--- title: deepseek-v4-flash-vision-exp API — DeepSeek Pricing & Specs | RunAPI description: Use deepseek-v4-flash-vision-exp via RunAPI — the DeepSeek family. Per-call pricing, model ID, specs, and developer setup guide. url: https://runapi.ai/models/deepseek/v4-flash-vision-exp.md canonical: https://runapi.ai/models/deepseek/v4-flash-vision-exp locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-f702f2b1.png alternates: en: https://runapi.ai/models/deepseek/v4-flash-vision-exp zh-CN: https://runapi.ai/zh-CN/models/deepseek/v4-flash-vision-exp es: https://runapi.ai/es/models/deepseek/v4-flash-vision-exp ja: https://runapi.ai/ja/models/deepseek/v4-flash-vision-exp de: https://runapi.ai/de/models/deepseek/v4-flash-vision-exp fr: https://runapi.ai/fr/models/deepseek/v4-flash-vision-exp pt-BR: https://runapi.ai/pt-BR/models/deepseek/v4-flash-vision-exp ko: https://runapi.ai/ko/models/deepseek/v4-flash-vision-exp it: https://runapi.ai/it/models/deepseek/v4-flash-vision-exp nl: https://runapi.ai/nl/models/deepseek/v4-flash-vision-exp pl: https://runapi.ai/pl/models/deepseek/v4-flash-vision-exp tr: https://runapi.ai/tr/models/deepseek/v4-flash-vision-exp zh-TW: https://runapi.ai/zh-TW/models/deepseek/v4-flash-vision-exp zh-HK: https://runapi.ai/zh-HK/models/deepseek/v4-flash-vision-exp ar: https://runapi.ai/ar/models/deepseek/v4-flash-vision-exp x-default: https://runapi.ai/models/deepseek/v4-flash-vision-exp model: DeepSeek provider: DeepSeek variant_id: deepseek-v4-flash-vision-exp sdk_model_id: deepseek-v4-flash-vision-exp modality: text billing_unit: 1K tokens status: active --- > HTML version: https://runapi.ai/models/deepseek/v4-flash-vision-exp > Site index for agents: https://runapi.ai/llms.txt # deepseek-v4-flash-vision-exp API Use deepseek-v4-flash-vision-exp from the DeepSeek family via RunAPI. Per-call pricing, no subscription, and failed generations are never charged. **DeepSeek / [DeepSeek](https://runapi.ai/models/deepseek.md)** **Operational · text · Commercial OK** deepseek-v4-flash-vision-exp targets the sweet spot of quality and cost within the DeepSeek family. It shares the same API key, request shape, and async task lifecycle as every other RunAPI model — switch to this variant by changing one model ID parameter. Install the DeepSeek skill to load docs, typed schemas, pricing notes, and setup steps into your coding workspace. Billing is metered per completed request in USD with no subscription or minimum spend, and failed generations are never charged. - Pay-per-call pricing in USD with no subscription - Failed generations are never charged - Streaming when supported by the model - Schema-validated parameters and tool calls - Switch variant by changing one model ID parameter - Unified billing across all models and providers ## Pricing ### `message` - Input: $0.22 / 1M tokens - Output: $0.66 / 1M tokens - Cache read: $0.02 / 1M tokens ### `chat_completion` - Input: $0.22 / 1M tokens - Output: $0.66 / 1M tokens - Cache read: $0.02 / 1M tokens Failed generations are not charged ## Technical details | Field | Value | |---|---| | Model ID | `deepseek-v4-flash-vision-exp` | | Provider | DeepSeek | | Modality | text | | Task type | synchronous | | Billing unit | 1K tokens | | API endpoint | `/v1/chat/completions` | | | `/v1/responses` | | | `/v1/messages` | | | `/v1beta/models/deepseek-v4-flash-vision-exp:generateContent` | | | `/v1beta/models/deepseek-v4-flash-vision-exp:streamGenerateContent` | | Commercial license | Yes — included via API | | Catalog status | Operational | **Request example** ```json { "model": "deepseek-v4-flash-vision-exp", "messages": [ { "role": "user", "content": "Refactor this Python module for readability, explain each change, then add unit tests for the edge cases." } ] } ``` ## Model skill — deepseek-v4-flash-vision-exp Install the skill once, then use the variant ID from this page while building. Base URL: `https://runapi.ai` | Endpoint | Protocol | |---|---| | `POST /v1/chat/completions` | OpenAI compatible | | `POST /v1/responses` | OpenAI