跳到正文
Hacker News 熱門(buzzing.cc 中文翻譯)·· 2026-10-17AI 評分65

OpenRouter 列出 DeepSeek V4.1 Flash 1017 模型快照

DeepSeek:DeepSeek v4.1 Flash 1017

AI 導讀

DeepSeek 透過 OpenRouter 提供 DeepSeek V4.1 Flash 1017,這是 DeepSeek V4.1 Flash 於 2026 年 10 月 17 日的模型快照。

正文

Skip to content

Image 1: OpenRouter

Alpha

Search⌘K

ModelsBenchmarksChatRankingsAppsOriPricingDocs

BenchmarksChatPricingDocs

Sign Up

Sign Up *

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

Dismiss

Image 2: Favicon for DeepSeek

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

$0.15 / $0.60 per 1M

Context

1.0M

Released

Oct 17, 2026

Image 3: Favicon for DeepSeek

DeepSeek: DeepSeek V4.1 Flash 1017

CompareAPI Try this model

ProvidersPricingPerformanceUptimeAppsActivityDocumentationFAQExplore

Providers

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Reasoning effort All Latency / throughput P50

Provider Input/M Output/M Cache read/M Latency Throughput Uptime
Image 4: Favicon for DeepSeek DeepSeek $0.15 $0.60 $0.003 1.21 s 152 tps 100.00%

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.

Weighted average

Weighted Avg Input Price

$0.01324

/M tokens

Weighted Avg Output Price

$0.5997

/M tokens

DeepSeek V4.1 Flash 1017 — Price history

Effective Listed

Input Output

Reset

3D 1W 1M 3M 1Y All

Chart visibility Provider Effective in /M Effective out /M Cache hit rate Token share 1d

| | Image 5: Favicon for DeepSeek DeepSeek | $0.0132 | $0.600 | 93.0% | 100.0% | | --- |

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

152 tok/s

P50, best across providers

Latency

1.21 s

P50, best provider

All locations

Reasoning effort All 3 days

Throughput

P50

Avg 155 tok/s

P75

Avg 103 tok/s

P90

Avg 66 tok/s

P95

Avg 53 tok/s

P99

Avg 37 tok/s

Latency

P50

Avg 1.21 s

P75

Avg 1.48 s

P90

Avg 1.81 s

P95

Avg 2.06 s

P99

Avg 2.97 s

E2E latency

P50

Avg 4.70 s

P75

Avg 9.26 s

P90

Avg 22.03 s

P95

Avg 36.79 s

P99

Avg 57.68 s

Tool call error rate

DeepSeek

Avg 1.69 %

Cache hit rate

DeepSeek

Avg 92.70 %

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.

99.72%

Availability over the last 3 days

Oct 14, 9 AM - Oct 17, 9 AM

Availability 99.72%

Wed Thu Fri Now

Availability over the last 24 hours

OpenRouter Availability

99.76%

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 the Endpoints API. Learn more about our load balancing and provider routing options.

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.

Image 6: Favicon for https://omp.sh/

omp

new

138M tokens

Image 7: Favicon for https://cline.bot

Cline

Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.

101M tokens

Image 8: Favicon for https://www.isekai.world/

ISEKAI ZERO

AI adventures. Travel with your favorite characters

96.6M tokens

Image 9: Favicon for https://nousresearch.com

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.

86.1M tokens

Image 10: Favicon for https://kilocode.ai/

Kilo Code

Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.

85.6M tokens

Activity

Token volume and request traffic to this model over time.

Tokens

Prompt

978K

Completion

7K

Reasoning

6K

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

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.

1

Get your API key

Create an API key from your OpenRouter dashboard and set it as an environment variable:

Get API Key

Copy Copied!

shell

export OPENROUTER_API_KEY=sk-or-v1-...

2

Make your first request

Use deepseek/deepseek-v4.1-flash-1017 with the OpenRouter API:

OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in your request to enable reasoning, and access the reasoning_details array in the response to see the model's internal reasoning before the final answer. When continuing a conversation, preserve the complete reasoning_details when passing messages back to the model so it can continue reasoning from where it left off. Learn more about reasoning tokens.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

TypeScript SDK Python TypeScript (fetch)cURL Python (OpenAI)TypeScript (OpenAI)

Copy Copied!

typescript

import { OpenRouter } from "@openrouter/sdk";

const openrouter = new OpenRouter({
  apiKey: "<OPENROUTER_API_KEY>"
});

// Stream the response to get reasoning tokens in usage
const stream = await openrouter.chat.send({
  chatRequest: {
    model: "deepseek/deepseek-v4.1-flash-1017",
    messages: [
      {
        role: "user",
        content: "How many r's are in the word 'strawberry'?"
      }
    ],
    stream: true
  }
});

let response = "";
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    response += content;
    process.stdout.write(content);
  }

  // Usage information comes in the final chunk
  if (chunk.usage) {
    console.log("\nReasoning tokens:", chunk.usage.completionTokensDetails?.reasoningTokens);
  }
}

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

3

Enable streaming

Add "stream": true to your request body to receive responses as server-sent events:

Copy Copied!

shell

curl -N https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
  "model": "deepseek/deepseek-v4.1-flash-1017",
  "stream": true,
  "messages": [
    {"role": "user", "content": "Hello"}
  ]
}'

Endpoint

Sends a request for a model response for the given chat conversation. Supports both streaming and non-streaming modes.

