DeepSeek V4 Flash
- Family
- DeepSeek V4
- Released
- 2026-04-24
- Context
- 1M
- Max output
- 384K
- Parameters
- 284B
- Architecture
- Mixture of Experts
- Specialization
- general
- Openness
- Open source
- License
- MITOSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Cheapest of 5 routes · OpenRouter · cache read $0.0182
About
DeepSeek V4 Flash is a 284B parameter (13B activated) Mixture-of-Experts language model with 1M-token context. It uses a hybrid attention architecture combining Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) for long-context inference, and supports thinking and non-thinking modes. MIT licensed. The legacy API aliases deepseek-chat and deepseek-reasoner mapped to its non-thinking and thinking modes and were scheduled for discontinuation on July 24, 2026. DeepSeek retired the model from its API on September 10, 2026. The legacy model name deepseek-v4-flash is still accepted, and DeepSeek now serves those requests with DeepSeek-V4.1-Flash-1017.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ BAgents
Q/$ AProviders(5)
Compare all 5Compare API pricing across 5 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| OpenRouter | $0.091 | $0.182 | read $0.0182 | Serverless |
| Vercel AI Gateway | $0.130 | $0.260 | read $0.028 | Serverless |
| Novita AI | $0.140 | $0.280 | read $0.028 | Serverless |
| Microsoft Foundry | $0.190 | $0.510 | read $0.028 | Serverless Scheduled retirement: February 20, 2028 |
| Yandex AI Studio | $2.46 | $4.10 | read $0.6148 | Serverless |
Deprecated provider routes(1)
| Provider | Status | Catalog ID |
|---|---|---|
| DeepSeek Platform | DeprecatedRetired September 10, 2026 | deepseek-v4-flash |
Available via routers & gateways(8)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(16)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 88.1 | GPQA Diamond pass@1, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 86.4 | MMLU-Pro EM, V4-Flash Think HighObserved 2026-07-03 | — | ||
| 79.0 | SWE-bench Verified resolved, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 52.6 | SWE-bench Pro resolved, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 91.6 | LiveCodeBench pass@1, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 69.5 | HumanEval pass@1, DeepSeek-V4-Flash-Base, 0-shotObserved 2026-07-03 | — | ||
| 88.7 | MMLU EM, DeepSeek-V4-Flash-Base, 5-shotObserved 2026-07-03 | — | ||
| 56.9 | Terminal Bench 2.0 accuracy, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 2.4 | xhighObserved 2026-06-30 | — | ||
| 34.8 | Humanity's Last Exam pass@1, no tools, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 45.1 | Humanity's Last Exam with tools pass@1, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 1437.0 | LMArena Chatbot Arena text leaderboard Elo, deepseek-v4-flash-thinkingObserved 2026-07-03 | — | ||
| 73.3 | SWE-bench Multilingual resolved, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 69.0 | MCPAtlas pass@1, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 73.2 | BrowseComp pass@1, V4-Flash Think MaxObserved 2026-07-03 | — | ||
| 57.4 | MATH EM, DeepSeek-V4-Flash-Base, 4-shotObserved 2026-07-03 | — |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(5)
Compare DeepSeek V4 Flash with other models
Comparison and alternatives
Browse all comparisons →Show all 69 popular comparisonssorted by 7-day search impressions
Cheapest of 5 routes · OpenRouter · cache read $0.0182