Responses | | `POST /v1/messages` | Anthropic compatible | | `POST /v1beta/models/deepseek-v4-flash-vision-exp:generateContent` | Gemini generateContent | | `POST /v1beta/models/deepseek-v4-flash-vision-exp:streamGenerateContent` | Gemini streamGenerateContent | Use the OpenAI or Anthropic SDK with your RunAPI API key and `model: "deepseek-v4-flash-vision-exp"`. ## Use deepseek-v4-flash-vision-exp with a model skill 1. **Install** — Install the model skill for the DeepSeek line. The skill loads docs, typed schemas, pricing notes, and setup steps into your coding workspace so your agent has the right context. 2. **Configure** — Set the model field to the full model ID shown on this page and configure your RunAPI API key as an environment variable. The same key works across all models and providers. 3. **Call** — Use the skill instructions while adding prompt, input, and callback handling to your application. RunAPI routes the request to the provider, manages the async lifecycle, and returns structured JSON. 4. **Receive** — Read the task response by polling the task ID, streaming when supported, or handling the webhook callback at your configured URL. Generated outputs are stored and retrievable by task ID. ## What's different about deepseek-v4-flash-vision-exp - **VS DEEPSEEK-V4-FLASH: 1M context; image input for vision tasks; JPEG, PNG, GIF, and WebP** — Fast, low-cost reasoning; toggle thinking per request - **VS DEEPSEEK-V4-PRO: 1M context; image input for vision tasks; JPEG, PNG, GIF, and WebP** — Flagship reasoning and analysis for complex agentic work ## Best for - **Customer support** — Answer customer questions from a private knowledge base, reducing ticket volume. - **Document analysis** — Draft contract summaries and flag key clauses for attorney review. - **Code generation** — Auto-generate unit tests, code reviews, and refactoring suggestions in CI. ## Frequently asked questions about deepseek-v4-flash-vision-exp ### How do I select deepseek-v4-flash-vision-exp? Pass the model ID shown in the quickstart. ### What's the rate limit on this variant? Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades. ### Can I switch variants later? Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape. ### Does it stream? Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery. ### Where do I report quality issues? Open an issue on the public GitHub repo or email support at support@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation. ### Do I need a separate provider account? No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider. ### Other variants of DeepSeek - [deepseek-v4-flash](https://runapi.ai/models/deepseek/v4-flash.md) — `deepseek-v4-flash` · Input $0.22 / 1M tokens | Output $0.66 / 1M tokens - [deepseek-v4-pro](https://runapi.ai/models/deepseek/v4-pro.md) — `deepseek-v4-pro` · Input $0.66 / 1M tokens | Output $1.98 / 1M tokens ### Alternatives from other models - [Claude](https://runapi.ai/models/claude.md) — Claude API access for Anthropic's LLM across complex reasoning, code, analysis, and extended-context tasks. - [Embedding](https://runapi.ai/models/embedding.md) — OpenAI text embeddings for semantic search, retrieval, clustering, and ranking workflows. - [Gemini](https://runapi.ai/models/gemini.md) — Gemini API access for Google's multimodal LLM across chat, code generation, reasoning, and long-context tasks. ## Start building with DeepSeek. - [Create free account](https://runapi.ai/login) - [Read the quickstart →](https://runapi.ai/docs/api/openai/chat-completions) --- ## More from RunAPI - [Home](https://runapi.ai/.md) - [Models](https://runapi.ai/models.md) - [AI Video API Comparison](https://runapi.ai/ai-video-api-comparison.md) - [OpenClaw Integration](https://runapi.ai/openclaw.md) - [Best API for OpenClaw](https://runapi.ai/best-api-for-openclaw.md) - [OpenClaw Image Generation](https://runapi.ai/openclaw-image-generation.md) - [Hermes Agent Integration](https://runapi.ai/hermes-agent.md) - [Pricing](https://runapi.ai/pricing.md) - [Claude