DeepSeek: DeepSeek v4.1 Flash 1017

DeepSeek V4.1 Flash 1017 - API Pricing & Benchmarks | OpenRouter

Skip to content

Alpha

Search⌘K

ModelsBenchmarksChatRankingsAppsOriPricingDocs

• Models
• Rankings
• Ori

BenchmarksChatPricingDocs

Sign Up

Sign Up *

ElevenLabs launch offer: every ElevenLabs model is 50% off through October 19, 2026.See ElevenLabs models

Dismiss

DeepSeek: DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

Model weights

CompareAPI Try this model

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 from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp Opens in new tab.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro Opens in new tab on performance, speed, and task completion time.

Show more

Modalities

In / Out Price

$0.09 / $0.55 per 1M

Context

1.0M

Released

Oct 17, 2026

DeepSeek: DeepSeek V4.1 Flash 1017

CompareAPI Try this model

ProvidersPricingPerformanceUptimeBenchmarksAppsActivityDocumentationFAQExplore

Providers

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Standard

Reasoning effort All Latency / throughput P50

Filter quantization

| Provider | Input/M | Output/M | Cache read/M | Latency | Throughput | Uptime | | --- | --- | --- | --- | --- | --- | --- | | Morph | $0.09 0 | $0.55 0 | $0.008 00 | 0.45 s | 76 tps | 100.00% | | inference.net | $0.10 0 | $0.50 0 | $0.002 00 | 1.33 s | 42 tps | 100.00% | | Cloudflare | $0.10 0 | $0.60 0 | $0.003 00 | 7.47 s | 39 tps | 100.00% | | DeepSeek | $0.15 0 | $0.60 0 | $0.003 00 | 1.33 s | 149 tps | 100.00% | | DeepInfra Priority 30% off | $0.30$0.21 0 | $0.90$0.63 0 | $0.009$0.0063 0 | 4.36 s | 16 tps | 94.12% | | Parasail | $0.30 0 | $1.20 0 | $0.006 00 | 1.05 s | 66 tps | 100.00% | | DeepInfra 30% off | $0.20$0.14 0 | $0.60$0.42 0 | $0.006$0.0042 0 | 3.33 s | 19 tps | 94.79% | | Not used in Standard routing:Why these endpoints are not used | | DeepInfra Flex 30% off | $0.16$0.112 | $0.48$0.336 | $0.0048$0.00336 | 239.0 s | 29 tps | 46.67% |

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

149 tok/s

P50, best across providers

Latency

0.45 s

P50, best provider

All locations

Reasoning effort All Latency / throughput P50 3 days

AutoExacto benchmarks

GPQA Diamond TAU-Bench Cloudflare 90.1%--inference.net 89.7%78.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.91%

Availability over the last 3 days

Oct 14, 5 PM - Oct 17, 5 PM

Availability 99.91%

Wed Thu Fri Now

Availability over the last 24 hours

OpenRouter Availability

99.90%

Without Routing

94.97%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through theEndpoints API. Learn more about ourload balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for DeepSeek: DeepSeek V4.1 Flash 1017 (Artificial Analysis) | Source | Benchmark | Score | | --- | --- | --- | | Artificial Analysis | DeepSeek V4.1 Flash (Max) Intelligence Index | 39.5 | | Artificial Analysis | DeepSeek V4.1 Flash (Max) HLE | 39.2% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) AA-LCR | 84.0% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) GDPval-AA | 55.0% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) CritPt | 14.3% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) SciCode | 51.9% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) Terminal-Bench 4.0 | 26.8% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) AA-Omniscience Accuracy | 46.4% | | Artificial Analysis | DeepSeek V4.1 Flash (Max) AA-Omniscience Non-Hallucination Rate | 3.5% |

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

16.8B tokens

2.

omp

new

9.04B tokens

3.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

8.37B tokens

4.

DeepSeek Harness

new

6.85B tokens

5.

pi

There are many coding agents, but this one is yours.

6.56B tokens

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

DeepSeek: DeepSeek Flash versions

Not currently available through EU in-region routing.In-region routing docs

Documentation

Guides, cookbooks, blog posts, and tools for building with DeepSeek: DeepSeek V4.1 Flash 1017 on OpenRouter.

• Does DeepSeek V4 Have Vision?Blog post

Frequently asked questions

What is DeepSeek V4.1 Flash 1017?

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 from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

Where is the DeepSeek V4.1 Flash 1017 documentation?

The DeepSeek V4.1 Flash 1017 documentation on OpenRouter includes the Does DeepSeek V4 Have Vision? blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does DeepSeek V4.1 Flash 1017 cost?

DeepSeek V4.1 Flash 1017 costs $0.09/M input tokens and $0.55/M output tokens, with separate rates for Cache Read at $0.008/M tokens.

What is the context length of DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.

Does DeepSeek V4.1 Flash 1017 support tool calling and structured outputs?

Yes. DeepSeek V4.1 Flash 1017 accepts tools and tool_choice for function calling on 5 of the 6 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does DeepSeek V4.1 Flash 1017 support?

