DeepSeek V4 Models by DeepSeek
Last refreshed 2026-08-24. Next refresh: weekly.
Details
Capabilities
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
- visionvision and multimodal workreasoning
- Capability starting point
- DeepSeek V4 Flash Vision Exp with 1m context and reasoning, JSON / Tool use, structured outputs, and multimodal inputs
- Lowest tracked input
- DeepSeek V4 Flash · $0.05866/1M · OpenRouter
- Closest related family
- Janus
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 | $0.435/1M | 1,456 | 80.6 | 93.5 | 90.1 |
| DeepSeek V4 Flash | 1m | $0.05866/1M | 1,437 | 79 | 91.6 | 88.1 |
| Kimi K2.6 | 262k | - | 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.
Use when the workload needs vision, 1m context, and reasoning.
Use when the workload needs 1m context, 284B parameters, and reasoning.
Use when the workload needs 1m context, 1600B parameters, and reasoning.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| DeepSeek V4 Flash Vision Exp | Use when the workload needs vision, 1m context, and reasoning. | 2026-08 | vision1m contextreasoning | 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
2 release groupsSpecifications(3 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | JSON / Tool use | Structured Outputs |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash Vision Exp | 2026-08 | 1m | — | Yes | Yes | Yes | Yes | Yes |
| 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(6 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| DeepSeek V4 Flash | OpenRouter | $0.05866 | $0.11732 | 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 | Microsoft Foundry | $0.19 | $0.51 | Serverless |
| DeepSeek V4 Flash | DeepSeek Platform | $0.22 | $0.66 | Serverless |
| DeepSeek V4 Flash Vision Exp | DeepSeek Platform | $0.22 | $0.66 | Serverless |
| DeepSeek V4 Pro | DeepSeek Platform | $0.435 | $0.87 | Serverless |
| DeepSeek V4 Pro | Vercel AI Gateway | $0.435 | $0.87 | Serverless |
| DeepSeek V4 Pro | OpenRouter | $0.44 | $0.87 | Serverless |
| DeepSeek V4 Pro | Novita AI | $1.6 | $3.2 | Serverless |
| DeepSeek V4 Pro | Fireworks AI | $1.74 | $3.48 | 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
- DeepSeek V4 Pro vs Llama 4 Maverick 17B Instruct FP8
- DeepSeek V4 Pro vs Grok 4
- DeepSeek V4 Flash vs Grok 4
- DeepSeek V4 Pro vs Mistral Large 2.1 (2411)