API Pricing](https://runapi.ai/claude-api-pricing.md) - [ChatGPT API Pricing](https://runapi.ai/chatgpt-api-pricing.md) - [OpenAI API Pricing](https://runapi.ai/openai-api-pricing.md) - [Gemini API Pricing](https://runapi.ai/gemini-api-pricing.md) - [Claude Code Pricing](https://runapi.ai/claude-code-pricing.md) - [Claude Code API](https://runapi.ai/claude-code-api.md) - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Claude Max vs API](https://runapi.ai/claude-max-vs-api.md) - [Requesty Alternative](https://runapi.ai/requesty-alternative.md) - [Docs](https://runapi.ai/docs/guides) - [SDK](https://runapi.ai/sdk.md) - [Skills](https://runapi.ai/skills.md) - [MCP Server](https://runapi.ai/mcp.md) - [CLI](https://runapi.ai/cli.md) - [Feedback](https://runapi.makethisbetter.dev) - [Contact](mailto:support@runapi.ai) - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "DeepSeek deepseek-v4-flash-vision-exp", "applicationCategory": "DeveloperApplication" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "Models", "item": "https://runapi.ai/models" }, { "@type": "ListItem", "position": 3, "name": "DeepSeek", "item": "https://runapi.ai/models/deepseek" }, { "@type": "ListItem", "position": 4, "name": "deepseek-v4-flash-vision-exp", "item": "https://runapi.ai/models/deepseek/v4-flash-vision-exp" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "Use deepseek-v4-flash-vision-exp with a model skill", "description": "Use deepseek-v4-flash-vision-exp via RunAPI — the DeepSeek family. Per-call pricing, model ID, specs, and developer setup guide.", "totalTime": "PT5M", "step": [ { "@type": "HowToStep", "position": 1, "name": "Install", "text": "Install the model skill for the DeepSeek line. The skill loads docs, typed schemas, pricing notes, and setup steps into your coding workspace so your agent has the right context.", "url": "https://runapi.ai/models/deepseek/v4-flash-vision-exp#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Configure", "text": "Set the model field to the full model ID shown on this page and configure your RunAPI API key as an environment variable. The same key works across all models and providers.", "url": "https://runapi.ai/models/deepseek/v4-flash-vision-exp#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Call", "text": "Use the skill instructions while adding prompt, input, and callback handling to your application. RunAPI routes the request to the provider, manages the async lifecycle, and returns structured JSON.", "url": "https://runapi.ai/models/deepseek/v4-flash-vision-exp#how-step-3" }, { "@type": "HowToStep", "position": 4, "name": "Receive", "text": "Read the task response by polling the task ID, streaming when supported, or handling the webhook callback at your configured URL. Generated outputs are stored and retrievable by task ID.", "url": "https://runapi.ai/models/deepseek/v4-flash-vision-exp#how-step-4" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "How do I select deepseek-v4-flash-vision-exp?", "acceptedAnswer": { "@type": "Answer", "text": "Pass the model ID shown in the quickstart." } }, { "@type": "Question", "name": "What's the rate limit on this variant?", "acceptedAnswer": { "@type": "Answer", "text": "Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades." } }, { "@type": "Question", "name": "Can I switch variants later?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape." } }, { "@type": "Question", "name": "Does it stream?", "acceptedAnswer": { "@type": "Answer", "text": "Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery." } }, { "@type": "Question", "name": "Where do I report quality issues?", "acceptedAnswer": { "@type": "Answer", "text": "Open an issue on the public GitHub repo or email support at support@runapi.ai. Include the task ID and model ID so the team can investigate the specific generation." } }, { "@type": "Question", "name": "Do I need a separate provider account?", "acceptedAnswer": { "@type": "Answer", "text": "No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider." } } ] } ] ```