DeepSeek V4.1 Flash 1017 accepts text and images as input and returns text.

Which providers serve DeepSeek V4.1 Flash 1017?

DeepSeek V4.1 Flash 1017 is served by 6 providers on OpenRouter: Morph, inference.net, Cloudflare, DeepInfra, DeepSeek, and Parasail. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was DeepSeek V4.1 Flash 1017 released?

DeepSeek V4.1 Flash 1017 was released on October 17, 2026.

Explore more models

AI Models with Vision: Multimodal LLMs for Image Understanding CollectionAI Model Rankings Ranking

More models from[DeepSeek](https://openrouter.ai/deepseek)

DeepSeek Pro Latest This model always redirects to the latest model in the DeepSeek Pro family. Text 1.0M context

DeepSeek Flash Latest This model always redirects to the latest model in the DeepSeek Flash family. Text 1.0M context

DeepSeek V4.1 Flash 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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time. Text 1.0M context$0.09 / $0.18

DeepSeek V4.1 Flash 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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time. Text 1.0M context$0.05 / $0.15

DeepSeek V4 Flash Vision Exp DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total. It is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images. Text 1.0M context$0.2156 / $0.6468

DeepSeek V4 Pro 0813 DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. Text 1.0M context$0.12 / $8

DeepSeek V4 Flash Latest This model always redirects to the latest model in the DeepSeek V4 Flash family. Text 1.0M context

DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash. Text 1.0M context$0.0075 / $1.28

DeepSeek V4 Pro 0423 DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical Text 1.0M context$0.1775 / $0.3549

DeepSeek V4 Flash 0423 DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. Reasoning efforts `high` and `xhigh` are supported; `xhigh` maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important. Text 1.0M context$0.0151 / $1.28

DeepSeek V3.2 Speciale DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning to push capability beyond the base model. Reported evaluations place Speciale ahead of GPT-5 on difficult reasoning workloads, with proficiency comparable to Gemini-3.0-Pro, while retaining strong coding and tool-use reliability. Like V3.2, it benefits from a large-scale agentic task synthesis pipeline that improves compliance and generalization in interactive environments. Text 131K context

DeepSeek V3.2 DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments. Users can control the reasoning behaviour with the `reasoning``enabled` boolean. Learn more in our docs Text 164K context$0.2088 / $0.3096

DeepSeek V3.2 Exp DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the `reasoning``enabled` boolean. Learn more in our docs The model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs. Text 164K context$0.27 / $0.41

DeepSeek V3.1 Terminus DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning``enabled` boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. Text 164K context$0.27 / $1

DeepSeek V3.1 DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning``enabled` boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks. Text 164K context$0.25 / $0.95

DeepSeek V3.1 Base This is a base model, trained only for raw next-token prediction. Unlike instruct/chat models, it has not been fine-tuned to follow user instructions. Prompts need to be written more like training text or examples rather than simple requests (e.g., “Translate the following sentence…” instead of just “Translate this”). DeepSeek-V3.1 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks. Text 164K context

R1 Distill Qwen 7B DeepSeek-R1-Distill-Qwen-7B is a 7 billion parameter dense language model distilled from DeepSeek-R1, leveraging reinforcement learning-enhanced reasoning data generated by DeepSeek's larger models. The distillation process transfers advanced reasoning, math, and code capabilities into a smaller, more efficient model architecture based on Qwen2.5-Math-7B. This model demonstrates strong performance across mathematical benchmarks (92.8% pass@1 on MATH-500), coding tasks (Codeforces rating 1189), and general reasoning (49.1% pass@1 on GPQA Diamond), achieving competitive accuracy relative to larger models while maintaining smaller inference costs. Text 131K context

DeepSeek R1 0528 Qwen3 8B DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought. The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024. Text 131K context

R1 0528 May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model. Text 164K context$0.50 / $2.15

DeepSeek Prover V2 DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from DeepSeek-Prover-V1.5 Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description. Text 164K context

Previous slide Next slide

Footer


© 2026 OpenRouter, Inc

Product

• Chat
• Rankings
• Benchmarks
• Apps
• Discover
• Models
• Ori
• Collections
• Providers
• Tools
• Pricing
• Business
• EU routing
• Enterprise
• Labs

Company

• About
• Blog
• Careers Hiring
• Privacy
• Terms of Service
• Trust Center
• Support
• Works With OR
• Data
• Brand

Developer

• Documentation
• API Reference
• Developer Platform
• Status
• AI Site Map

Connect

• Discord
• GitHub
• LinkedIn
• X
• YouTube

CompareAPI Try

API

Your key, drop-in code and the LLMs.txt for deepseek/deepseek-v4.1-flash-1017.

Copy LLMs.txtView docs

AutoExacto benchmarks Rolling average over the past 32 days — the same lookback window used for quality-based routing[Learn more](https://openrouter.ai/docs/guides/routing/auto-exacto)

| Provider | GPQA Diamond | TAU-Bench Airline | | --- | --- | --- | | Cloudflare | 90.1% | -- | | inference.net | 89.7% | 78.0% |

Close

17