DeepSeek-V3.1

ActiveDeepSeekdeepseek/deepseek-v3-16 platforms

What breaks Add its dates to my calendar

Shutting down. DeepSeek-V3.1 shuts down on Google Vertex AI on Oct 21, 2026. DeepSeek names DeepSeek-V4-Flash as the replacement.

7 days

Next shutdown: 7 daysOct 21, 2026 · Google Vertex AI
Arena Text: 1,417#63 of 128 · Arena
Released: Aug 21, 2025DeepSeek

Dates on every platform

6 listings · a floor is the earliest possible date

DeepSeek-V3.1 on each platform: model ID, status, dates, replacement and source
Platform	Model ID and status	Deprecated	Shuts down	Replacement
Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026	`DeepSeek-V3.1:1`Shut down	–	Jul 13, 2026Shut down	DeepSeek-V4-Flash
Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026	`FW-DeepSeek-V3.1:1`Active	–	Jul 1, 20279 mo	–
Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-west-2 (opens in a new tab) · checked Oct 14, 2026ap-northeast-1, ap-south-1, ap-southeast-2, ap-southeast-3, eu-north-1, eu-west-2, us-east-2, us-west-2	`deepseek.v3-v1:0`Deprecated since Sep 30, 2026 · also deepseek.v3.1	–	Mar 30, 20275 mo	–
Google Vertex AIGoogle Cloud: Open model deprecations (opens in a new tab) · checked Oct 14, 2026	`deepseek-v3.1-maas`Deprecated	Jul 21, 2026	Oct 21, 20267 days	–
Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026	`deepseek-ai/DeepSeek-V3.1`Shut down	–	May 14, 2026Shut down	–
Fireworks AIFireworks AI: DeepSeek V3.1 model page (opens in a new tab) · checked Oct 14, 2026	`accounts/fireworks/models/deepseek-v3p1`Shut down	–	May 14, 2026Shut down	Kimi K2.6

Requests to retired deployments return 410 Gone.

Served by Fireworks through Foundry. Fireworks per-token models carry a 15-day retirement notice.

New customers can't use Legacy models on Bedrock, and accounts that stop calling one for 15 days may lose access before end of life.

On 14 October 2026 ListFoundationModels still returned this model as active with no end-of-life date; the Bedrock lifecycle page lists the Legacy and end-of-life dates.

Bedrock lists the public extended access start date as to be announced.

Google suggests self-deploying the model from Model Garden or moving to another managed endpoint.

Fireworks also named GLM 5.1 as a migration target.

Removed from serverless only; dedicated deployments of this model are unaffected.

