LiteLLMModels

DeepSeek V4 Flash API Pricing

As of October 10, 2026, DeepSeek V4 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on DeepSeek, with cache reads at $0.006 and cache writes at $0 per 1M tokens. Across 22 providers on LiteLLM, the input price ranges from $0.08 to $0.44. It has a 1,000,000-token context window and returns up to 393,216 tokens per response.

By DeepSeekModel ID deepseek-v4-flashPrices updated Checked
Input
$0.30 / 1M tokens
Output
$1.20 / 1M tokens
Cache read
$0.006 / 1M tokens
Context window
1,000,000 tokens
Max output
393,216 tokens
Providers
22
Added to LiteLLM
June 2026

DeepSeek V4 Flash pricing by provider

34 listings across 22 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
DeepSeekdeepseek-v4-flash$0.30$1.20$0.006$01M
DeepSeekdeepseek/deepseek-v4-flash$0.30$1.20$0.006$01M
AIHubMixaihubmix/deepseek-v4-flash$0.142$0.284$0.0284–1M
Alibaba Cloud Model Studiodashscope/deepseek-v4-flash$0.20$0.40$0.04–1M
Alibaba Cloud Model Studiosnapshot 0731dashscope/deepseek-v4-flash-0731$0.20$0.40$0.04–1M
Azure AI Foundryazure_ai/deepseek-v4-flash$0.19$0.51$0.028–1M
Azure AI Foundrysnapshot 0731azure_ai/DeepSeek-V4-Flash-0731$0.44$1.32$0.014–1M
Basetensnapshot 0731baseten/deepseek-ai/DeepSeek-V4-Flash-0731$0.13$0.26$0.028–1M
Databrickssnapshot 0731databricks/databricks-deepseek-v4-flash-0731$0.14$0.28$0.028$0.141M
DeepInfradeepinfra/deepseek-ai/DeepSeek-V4-Flash$0.09$0.18$0.018–1M
DeepInfrasnapshot 0731deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731$0.08$0.18$0.016–1M
Fireworks AIfireworks_ai/accounts/fireworks/models/deepseek-v4-flash$0.14$0.28$0.028–1M
Fireworks AIsnapshot 0731fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731$0.22$0.66$0.007–1M
Fireworks AIfireworks_ai/deepseek-v4-flash$0.14$0.28$0.028–1M
Fireworks AIsnapshot 0731fireworks_ai/deepseek-v4-flash-0731$0.22$0.66$0.007–1M
LibertAIlibertai/deepseek-v4-flash$0.25$1.75––200K
Nebius AI Studionebius/deepseek-ai/DeepSeek-V4-Flash$0.14$0.28––1M
Nebius AI Studiosnapshot 0731nebius/deepseek-ai/DeepSeek-V4-Flash-0731$0.14$0.28––1M
Novita AInovita/deepseek/deepseek-v4-flash$0.14$0.28$0.028–1M
Novita AIsnapshot 0731novita/deepseek/deepseek-v4-flash-0731$0.44$1.32$0.028–1M
Perplexitysnapshot 0731perplexity/perplexity/deepseek-v4-flash-0731$0.13$0.26$0.028––
Pinstripespinstripes/ps/deepseek-v4-flash$0.10$0.20––160K
Prismprism/deepseek-v4-flash$0.17$0.21$0.07–1M
Qianwen AI Platformqwen_ai_platform/deepseek-v4-flash$0.20$0.40$0.04–1M
Qianwen AI Platformsnapshot 0731qwen_ai_platform/deepseek-v4-flash-0731$0.20$0.40$0.04–1M
Show 9 more listings
ProviderModel name in LiteLLMInputOutputCache readCache writeContext
QwenCloudqwencloud/deepseek-v4-flash$0.20$0.40$0.04–1M
QwenCloudsnapshot 0731qwencloud/deepseek-v4-flash-0731$0.20$0.40$0.04–1M
Sailsnapshot 0731sail/deepseek-ai/DeepSeek-V4-Flash-0731$0.09$0.18$0.02–1M
Scalewaysnapshot 0731scaleway/deepseek-v4-flash-0731$0.40$0.80$0.08–256K
Tencent TokenHubtencent/deepseek-v4-flash$0.14$0.28$0.0028$01M
Tensormeshtensormesh/deepseek-ai/DeepSeek-V4-Flash$0.14$0.28$0–32K
Together AIsnapshot 0731together_ai/deepseek-ai/DeepSeek-V4-Flash-0731$0.14$0.28$0.03–1M
Weights & Biaseswandb/deepseek-ai/DeepSeek-V4-Flash$0.14$0.28$0.07–1M
Weights & Biasessnapshot 0731wandb/deepseek-ai/DeepSeek-V4-Flash-0731$0.13$0.28$0.07–262K

What DeepSeek V4 Flash costs in practice

1,000 requests with 2,000 input and 500 output tokens each

DeepSeek$1.20
DeepInfra$0.25
Sail$0.27
Pinstripes$0.30

100 long-document requests with 100,000 input and 2,000 output tokens each

DeepSeek$3.24
DeepInfra$0.836
Sail$0.936
Pinstripes$1.04

DeepSeek V4 Flash features

Use DeepSeek V4 Flash with LiteLLM

Call DeepSeek V4 Flash through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-v4-flash
    litellm_params:
      model: deepseek-v4-flash
      api_key: os.environ/DEEPSEEK_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek V4 Flash FAQ

How much does DeepSeek V4 Flash cost?

DeepSeek V4 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on DeepSeek, with cache reads at $0.006 and cache writes at $0 per 1M tokens. Across 22 providers on LiteLLM, the input price ranges from $0.08 to $0.44.

What is the context window of DeepSeek V4 Flash?

DeepSeek V4 Flash has a 1,000,000-token context window and returns up to 393,216 tokens per response.

Which providers offer DeepSeek V4 Flash?

DeepSeek V4 Flash is available from 22 providers through LiteLLM: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks, DeepInfra, Fireworks AI, LibertAI, Nebius AI Studio, Novita AI and Perplexity and 10 more. The lowest price is on DeepInfra.

How do I call DeepSeek V4 Flash with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepseek-v4-flash", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does DeepSeek V4 Flash support?

DeepSeek V4 Flash supports function calling, parallel tool calls, structured output, image input, reasoning, prompt caching and web search.

When did LiteLLM add DeepSeek V4 Flash?

DeepSeek V4 Flash was added to LiteLLM's model price file in June 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks.

Provider pages: DeepSeek, AIHubMix, Alibaba Cloud Model Studio, Azure AI Foundry, Baseten, Databricks, DeepInfra, Fireworks AI, LibertAI, Nebius AI Studio, Novita AI, Perplexity.