Read |
| Modal | $0.250 | $1.00 | 100% | Read |
| Nebius · fp8 | $0.300 | $1.20 | 100% | Read |
| Mistral · fp8 | $0.300 | $1.20 | 100% | Read |
| CoreWeave · fp8 | $0.300 | $1.20 | 100% | Read |
| Near AI | $0.300 | $1.20 | 100% | Read |
| Venice · fp8 | $0.300 | $1.20 | 100% | Read |
| OpenInference · fp4 | $0.090 | $1.20 | 100% | Read |
| Together | $0.300 | $1.20 | 100% | Read |
| Crusoe · fp8 | $0.290 | $1.20 | 100% | Read |
| Fireworks | $0.300 | $1.20 | 100% | Read |
| BaseTen | $0.300 | $1.20 | 100% | Read |
| Parasail · fp8 | $0.300 | $1.20 | 100% | Read |
| Fireworks | $0.450 | $1.80 | 100% | Read |
| Morph · fp8 | $0.600 | $2.40 | 99% | Read |
| BaseTen | $0.600 | $2.40 | 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: 262K tokens
- Repeated text is billed at $0.010 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with DeepSeek V4.1 Flash 1017
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.
