DeepSeek

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

Model weightsReleased Oct 17, 2026MIT

ThinkingToolsVisionopen weights

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...

Run in ChatOSS Cloud Plans

Cost / 1M tokens

Low usage

$0.15

input

$0.003

cached input

$0.60

output

Context Window

Up to 393K max output

Architecture

552B total · 32B active MoE

text + image → text

Quickstart & API

deepseek/deepseek-v4.1-flash-1017

Open the model picker in ChatOSS Desktop (Code, Kanban, or Chat) and select or paste this model ID.

Best for & Strengths

Key Strengths

Agentic coding1M context windowUltra-low cache cost ($0.003/M)Fast throughputMIT open weights

Recommended Workloads in ChatOSS

Autonomous coding agents
Full-stack web app generation
High-volume agent loops

Available in ChatOSS Code, Kanban Orchestrate, and Chat modes via Plus, Max, or BYOK.

Verified Evaluations

Benchmarks & Frontier Comparison

How DeepSeek V4.1 Flash 1017 compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.

View full Top 40 Leaderboard →

DeepSeek V4.1 Flash 1017GLM 5.3Kimi K3.1 ProClaude Opus 5.5

Benchmark (Metric)	DeepSeek V4.1 Flash 1017	GLM 5.3	Kimi K3.1 Pro	Claude Opus 5.5	Gemini 4 Argon
Agentic & Software Engineering
ChatOSS Agentic Coding Index (%)	63.2%	58.3%	65%	74.1%	73.9%
SWE-Bench Verified (%)	—	95.4%	94.8%	97%	94%
DeepSWE v1.1 (Pass@1 %)	77%	69%	73.5%	74.2%	77.9%
Vibe Code Bench v1.1 (%)	87.73%	78.1%	88.4%	90.3%	91.9%
Terminal-Bench 4.0 (%)	42.3%	42%	46.2%	65.2%	57.6%
Code Migration (%)	45.62%	44.2%	52%	66.7%	68.2%
Intelligence & Token Economics
Artificial Analysis Intelligence Index (0–100)	39.5	44.8	55.1	57.6	52.6
Input Price (/ 1M tokens)	$0.15	$1.40	$2.00	$4.00	$4.00
Output Price (/ 1M tokens)	$0.60	$4.40	$10.00	$20.00	$20.00

ChatOSS Agentic Coding Index

ChatOSS Benchmark Audit · 4-benchmark composite mean

63.2%

DeepSWE v1.1

DeepSWE / Official Audit · Mini-SWE-Agent

77%

Vibe Code Bench v1.1

Vals.ai · OpenHands

87.73%

Terminal-Bench 4.0

Vals.ai / Artificial Analysis · Terminus 2

42.3%

Terminal-Bench 2.1

Vals.ai · Terminus 2

90.6%

Code Migration

Vals.ai · Vals evaluation harness

45.62%

AutomationBench

Artificial Analysis v4.3

67%

CyberGym (Pass@1)

Model Release Evaluation

88.1%

Artificial Analysis Intelligence Index

Artificial Analysis

39.5

GPQA Diamond (Pass@1)

Benchmark Audit

90.9%

Humanity's Last Exam (Pass@1)

Artificial Analysis / Audit

43%

Design Arena: SPREADSHEET

Design Arena · Rank #6 (51.2% win)

1280 Elo

Design Arena: 3D

Design Arena · Rank #10 (46.7% win)

1362 Elo

Design Arena: ASCIIART

Design Arena · Rank #20 (50.8% win)

1220 Elo

Design Arena: Code Generation

Design Arena · Rank #20 (47.8% win)

1289 Elo

Active Provider Endpoints (36)

Upstream inference providers serving DeepSeek V4.1 Flash 1017, with per-provider pricing, context limits, quantization, and 24-hour uptime.

