DeepSeek V4 Models by DeepSeek
DeepSeek releases · 10 in the last 12 months · this family litChangelog →
5 models2026Up to 1M ctxFrom $0.076/1M input
Last refreshed 2026-10-19. Next refresh: weekly.
Details
ResearcherDeepSeek
LicenseMITOSI-approved
Commercial usePermitted
Models5
Released2026
Max context1M
Capabilities
Vision1 of 5 models
Multimodal1 of 5 models
ReasoningAll models
JSON / Tool use3 of 5 models
Structured Outputs3 of 5 models
Links
WebsiteAbout
DeepSeek V4 is the April 2026 DeepSeek release for long-context reasoning and coding. The family has two models: DeepSeek V4 Pro, a 1.6T-parameter MoE with 49B active parameters, a 1M-token context window, and the family's highest SWE-bench Verified score at 80.6, and DeepSeek V4 Flash, a 284B MoE with 13B active parameters for lower-cost inference. Direct DeepSeek pricing starts at $0.435 / $0.87 per million input / output tokens for Pro and $0.14 / $0.28 for Flash.
Decision facts
- Best fit
- vision and multimodal workreasoningJSON / Tool use
- Capability starting point
- DeepSeek V4 Pro with 1M context and reasoning, JSON / Tool use, and structured outputs
- Lowest tracked input
- DeepSeek V4 Flash 0731 · $0.076/1M · Vercel AI Gateway
- Closest related family
- DeepSeek OCR
Compare Against Top Competitors
Long-context coding and reasoning set for comparing DeepSeek V4 Pro and Flash against Kimi, Claude, GLM, and GPT-5. Scores come from existing benchmark seed data; "-" means this site has no local score for that benchmark yet.
| Model | Context | Input / 1M | Chatbot Arena | SWE-bench Verified | LiveCodeBench | GPQA |
|---|---|---|---|---|---|---|
| DeepSeek V4 Profamily pick | 1M | $0.363/1M | 1,456 | 80.6 | 93.5 | 90.1 |
| DeepSeek V4 Flash | 1M | $0.091/1M | 1,437 | 79 | 91.6 | 88.1 |
| Kimi K2.6 | 256K | - | 1,462 | 80.2 | 89.6 | 90.5 |
| Claude Sonnet 4.6 | 1M | - | 1,459 | 79.6 | 80 | 89.9 |
| GLM-5.1 | 200K | - | 1,475 | - | - | 86.2 |
| GPT-5.5 | 1.05M | - | 1,488 | 82.6 | - | 93.6 |
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
4 in view1 retired
DeepSeek V4 FlashCurrent
Use when the workload needs 1M context, 284B parameters, and reasoning.
2026-041M context284B parametersreasoning
DeepSeek V4 ProCurrent
Use when the workload needs 1M context, 1600B parameters, and reasoning.
2026-041M context1600B parametersreasoning
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | Use when the workload needs reasoning. | 2026-08 | reasoning | Current |
| DeepSeek V4 Flash 0731 | Use when the workload needs reasoning. | 2026-07 | reasoning | Current |
| DeepSeek V4 Flash | Use when the workload needs 1M context, 284B parameters, and reasoning. | 2026-04 | 1M context284B parametersreasoning | Current |
| DeepSeek V4 Pro | Use when the workload needs 1M context, 1600B parameters, and reasoning. | 2026-04 | 1M context1600B parametersreasoning | Current |
Release Timeline
3 release groups2026-08
1 current · 1 retired
DeepSeek V4 Flash Vision Exp
Archivedvision1M contextreasoning
DeepSeek V4 Pro 0813
Currentreasoning
2026-07
1 current
DeepSeek V4 Flash 0731
Currentreasoning
2026-04
2 current
DeepSeek V4 Flash
Current1M context284B parametersreasoning
DeepSeek V4 Pro
Current1M context1600B parametersreasoning
Specifications(5 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | JSON / Tool use | Structured Outputs |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | 2026-08 | — | — | No | No | Yes | No | No |
| DeepSeek V4 Flash 0731 | 2026-07 | — | — | No | No | Yes | No | No |
| DeepSeek V4 Flash | 2026-04 | 1M | 284B | No | No | Yes | Yes | Yes |
| DeepSeek V4 Pro | 2026-04 | 1M | 1.6T | No | No | Yes | Yes | Yes |
Available From(9 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | Vercel AI Gateway | $0.076 | $0.153 | Serverless |
| DeepSeek V4 Flash | OpenRouter | $0.091 | $0.182 | Serverless |
| DeepSeek V4 Flash 0731 | OpenRouter | $0.1298 | $0.3894 | Serverless |
| DeepSeek V4 Flash | Vercel AI Gateway | $0.13 | $0.26 | Serverless |
| DeepSeek V4 Flash | Novita AI | $0.14 | $0.28 | Serverless |
| DeepSeek V4 Flash 0731 | Together AI | $0.14 | $0.28 | Serverless |
| DeepSeek V4 Flash | Microsoft Foundry | $0.19 | $0.51 | Serverless |
| DeepSeek V4 Pro | OpenRouter | $0.363312 | $0.726624 | Serverless |
| DeepSeek V4 Pro | Vercel AI Gateway | $0.435 | $0.87 | Serverless |
| DeepSeek V4 Pro 0813 | OpenRouter | $0.66 | $1.98 | Serverless |
| DeepSeek V4 Pro 0813 | Vercel AI Gateway | $0.66 | $1.98 | Serverless |
| DeepSeek V4 Pro | DeepSeek Platform | $1.32 | $3.96 | Serverless |
| DeepSeek V4 Pro 0813 | Together AI | $1.32 | $3.96 | Serverless |
| DeepSeek V4 Pro | Novita AI | $1.6 | $3.2 | Serverless |
| DeepSeek V4 Pro | Featherless | $1.6 | $3.2 | Serverless |
| DeepSeek V4 Pro | Fireworks AI | $1.74 | $3.48 | Serverless |
| DeepSeek V4 Flash | Yandex AI Studio | $2.459016 | $4.09836 | Serverless |
Popular comparisons in this family
- DeepSeek V4 Pro vs GLM-5.118K
- DeepSeek V4 Pro vs Kimi K2.610K
- Claude Sonnet 4.6 vs DeepSeek V4 Flash6K
- DeepSeek V4 Flash vs Grok 45K
- DeepSeek V4 Flash vs Qwen3.6-27B5K
- Claude Sonnet 4.6 vs DeepSeek V4 Pro4K
- DeepSeek V4 Flash vs DeepSeek V4 Pro4K
- DeepSeek V4 Flash vs GLM-5.14K
- DeepSeek V4 Flash vs Kimi K2.63K
- DeepSeek V4 Pro vs Grok 43K
Comparisons
- GPT-4o (08-06) vs DeepSeek V4 Pro
- Claude Sonnet 4.6 vs DeepSeek V4 Pro
- Claude Sonnet 4.6 vs DeepSeek V4 Flash
- Claude Fable 5 vs DeepSeek V4 Pro
- Gemini 3.1 Pro Preview vs DeepSeek V4 Pro
- DeepSeek V4 Pro vs Llama 4 Maverick 17B Instruct FP8
- DeepSeek V4 Pro vs Grok 4
- DeepSeek V4 Flash vs Grok 4
