DeepSeek V4 Flash
deepseek/deepseek-v4-flashDeepSeekoperationalDeepSeek V4 Flash: fast, low-cost general model with native multimodal support (retired by DeepSeek; requests route to V4.1 Flash).
Official pricing
USD per million tokens, exactly what DeepSeek publishes. ElevenRouter adds no markup on tokens.
Example: 1,000 input + 500 output tokens ≈ $0.00110. Zero-completion responses are never charged.
Specs
- Context
- 1M
- Max output
- 64K
- Modalities
- text+image->text
- Tokenizer
- DeepSeek
- Released
- 2026-09-20
- Family
- deepseek-flash
Availability on ElevenRouter
Measured by the routing engine; up when at least one credential can serve the model.
Observed performance
Real requests over the last 7 days.
- Time to first token p50
- —
- p95
- —
- Output tokens/s p50
- —
- p95
- —
Percentiles appear after five successful requests.
Usage on ElevenRouter
Tokens per day across all customers (anonymous, aggregate).
Use it
Any OpenAI or Anthropic SDK works by changing the base URL. Supported parameters: max_tokens, temperature, top_p, top_k, frequency_penalty, presence_penalty, repetition_penalty, seed, stop, tools, tool_choice, response_format, reasoning, include_reasoning.
curl https://elevenrouter.com/api/v1/chat/completions \
-H "Authorization: Bearer $ELEVENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "deepseek/deepseek-v4-flash", "messages": [{ "role": "user", "content": "Hello" }] }'Related models
- DeepSeek V4.1 Flash · DeepSeek$0.300 / $1.20
- DeepSeek V4 Pro · DeepSeek$1.32 / $3.96
- GPT-5.6 Luna · OpenAI$0.200 / $1.20
- Hunyuan Hy3 · Tencent$0.132 / $0.528
- GLM 5.3 Flash · Z.AI$0.150 / $0.500
- Claude Haiku 4.5 · Anthropic$1.00 / $5.00
- Qwen3.8 Max · Qwen$2.00 / $6.00
- Claude Sonnet 5 · Anthropic$2.00 / $10.00
Frequently asked questions
How much does DeepSeek V4 Flash cost on ElevenRouter?
DeepSeek V4 Flash is billed at DeepSeek's official list price: $0.440 per million input tokens and $1.32 per million output tokens, with cached input at $0.014. A request with 1,000 input and 500 output tokens costs about $0.00110.
What is the context length of DeepSeek V4 Flash?
DeepSeek V4 Flash accepts up to 1M tokens of context and can produce up to 64K output tokens.
Does DeepSeek V4 Flash support tool calling and structured outputs?
Yes, tool calling is supported and JSON mode is available; add the response-healing plugin for schema validation. Supported parameters: max_tokens, temperature, top_p, top_k, frequency_penalty, presence_penalty, repetition_penalty, seed, stop, tools, tool_choice, response_format, reasoning, include_reasoning.
How do I call DeepSeek V4 Flash?
Send an OpenAI-compatible chat completion to https://elevenrouter.com/api/v1/chat/completions with "model": "deepseek/deepseek-v4-flash" and your ElevenRouter key, or use the Anthropic Messages endpoint. Any OpenAI or Anthropic SDK works by changing the base URL.
Is DeepSeek V4 Flash available right now?
Availability is measured continuously by the routing engine. Current status: operational, 100.00% uptime over the last 30 days. When one credential fails, requests fail over to another automatically.