DeepSeek-V4-Flash
Shutting down. DeepSeek-V4-Flash shuts down on Together AI on Oct 22, 2026. DeepSeek names DeepSeek-V4.1-Flash as the replacement.
8 days- Next shutdown
- 8 daysOct 22, 2026 · Together AI
- Arena Text
- 1,436#53 of 128 · Arena
- GPQA Diamond
- 91.0%#26 of 108 · Epoch AI
- List price · $ per 1M
- $0.44 in $1.32 outAzure AI Foundry · cached input $0.014
- Context window
- 1Mtokens
Dates on every platform
| 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-V4-Flash-0731:2026-07-31Preview | – | ≥ 50 daysNot sooner than | – |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | DeepSeek-V4-Flash:2026-04-23Active | – | 16 mo | – |
| Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026 | deepseek-ai/DeepSeek-V4-Flash-0731Deprecated | – | 8 days | DeepSeek-V4.1-Flash |
| Fireworks AIFireworks AI: DeepSeek-V4-Flash model page (opens in a new tab) · checked Oct 14, 2026 | accounts/fireworks/models/deepseek-v4-flashShut down | – | Shut down | – |
| Fireworks AIFireworks AI: Changelog (opens in a new tab) · checked Oct 14, 2026 | accounts/fireworks/models/deepseek-v4-flash-0731Shut down | Shut down | DeepSeek-V4.1-Flash |
Preview dates on Azure are a floor. Preview deployments are upgraded to a newer version or retired with at least 30 days' notice.
Microsoft lists DeepSeek-V4-Flash-0731 as the replacement version.
Supported by on-demand dedicated endpoints after removal from serverless.
Fireworks named DeepSeek V4 Flash (0731), a later snapshot of the same model, as the migration target. That snapshot left serverless on 25 September 2026.
Removed from serverless only; dedicated deployments of this model are unaffected.
Removed from serverless only; dedicated deployments of this model are unaffected.
What breaks when you move off DeepSeek-V4-Flash
- Availability
- Availability
- Availability
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,436 ± 2 | #53 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 91.0% ± 1.8% | #26 of 108 | Aug 2, 2026 |
| Arena WebDev | Arena | 1,582 ± 5 | #20 of 69 | Oct 8, 2026 |
| FrontierMath Tier 4 | Epoch AI | 24.4% ± 6.8% | #36 of 58 | Aug 2, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 57.5% ± 2.9% | #37 of 71 | Aug 2, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 94.4% ± 2.1% | #35 of 105 | Aug 2, 2026 |
| SimpleQA Verified | Epoch AI | 33.6% ± 1.5% | #50 of 68 | Aug 27, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Azure AI FoundryDeepSeek-V4-Flash-0731:2026-07-31 | $0.44 | $0.014 | $1.32 | Aug 1, 2026Current · Global Standard rate from the US East 2 price list. | Microsoft: Azure Retail Prices API (Foundry Models, US East 2) (opens in a new tab) |
Azure AI FoundryDeepSeek-V4-Flash:2026-04-23 | $0.19 | $0.028 | $0.51 | Aug 1, 2026Current · Global Standard rate from the US East 2 price list. | Microsoft: Azure Retail Prices API (Foundry Models, US East 2) (opens in a new tab) |
Together AIdeepseek-ai/DeepSeek-V4-Flash-0731 | $0.14 | $0.03 | $0.28 | Aug 3, 2026Current | Together AI: Changelog (opens in a new tab) |
Change history
ShutdownDeepSeek V4 Flash 0731 leaves Together serverlessTogether AI1 break
Together removes deepseek-ai/DeepSeek-V4-Flash-0731 from serverless inference and recommends DeepSeek V4.1 Flash.
- Platform
- Together AI
- Model
- DeepSeek-V4-Flash
- Replacement
- DeepSeek-V4.1-Flash
- AvailabilityRequests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.
ShutdownFireworks removes older DeepSeek, GLM, Muse and Kimi models from serverlessFireworks AI1 break
DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), DeepSeek V4 Flash Vision Exp, Muse Glimmer 30B, Kimi K2.6, Kimi K2.7 Code and GLM 5.2 left serverless, including their Fast and US-only endpoints. Fireworks named DeepSeek V4.1 Flash, NVIDIA Nemotron 3.5 Lightning 30B A3B, GLM 5.3 and Kimi K3 as migration targets.
- Platform
- Fireworks AI
- Models
- DeepSeek-V4-Pro, DeepSeek-V4-Flash, DeepSeek-V4-Flash-Vision-Exp, Muse Glimmer 30B, Kimi K2.6, Kimi K2.7 Code, GLM-5.2
- Announced
- AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.
ShutdownOriginal DeepSeek V4 Flash leaves Fireworks serverlessFireworks AI1 break
Fireworks deprecated the original DeepSeek V4 Flash from serverless and pointed users to the DeepSeek V4 Flash (0731) snapshot, which later left serverless on 25 September 2026.
- Platform
- Fireworks AI
- Model
- DeepSeek-V4-Flash
- AvailabilityServerless requests to accounts/fireworks/models/deepseek-v4-flash stop working. Switch to a model that is still on serverless.
ReleaseDeepSeek V4 Flash 0731 arrives on Together serverlessTogether AI
deepseek-ai/DeepSeek-V4-Flash-0731 is available on serverless with a context length of one million tokens.
- Platform
- Together AI
- Model
- DeepSeek-V4-Flash
Source: Together AI, Changelog (opens in a new tab); Together AI, Available models (serverless) (opens in a new tab)