Provider	Input / 1M	Output / 1M	Cache Read / 1M	Context	Max Output	Quantization	Uptime (24h)
OpenInferencecache open-inference/fp4	$0.018	$1.80	$0.017	1M	944K	fp4	99.9%
Rekacache reka	$0.04	$0.50	$0.004	1M	393K	—	96.2%
Wafercache wafer/mxfp4	$0.07	$0.50	$0.0069	1M	944K	mxfp4	100.0%
Relacecache relace	$0.07	$0.50	$0.008	1M	944K	—	99.8%
DeepInfracache deepinfra/fp8/flex	$0.078	$0.235	$0.0024	1M	131K	fp8	68.5%
InferenceNetcache inference-net/us	$0.08	$0.55	$0.008	1M	393K	fp8	100.0%
InferenceNetcache inference-net/fp8	$0.08	$0.55	$0.008	1M	393K	fp8	100.0%
DeepInfracache deepinfra/fp8	$0.098	$0.294	$0.0029	1M	131K	fp8	99.9%
Cloudflarecache cloudflare	$0.10	$0.60	$0.003	1M	944K	—	100.0%
Sail Researchcache sail-research/fp4/us	$0.101	$0.15	$0.0067	1M	384K	fp4	100.0%
Sail Researchcache sail-research/fp4	$0.101	$0.15	$0.0067	1M	384K	fp4	100.0%
Morphcache morph/fp8	$0.123	$0.368	$0.004	1M	944K	fp8	100.0%
Ionstreamcache ionstream	$0.129	$0.51	$0.0072	1M	944K	—	99.9%
Decartcache decart/fp4	$0.129	$0.516	$0.0026	1M	262K	fp4	100.0%
DeepInfracache deepinfra/fp8/priority	$0.147	$0.441	$0.0044	1M	131K	fp8	100.0%
DeepSeekcache deepseek	$0.15	$0.60	$0.003	1M	393K	—	100.0%
Makoracache makora/fp8	$0.15	$1.20	$0.006	1M	944K	fp8	99.9%
Alibabacache alibaba	$0.165	$0.66	$0.017	1M	393K	—	100.0%
StreamLakecache streamlake/fp8	$0.178	$0.714	$0.0036	1M	384K	fp8	100.0%
GMICloudcache gmicloud/fp8	$0.18	$0.72	$0.0036	1M	944K	fp8	100.0%
AtlasCloudcache atlas-cloud/fp8	$0.195	$0.78	$0.0039	1M	393K	fp8	100.0%
Novitacache novita/fp8	$0.195	$0.78	$0.0039	1M	393K	fp8	100.0%
Phalacache phala	$0.20	$1.20	$0.006	1M	393K	—	99.9%
Fireworkscache fireworks/spot	$0.21	$0.84	$0.0042	1M	944K	—	100.0%
DigitalOceancache digitalocean	$0.225	$0.90	$0.006	1M	944K	—	100.0%
Modalcache modal	$0.25	$1.00	$0.005	1M	944K	—	99.4%
Baiducache baidu/fp8	$0.28	$1.13	$0.006	1M	393K	fp8	100.0%
Crusoecache crusoe/fp8	$0.29	$1.20	$0.007	1M	944K	fp8	100.0%
Nebiuscache nebius/fp8	$0.30	$1.20	$0.006	1M	944K	fp8	98.8%
SiliconFlowcache siliconflow/fp8	$0.30	$1.20	$0.006	1M	393K	fp8	99.7%
Togethercache together	$0.30	$1.20	$0.006	1M	944K	—	100.0%
Fireworkscache fireworks	$0.30	$1.20	$0.006	1M	944K	—	98.3%
PrimeIntellectcache primeintellect	$0.30	$1.20	$0.006	1M	131K	—	99.9%
BaseTencache baseten	$0.30	$1.20	$0.007	1M	262K	—	100.0%
Parasailcache parasail/fp8	$0.30	$1.20	$0.006	1M	944K	fp8	99.9%
Fireworkscache fireworks/us	$0.45	$1.80	$0.009	1M	944K	—	100.0%

Supported API Parameters

Parameters accepted by this model when called through ChatOSS or OpenRouter.

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Deep-Dive Benchmarks & Teardowns

Independent benchmark analysis and real-world agent billing teardowns featuring DeepSeek V4.1 Flash 1017.

2026-10-27 · 10 min read

MiniMax M3.1 Flash vs. DeepSeek V4.1 Flash 1017: cheaper tokens, higher bill

Both list at $0.15/$0.60 per million tokens, and MiniMax wins the business-workflow benchmarks. But on vals.ai's Vibe Code Bench v1.1, DeepSeek's October 17 checkpoint scores 87.73% at $0.58 per test while M3.1 Flash scores 73.94% at $1.15 — because the cheaper token burns 66.86M of them per task. Here is the independent evidence and the cache-aware math.

Read article →

2026-09-21 · 11 min read

GLM 5.3 Flash vs. DeepSeek V4.1 Flash: which is better at agentic coding?

Both labs ship a million-token context, MIT weights, and a ~$0.15-per-million price tag. On the independent harnesses that have actually run both models — vals.ai's Vibe Code Bench and Terminal-Bench 2.1, BenchLM's Vibe Code Bench 1-100, and Artificial Analysis' v4.3 index — DeepSeek V4.1 Flash wins agentic coding, and by a wider margin than either vendor's own table suggests.

Read article →

Compare Similar Models

Browse all models →

DeepSeek

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...

$0.14 / $0.42Coding 63.2%

DeepSeek

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,...

$0.216 / $0.647Intel 34.8

DeepSeek

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.

$0.66 / $1.98Coding 46.9%

DeepSeek

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....

$0.119 / $0.238Coding 44.2%

Anthropic

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

$4.00 / $20.00Coding 74.1%

Moonshot AI

Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

$2.00 / $10.00Coding 65%