DeepSeek V4.1 Flash
Newer version available: DeepSeek V4.1 Flash 1017
- Family
- DeepSeek V4.1
- Released
- 2026-09-10
- Context
- 1M
- Max output
- 384K
- Parameters
- 552B
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open source
- License
- MITOSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Cheapest of 1 route · OpenRouter · cache read $0.006
About
DeepSeek V4.1 Flash is a 552B-parameter (8B prefill / 16B decode activated) mixture-of-experts model with Compressed Expert Dispatch (CED), released September 10, 2026 under the MIT license. It supports 1M-token context, up to 384K output tokens, multimodal vision input, reasoning, function calling, tool use, structured outputs, and prompt caching. Weights are available on Hugging Face. On October 17, 2026 DeepSeek replaced it on its API, web and app with DeepSeek V4.1 Flash 1017; the API name deepseek-flash now serves the 1017 version. The September weights remain on Hugging Face and third-party hosts still serve them.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.300 | $1.20 | read $0.006 | Serverless |
Deprecated provider routes(1)
| Provider | Status | Catalog ID |
|---|---|---|
| DeepSeek Platform | DeprecatedRetired October 17, 2026 | deepseek-flash |
Available via routers & gateways(4)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Requesty
HybridAI gateway to 400+ LLM providers with intelligent routing, caching, guardrails, and governance; flat 5% markup on model costs with no subscription fee.
Respan
HybridUnified LLM engineering platform (gateway + observability + evals + prompt management) routing across 250+ models; previously Keywords AI, rebranded February 2026.
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(19)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 90.9 | GPQA Diamond Pass@1; max reasoning effort (reasoning_effort=100)Observed 2026-09-10 | — | ||
| 36.8 | HLE Pass@1; full set; no tools; max reasoning effortObserved 2026-10-17 | — | ||
| 63.9 | HLE with tools Pass@1; max reasoning effortObserved 2026-09-10 | — | ||
| 3471.0 | Codeforces Rating; max reasoning effortObserved 2026-09-10 | — | ||
| 65.6 | MathArena Apex Pass@1; max reasoning effortObserved 2026-09-10 | — | ||
| 90.6 | Terminal-Bench 2.1 Pass@1; DeepSeek Harness Minimal mode; 1M contextObserved 2026-09-10 | — | ||
| 30.0 | Terminal-Bench 3.0 Pass@1; DeepSeek Harness Minimal mode; 1M contextObserved 2026-09-10 | — | ||
| 31.2 | Terminal-Bench 4.0 Pass@1; DeepSeek Harness Minimal mode; 1M contextObserved 2026-10-17 | — | ||
| 74.2 | DeepSWE 1.1 Resolved; mini-SWE harness; max reasoning effortObserved 2026-09-10 | — | ||
| 20.3 | ProgramBench Almost@1; DeepSeek Harness Minimal mode; 1M contextObserved 2026-09-10 | — | ||
| 65.4 | NL2Repo-Bench Score; DeepSeek Harness Minimal mode; 1M contextObserved 2026-10-17 | — | ||
| 88.1 | CyberGym Pass@1; max reasoning effortObserved 2026-09-10 | — | ||
| 62.8 | SEC-Bench Pro Pass@1; Claude Code harness; max reasoning effortObserved 2026-09-10 | — | ||
| 15.3 | ExploitGym Pass@1; max reasoning effortObserved 2026-09-10 | — | ||
| 54.8 | AutomationBench Pass@1; official scaffold; max reasoning effortObserved 2026-09-10 | — | ||
| 31.8 | Agent's Last Exam Pass@1; official scaffold; max reasoning effortObserved 2026-09-10 | — | ||
| 78.9 | Chartography w/ tools Pass@1; Claude Code harness; 512k contextObserved 2026-09-10 | — | ||
| 89.6 | BabyVision w/ tools Pass@1; Claude Code harness; 512k contextObserved 2026-09-10 | — | ||
| 49.0 | ZeroBench-main w/ tools Pass@5; Claude Code harness; 512k contextObserved 2026-09-10 | — |
Migration checks
No linked migration route is available for this model yet.
Comparison and alternatives
Browse all comparisons →Cheapest of 1 route · OpenRouter · cache read $0.006