All models
Text & reasoningStable
DeepSeekDeepSeek-V4-Flash
DeepSeek's lower-cost V4 model for high-volume reasoning, coding, agents, and million-token text workloads.
Plain-English overview
What DeepSeek-V4-Flash actually is
DeepSeek-V4-Flash keeps the core text, reasoning, and tool interface of the V4 family while activating a smaller model and charging substantially less than Pro. It is the practical first test for routine coding agents, extraction, long-context analysis, and repeated tool loops.
The standard Flash endpoint is text-only; DeepSeek offers a separate experimental Flash Vision model for image input. Naming that distinction explicitly prevents an application from assuming the stable text route can accept media it does not support.
Good fit for
- Cost-efficient coding and agent workloads
- Large-context text analysis
- High-concurrency applications using familiar API formats
Category comparison
The facts that matter for text models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Context window
- 1M tokensMaximum combined prompt and working context documented by the provider.
- Maximum output
- Up to 384K tokensProvider-published response limit, where available.
- Knowledge cutoff
- Not publishedLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.
- Input price
- $0.44 / 1M peak uncached; $0.22 off-peakCurrent standard list price per million input tokens unless noted.
- Output price
- $1.32 / 1M peak; $0.66 off-peakCurrent standard list price per million output tokens unless noted.
- Inputs
- Text; separate Flash-Vision-Exp accepts imagesMedia types accepted by the listed model endpoint.
- Tools & agents
- Tools, JSON output, Responses API, thinking effort, FIM betaSelected native tools and agent-building capabilities, not an exhaustive list.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Advanced options
DeepSeek-V4-Flash
DeepSeek
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get DeepSeek-V4-Flash
Availability
Regions and access stage
Available in the DeepSeek API through OpenAI-, Anthropic-, and Responses-compatible formats; current API version is V4-Flash-0731.
DeepSeek's public model pages do not enumerate one global model-specific country or processing-region list; confirm account eligibility and applicable law.
Check live availabilityData and training
The route matters.
DeepSeek documents its Responses API as stateless and says responses and conversations are not stored by that endpoint. This is not a complete account-wide retention or training-use promise; review current platform terms and automatic cache behavior for sensitive data.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
DeepSeek-V4-Flash FAQ
What is DeepSeek-V4-Flash?
DeepSeek's lower-cost V4 model for high-volume reasoning, coding, agents, and million-token text workloads. DeepSeek-V4-Flash keeps the core text, reasoning, and tool interface of the V4 family while activating a smaller model and charging substantially less than Pro. It is the practical first test for routine coding agents, extraction, long-context analysis, and repeated tool loops.
When was DeepSeek-V4-Flash released?
DeepSeek-V4-Flash was released on July 31, 2026 according to the cited provider materials.
Where can I access DeepSeek-V4-Flash?
Available in the DeepSeek API through OpenAI-, Anthropic-, and Responses-compatible formats; current API version is V4-Flash-0731. The access routes listed in this guide are DeepSeek API and DeepSeek.
How much does DeepSeek-V4-Flash cost?
Peak: $0.44 input · $1.32 output / 1M tokens. Off-peak uncached input and output are $0.22 and $0.66 per million. Cached input is cheaper, and the separate experimental Vision route uses Flash token pricing.
Where is DeepSeek-V4-Flash available?
Available in the DeepSeek API through OpenAI-, Anthropic-, and Responses-compatible formats; current API version is V4-Flash-0731. DeepSeek's public model pages do not enumerate one global model-specific country or processing-region list; confirm account eligibility and applicable law.
Is my DeepSeek-V4-Flash API data used for training?
DeepSeek documents its Responses API as stateless and says responses and conversations are not stored by that endpoint. This is not a complete account-wide retention or training-use promise; review current platform terms and automatic cache behavior for sensitive data. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Small 4$0.15
Mistral AI
- Gemini 3.8 Flash$0.75
Google
- GPT-5.6 Sol$4.00
OpenAI
- GPT-6 Astra$10.00
OpenAI
- Claude Fable 5.1$10.00
Anthropic
- Mistral Small 4$0.60
Mistral AI
- Gemini 3.8 Flash$3.75
Google
- GPT-5.6 Sol$20.00
OpenAI
- GPT-6 Astra$50.00
OpenAI
- Claude Fable 5.1$50.00
Anthropic
Related comparisons
Head-to-head comparisons
DeepSeek-V4-Flash vs GPT-6 Astra
OpenAI's most capable model for difficult end-to-end work, combining frontier reasoning with a million-token context window and a broad set of agent tools.
Open full comparisonDeepSeek-V4-Flash vs GPT-5.6 Sol
OpenAI's flagship general model for difficult coding, analysis, and professional work, with a very large context window and a broad native tool set.
Open full comparisonDeepSeek-V4-Flash vs Claude Fable 5.1
Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.
Open full comparisonDeepSeek-V4-Flash vs Gemini 3.8 Flash
Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Open full comparisonDeepSeek-V4-Flash vs Grok 4.6
SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools.
Open full comparisonDeepSeek-V4-Flash vs Grok 4.20 Multi-Agent Beta
A specialist Grok model that sends several AI agents to investigate a difficult question in parallel, then combines their work into one researched answer.
Open full comparisonDeepSeek-V4-Flash vs Inkling
Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.
Open full comparisonDeepSeek-V4-Flash vs Mistral Medium 3.5
Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.
Open full comparisonDeepSeek-V4-Flash vs Mistral Small 4
Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint.
Open full comparisonDeepSeek-V4-Flash vs Qwen3.8 Max
Alibaba's frontier Qwen model for long-context reasoning, coding, tools, and understanding text, images, and video.
Open full comparisonDeepSeek-V4-Flash vs MiniMax M3
MiniMax's million-token multimodal model for coding, agents, computer use, and long projects at a low direct API price.
Open full comparisonDeepSeek-V4-Flash vs GLM-5.3
Z.ai's open-weight long-context reasoning model for coding, tools, and agentic work across self-hosted and managed routes.
Open full comparisonDeepSeek-V4-Flash vs Kimi K3
Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
Open full comparisonDeepSeek-V4-Flash vs Falcon-H1R-7B
TII's compact open reasoning model for text tasks, long contexts, and self-hosted function-calling workflows.
Open full comparisonDeepSeek-V4-Flash vs Falcon-H1-34B-Instruct
TII's 34B open instruction model for multilingual text, coding, and controlled self-hosted applications.
Open full comparisonDeepSeek-V4-Flash vs Muse Spark 1.3
Meta's latest multimodal reasoning model for long-running agents, coding, tools, and complex user collaboration.
Open full comparisonDeepSeek-V4-Flash vs Celeris-1 Magnus
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
Open full comparisonDeepSeek-V4-Flash vs NVIDIA Nemotron 3 Ultra
NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.
Open full comparisonDeepSeek-V4-Flash vs NVIDIA Nemotron 3.5 Lightning
NVIDIA's compact 30B mixture-of-experts model for efficient specialist agents and high-volume text workflows.
Open full comparisonDeepSeek-V4-Flash vs Qwen3.8-Flash
Alibaba's efficient million-context multimodal model for fast agents, coding, document work, vision, video understanding, and tool use.
Open full comparisonDeepSeek-V4-Flash vs DeepSeek-V4-Pro
DeepSeek's flagship million-context text model for difficult reasoning, coding, long-running agents, tools, and very large outputs.
Open full comparison