What breaks when you move off DeepSeek-V3.1

Availability
New customers can't use Legacy models, and accounts that stop calling one for 15 days may lose access before the end-of-life date.
Gemma 3 4B IT, Gemma 3 12B IT, Gemma 3 27B IT, Llama 3 8B Instruct, Llama 3 70B Instruct, Llama 3.1 8B Instruct, Llama 3.1 70B Instruct, Llama 3.3 70B Instruct, Llama 4 Scout 17B 16E Instruct, Llama 4 Maverick 17B 128E Instruct, DeepSeek-R1, DeepSeek-V3.1, Qwen3-Coder-30B-A3B-Instruct, Qwen3-Coder-480B-A35B-Instruct, MiniMax-M2, MiniMax-M2.1, Devstral 2, Mistral 7B Instruct, Mixtral 8x7B Instruct, Voxtral Mini, Voxtral Small, Kimi K2 Thinking, NVIDIA Nemotron Nano 9B v2, NVIDIA Nemotron Nano 12B v2 VL, GLM-4.7, GLM-4.7-Flash · Amazon Bedrock · Mar 30, 2027
Availability
Requests to the model ID fail after the end-of-life date. Bedrock does not migrate applications to another model.
Gemma 3 4B IT, Gemma 3 12B IT, Gemma 3 27B IT, Llama 3 8B Instruct, Llama 3 70B Instruct, Llama 3.1 8B Instruct, Llama 3.1 70B Instruct, Llama 3.3 70B Instruct, Llama 4 Scout 17B 16E Instruct, Llama 4 Maverick 17B 128E Instruct, DeepSeek-R1, DeepSeek-V3.1, Qwen3-Coder-30B-A3B-Instruct, Qwen3-Coder-480B-A35B-Instruct, MiniMax-M2, MiniMax-M2.1, Devstral 2, Mistral 7B Instruct, Mixtral 8x7B Instruct, Voxtral Mini, Voxtral Small, Kimi K2 Thinking, NVIDIA Nemotron Nano 9B v2, NVIDIA Nemotron Nano 12B v2 VL, GLM-4.7, GLM-4.7-Flash · Amazon Bedrock · Mar 30, 2027
Tooling
You can't create new Provisioned Throughput or fine-tuning jobs for a Legacy model.
Gemma 3 4B IT, Gemma 3 12B IT, Gemma 3 27B IT, Llama 3 8B Instruct, Llama 3 70B Instruct, Llama 3.1 8B Instruct, Llama 3.1 70B Instruct, Llama 3.3 70B Instruct, Llama 4 Scout 17B 16E Instruct, Llama 4 Maverick 17B 128E Instruct, DeepSeek-R1, DeepSeek-V3.1, Qwen3-Coder-30B-A3B-Instruct, Qwen3-Coder-480B-A35B-Instruct, MiniMax-M2, MiniMax-M2.1, Devstral 2, Mistral 7B Instruct, Mixtral 8x7B Instruct, Voxtral Mini, Voxtral Small, Kimi K2 Thinking, NVIDIA Nemotron Nano 9B v2, NVIDIA Nemotron Nano 12B v2 VL, GLM-4.7, GLM-4.7-Flash · Amazon Bedrock · Mar 30, 2027
Availability
API requests to the retired model IDs fail after the retirement date.
DeepSeek-R1, DeepSeek-V3.2, DeepSeek-V3.1, GLM-5, GLM-4.7, gpt-oss-20b, Kimi K2 Thinking, Llama 3.3 70B Instruct, MiniMax-M2, Qwen3-235B-A22B-Instruct-2507, Qwen3-Coder-480B-A35B-Instruct, Qwen3-Next-80B-A3B-Instruct, Qwen3 Next 80B A3B Thinking · Google Vertex AI · Oct 21, 2026
Availability
Inference requests to retired deployments return 410 Gone.
DeepSeek-R1, DeepSeek-V3, DeepSeek-V3.1 · Azure AI Foundry · Jul 13, 2026
Availability
Serverless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.
DeepSeek-V3.1, DeepSeek-V3.2, GLM-4.7, GLM-5, Qwen3-8B, Qwen3-VL-30B-A3B-Thinking, Qwen3-VL-30B-A3B-Instruct, Llama 3.3 70B Instruct · Fireworks AI · May 14, 2026
Availability
Requests to the removed serverless model IDs fail. DeepSeek V3.1 and Qwen3 Coder Next stay available on on-demand dedicated endpoints; DeepSeek R1 does not.
DeepSeek-R1, DeepSeek-V3.1, Qwen3-Coder-Next · Together AI · May 14, 2026

Intelligence

Third-party results, credited below

Third-party benchmark scores for DeepSeek-V3.1
Benchmark	Publisher	Score	Rank	Published
Arena Text	Arena	1,417 ± 3	#63 of 128	Oct 8, 2026

Arena (arena.ai), https://arena.ai/leaderboard

List prices

$ per 1M tokens, with each price’s source

List prices per 1M tokens, in US dollars
Platform	Input	Cached	Output	In effect	Source
Amazon Bedrock`deepseek.v3-v1:0`	$0.58	–	$1.68	Oct 1, 2026Current · Standard tier on the bedrock-mantle endpoint (deepseek.v3.1) in us-east-1, where bedrock-runtime does not serve this model.	Amazon Web Services: AWS Price List API: AmazonBedrock, us-east-1 (opens in a new tab)

Change history

Mar 30, 2027Shutdown26 open-weight models reach end of life on Amazon BedrockAmazon Bedrock3 breaks

Bedrock moved 26 open-weight models from DeepSeek, Google, Meta, MiniMax, Mistral AI, Moonshot AI, NVIDIA, Qwen and Z.ai to Legacy on 30 September 2026. Requests to them fail after 30 March 2027. On 14 October 2026 ListFoundationModels still reported them as active.

