DeepSeek V4.1 Flash 260910
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
deepseek-v4.1-flash-260910Released 10 Sep 2026 (Sep 2026)Pricing
List prices at StreamLake, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $1.20 | |
| Cached input 98% off input | $0.006 | 98% off input |
What it costs a month
At StreamLake list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$154
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$117
- Coding agent1,000 requests a day, 40K in / 2K out, cached$185
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Where to run it
1 host serve DeepSeek V4.1 Flash 260910. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
StreamLakeCloud deepseek-v4.1-flash-260910 | $0.30 / $1.20 | deepseek-v4.1-flash-260910 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: DeepSeek License (MIT code)Runs in about 1831.7 GB of GPU memoryRuntimes: SGLang, TGI, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than StreamLake.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 12% less
- 62% less
- 62% less
- 50% less
Open-weight picks
- 8% less
- 17% less
- 25% less
- 33% less
Call it
Using StreamLake's API.
from litellm import completion
response = completion(
model="streamlake/deepseek-v4.1-flash-260910",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4.1 Flash 260910 cost?
On StreamLake, DeepSeek V4.1 Flash 260910 costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input costs $0.006 per million tokens.
Which APIs offer DeepSeek V4.1 Flash 260910?
DeepSeek V4.1 Flash 260910 runs on 1 API: StreamLake.
What is DeepSeek V4.1 Flash 260910's context window?
1M tokens, with up to 384K tokens in one reply.
Is DeepSeek V4.1 Flash 260910 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4.1 Flash 260910?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (12% less), Claude Haiku 5.5 on Anthropic (62% less) and Qwen3.7 Plus on Replicate (8% less). Savings are on a mix of 3 input tokens to 1 output token.
When was DeepSeek V4.1 Flash 260910 released?
DeepSeek released it on 10 Sep 2026.
What is DeepSeek V4.1 Flash 260910's API model id?
Use deepseek-v4.1-flash-260910 with StreamLake.
Sources
Raw catalog entry for deepseek-v4.1-flash-260910 on StreamLake
{
"cache_read_input_token_cost": 6e-9,
"input_cost_per_token": 3e-7,
"litellm_provider": "streamlake",
"max_input_tokens": 1048568,
"max_output_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 0.0000012,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": true,
"supports_prompt_caching": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
}