cheapaimodelSearch
Back to models

DeepSeek: DeepSeek-V4.1-Flash30% off

Verified
DeepSeekdeepseek-v4-1-flash
#1 on OpenRouter this week

The smallest model in DeepSeek's new architecture family, with native image understanding. It runs in thinking mode by default and also offers a non-thinking mode; DeepSeek reports it outperforms its earlier DeepSeek-V4-Pro flagship on benchmarks.

Modalities
text, image → text
In / out price30% off
List price $0.30 / $1.20$0.209351 / $0.837404per 1M tokens
Context
1Mtokens
Released
2026-09-10
On this page

Pricing

Prices in US dollars, charged from your prepaid balance as you go. No subscription.

30% off30% below the list price, on every token price.

Input
List price $0.30$0.209351/ 1M tokens
Output
List price $1.20$0.837404/ 1M tokens
Cache read
List price $0.006$0.004187/ 1M tokens
Cache write
$0/ 1M tokens

Specs

Limits and capabilities as published by the model’s provider.

Context
1Mtokens
Max output
384Ktokens
Input types
text, image
Output types
text
Released
2026-09-10
Open weights
Hugging Face
License
MIT
Tokens, last 7 days
82Mtokens

Call this model

The examples read your key from the CHEAPAIMODEL_API_KEY environment variable.

curl https://api.cheapaimodel.ai/v1/chat/completions \
  -H "Authorization: Bearer $CHEAPAIMODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-1-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Endpoints

Endpoints that accept this model, each with its API reference.

  • POST /v1/chat/completionsChat Completions · OpenAI compatible
    API reference
  • POST /v1/responsesResponses · OpenAI compatible
    API reference

Compare with other models

DeepSeek-V4.1-Flash side by side with each other model in the catalog: price, context and the same code.

From the blog

Posts on our blog that cover DeepSeek-V4.1-Flash: pricing, setup and troubleshooting.

All posts