AvailabilityNew customers can't use Legacy models, and accounts that stop calling one for 15 days may lose access before the end-of-life date.
AvailabilityRequests to the model ID fail after the end-of-life date. Bedrock does not migrate applications to another model.
ToolingYou can't create new Provisioned Throughput or fine-tuning jobs for a Legacy model.

Source: Amazon Web Services, Amazon Bedrock User Guide: Model lifecycle (Legacy) (opens in a new tab); Amazon Web Services, Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab)

Oct 21, 2026ShutdownDeepSeek, GLM, Kimi, Llama, MiniMax, Qwen and GPT OSS endpoints retire on Agent PlatformGoogle Vertex AI1 break

Google retires its managed endpoints for DeepSeek, GLM, GPT OSS 20B, Kimi K2 Thinking, Llama 3.3 70B, MiniMax M2 and Qwen3 models on Gemini Enterprise Agent Platform. Google suggests self-deploying them from Model Garden.

Platform: Google Vertex AI
Models: DeepSeek-R1, DeepSeek-V3.2, DeepSeek-V3.1, GLM-5, GLM-4.7, gpt-oss-20b, Kimi K2 Thinking, Llama 3.3 70B Instruct, MiniMax-M2, Qwen3-235B-A22B-Instruct-2507, Qwen3-Coder-480B-A35B-Instruct, Qwen3-Next-80B-A3B-Instruct, Qwen3 Next 80B A3B Thinking
Announced: Jul 21, 2026

AvailabilityAPI requests to the retired model IDs fail after the retirement date.

Source: Google Cloud, Gemini Enterprise Agent Platform release notes (opens in a new tab); Google Cloud, Open model deprecations (opens in a new tab)

Jul 13, 2026ShutdownDeepSeek R1-0528, V3-0324 and V3.1 retired on Azure AI FoundryAzure AI Foundry1 break

Microsoft retired DeepSeek-R1-0528, DeepSeek-V3-0324 and DeepSeek-V3.1. It lists DeepSeek-V4-Pro for R1-0528 and DeepSeek-V4-Flash for the V3 models.

Platform: Azure AI Foundry
Models: DeepSeek-R1, DeepSeek-V3, DeepSeek-V3.1

AvailabilityInference requests to retired deployments return 410 Gone.

Source: Microsoft, Model retirement schedule - Microsoft Foundry (opens in a new tab); Microsoft, Microsoft Foundry Models lifecycle and support policy (opens in a new tab)

May 14, 2026ShutdownFireworks removes eight older models from serverlessFireworks AI1 break

DeepSeek V3.1, DeepSeek V3.2, GLM 4.7, GLM 5, Qwen3 8B, both Qwen3 VL 30B A3B models and Llama 3.3 70B Instruct left serverless. Fireworks named Kimi K2.6, GLM 5.1, GPT-OSS 20B and GPT-OSS 120B as migration targets.

Platform: Fireworks AI
Models: DeepSeek-V3.1, DeepSeek-V3.2, GLM-4.7, GLM-5, Qwen3-8B, Qwen3-VL-30B-A3B-Thinking, Qwen3-VL-30B-A3B-Instruct, Llama 3.3 70B Instruct

AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.

Source: Fireworks AI, Changelog (opens in a new tab)

May 14, 2026ShutdownDeepSeek R1, DeepSeek V3.1 and Qwen3 Coder Next leave Together serverlessTogether AI1 break

Together removed deepseek-ai/DeepSeek-R1, deepseek-ai/DeepSeek-V3.1 and Qwen/Qwen3-Coder-Next-FP8 from serverless inference.

Platform: Together AI
Models: DeepSeek-R1, DeepSeek-V3.1, Qwen3-Coder-Next

AvailabilityRequests to the removed serverless model IDs fail. DeepSeek V3.1 and Qwen3 Coder Next stay available on on-demand dedicated endpoints; DeepSeek R1 does not.

Source: Together AI, Deprecations (opens in a new tab); Together AI, Changelog (opens in a new tab)