Submit
DeepSeekOpen-weight·1000K context·552B params·MIT

DeepSeek V4.1 Flashdeepseek/deepseek-v4-1-flash

DeepSeek V4.1 Flash is an open-weight vision-language model with a 552B-parameter backbone. Its asymmetric architecture activates 8B parameters for input encoding and 16B for output generation. It supports image understanding, coding and tool-based reasoning.

Cheapest blended:$0.53 / 1M tokenson DeepSeek · 1 provider listed

Availability and billing notes

Reviewed September 21, 2026 · check the linked provider documentation for later changes.

Use API model ID deepseek-flash. The retired deepseek-v4-flash and deepseek-v4-flash-vision-exp names temporarily route to V4.1 Flash.

Peak input/cache/output: $0.30 / $0.006 / $1.20 per million tokens. Off-peak: $0.15 / $0.003 / $0.60. USD peak-hour rates. Off-peak rates are 50% lower. Peak: weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays.

Official source 1 →Official source 2 →Official source 3 →

Pricing across providers

Sort by:
ProviderInput /1MOutput /1MBlended /1MLatency p50FormatFreshnessAction
DeepSeek
deepseek-flash

USD peak-hour rates. Off-peak rates are 50% lower. Peak: weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays.

$0.3
Cached $0.006
$1.2$0.525—OpenAI-compatiblePrice 1mo agoTry →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

  • reasoning
  • code
  • vision
  • tool_calling

Code samples

Example using DeepSeek — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.deepseek.com",
)

response = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context
1000K
Max output
384K
Parameters
552B
Release
2026-09-10
Training cutoff
—
License
MIT
Hugging Face →Official documentation →

Similar models

Compare with

  • DeepSeek V4.1 Flash vs GLM 5.3 Flash
    Comparison planned — not yet published
  • DeepSeek V4.1 Flash vs Qwen3.5 397B A17B
    Comparison planned — not yet published
  • DeepSeek V4.1 Flash vs GLM 5.3 FlashX
    Comparison planned — not yet published

Frequently asked

How much does DeepSeek V4.1 Flash cost?+
The cheapest public hosting is $0.53 per 1M blended tokens on DeepSeek. 1 total providers are listed above with per-input / per-output / cached pricing.
How do I access DeepSeek V4.1 Flash from outside China?+
Availability, account verification and payment methods vary by provider and region. Check the official documentation and the selected provider's access requirements before integrating. A directory listing does not guarantee global API access.
Is DeepSeek V4.1 Flash open-source? Can I fine-tune it?+
DeepSeek V4.1 Flash has published weights. License: MIT. Review the linked repository and license for deployment, fine-tuning and commercial-use conditions.
Is DeepSeek V4.1 Flash OpenAI-compatible?+
At least one listed hosting exposes an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.
What's the maximum context window for DeepSeek V4.1 Flash?+
The model supports up to 1,000,000 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.