POSThttps://openrouter.ai/api/v1/chat/completions

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modeldeepseek/deepseek-v4.1-flash-1017

Creates a streaming or non-streaming response using the OpenAI Responses API format.

Docs

POSThttps://openrouter.ai/api/v1/responses

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modeldeepseek/deepseek-v4.1-flash-1017

Creates a message using the Anthropic Messages API format. Supports text, images, PDFs, tools, and extended thinking.

Docs

POSThttps://openrouter.ai/api/v1/messages

AuthorizationBearer $OPENROUTER_API_KEY

Content-Typeapplication/json

HTTP-Refereroptional — your site URL, for rankings

X-Titleoptional — your site name, for rankings

Modeldeepseek/deepseek-v4.1-flash-1017

Parameters

Name Type Default Description
reasoning map — Controls reasoning behavior for models that support thinking tokens, including whether reasoning is enabled, the reasoning effort, maximum reasoning tokens, and whether reasoning is excluded from the response.
max_tokens integer — This sets the upper limit for the number of tokens the model can generate in response.
temperature float 1 This setting influences the variety in the model's responses.
top_p float 1 This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P.
stop array — Stop generation immediately if the model encounter any token specified in the stop array.
frequency_penalty float 0 This setting aims to control the repetition of tokens based on how often they appear in the input.
presence_penalty float 0 Adjusts how often the model repeats specific tokens already used in the input.
logprobs boolean — Whether to return log probabilities of the output tokens or not.
top_logprobs integer — An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.
tools array — Tool calling parameter, following OpenAI's tool calling request shape.
tool_choice string or object — Controls which (if any) tool is called by the model.
response_format map — Forces the model to produce specific output format.

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.

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 $0.15/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.003/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 393,216 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. It supports response_format for JSON output, without JSON-schema enforcement.

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.

What other text models does DeepSeek have?

DeepSeek V4.1 Flash, DeepSeek V4 Flash Vision Exp, DeepSeek V4 Pro 0813 and 10 more are other text models from DeepSeek.

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 fromDeepSeek

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$0.0179 / $0.6246

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$0.1233 / $0.5588

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$0.0092 / $0.2971

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$0.1675 / $0.4607

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$0.02142 / $0.04284

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](https://openrouter.ai/deepseek/deepseek-v3.2)

[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](https://openrouter.ai/deepseek/deepseek-v3.2-exp)

[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](https://openrouter.ai/deepseek/deepseek-v3.1-terminus)

[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](https://openrouter.ai/deepseek/deepseek-chat-v3.1)

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

DeepSeek V3 Base Note that this is a base model mostly meant for testing, you need to provide detailed prompts for the model to return useful responses. DeepSeek-V3 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. DeepSeek-V3 Base is the pre-trained model behind DeepSeek V3 Text 131K context

DeepSeek V3 0324 DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well on a variety of tasks. Text 164K context$0.25 / $1

DeepSeek R1 Zero DeepSeek-R1-Zero is a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. It's 671B parameters in size, with 37B active in an inference pass. It demonstrates remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. See DeepSeek R1 for the SFT model. Text 164K context

R1 Distill Llama 8B DeepSeek R1 Distill Llama 8B is a distilled large language model based on Llama-3.1-8B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Hugging Face: Text

R1 Distill Qwen 1.5B DeepSeek R1 Distill Qwen 1.5B is a distilled large language model based on Qwen 2.5 Math 1.5B, using outputs from DeepSeek R1. It's a very small and efficient model which outperforms GPT 4o 0513 on Math Benchmarks. Other benchmark results include: The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Text 131K context

R1 Distill Qwen 32B DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 72.6\n- MATH-500 pass@1: 94.3\n- CodeForces Rating: 1691\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Text 128K context

R1 Distill Qwen 14B DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Text 131K context

R1 Distill Llama 70B DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. Text 128K context

R1 DeepSeek R1 is here: 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 &technical report. MIT licensed: Distill & commercialize freely! Text 64K context$0.70 / $2.50

DeepSeek V2.5 DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct. The new model integrates the general and coding abilities of the two previous versions. For model details, please visit DeepSeek-V2 page for more information. Text 128K context

Previous slide Next slide

Footer

Image 11: OpenRouterImage 12: OpenRouter

© 2026 OpenRouter, Inc

Product

Company

Developer

Connect

Join the OpenRouter newsletter Model usage data, product updates, and research reports. One email each week.

Subscribe

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.

Playground

Open in Chat

Sign in to try this model

Responses are AI-generated. Verify before relying on them.

Playground

Open in Chat

Sign in to try this model

Responses are AI-generated. Verify before relying on them.

CompareAPI Try

API

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

Copy LLMs.txtView docs

Throughput percentiles on OpenRouter

Reset All locations

Close

Latency percentiles on OpenRouter

Reset All locations

Close

End-to-End Latency percentiles on OpenRouter

Reset All locations

Close

Cache Hit Rate by Provider

Reset

Close

Tool Call Error Rate by Provider

Reset

Close

DeepSeek V4.1 Flash 1017 — Price history

Close

來源:Hacker News 熱門(buzzing.cc 中文翻譯) · openrouter.ai