DeepSeek V4.1 Flash Fast
DeepSeek-V4.1-Flash-FastPricing
List prices at Baseten, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.60 | $2.40 | |
| Cached input 98% off input | $0.014 | 98% off input |
What it costs a month
At Baseten list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$307
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$234
- Coding agent1,000 requests a day, 40K in / 2K out, cached$372
- Overnight batch20,000 requests a day, 4K in / 0.4K out$2,016
Where to run it
4 hosts serve DeepSeek V4.1 Flash Fast. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
RefuselessCloud deepseek-v4.1-flash-fast | $0.05 / $0.15 −93% vs headline | deepseek-v4.1-flash-fast | |
CoralBricksCloud deepseek-v4.1-flash-fast | $0.01 / $1.20 −71% vs headline | deepseek-v4.1-flash-fast | |
WallyCloud deepseek-v4.1-flash-fast | $0.60 / $2.40 | deepseek-v4.1-flash-fast | |
BasetenInference DeepSeek-V4.1-Flash-Fast | $0.60 / $2.40 | DeepSeek-V4.1-Flash-Fast |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Baseten | |||||||
| 1017 DeepSeek-V4.1-Flash-1017-Fast | $0.60 / $2.40 | DeepSeek-V4.1-Flash-1017-Fast | |||||
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)Runtimes: 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
- Refuseless93% lessdeepseek-v4.1-flash-fast$0.05 / $0.15
- CoralBricks71% lessdeepseek-v4.1-flash-fast$0.01 / $1.20
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 19% less
- 56% less
- 81% less
- 81% less
Open-weight picks
- 35% less
- 39% less
- 50% less
- 54% less
Call it
Using Baseten's API.
from litellm import completion
response = completion(
model="baseten/DeepSeek-V4.1-Flash-Fast",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4.1 Flash Fast cost?
On Baseten, DeepSeek V4.1 Flash Fast costs $0.60 per million input tokens and $2.40 per million output tokens. Cached input costs $0.014 per million tokens. The cheapest host is Refuseless, at $0.05 per million input tokens and $0.15 per million output tokens.
Which APIs offer DeepSeek V4.1 Flash Fast?
DeepSeek V4.1 Flash Fast runs on 4 APIs: Refuseless, CoralBricks, Wally and Baseten.
What is DeepSeek V4.1 Flash Fast's context window?
1M tokens, with up to 131K tokens in one reply.
Is DeepSeek V4.1 Flash Fast being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4.1 Flash Fast?
Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (19% less), GPT-5.4 Nano on OpenAI (56% less) and Kimi K2.7 Code on CLF AI Gateway (35% less). DeepSeek V4.1 Flash Fast itself costs 93% less on Refuseless. Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4.1 Flash Fast's API model id?
Use DeepSeek-V4.1-Flash-Fast with Baseten. Other hosts use their own ids: deepseek-v4.1-flash-fast on Refuseless, deepseek-v4.1-flash-fast on CoralBricks, deepseek-v4.1-flash-fast on Wally.
Sources
Raw catalog entry for DeepSeek-V4.1-Flash-Fast on Baseten
{
"cache_read_input_token_cost": 1.4e-8,
"input_cost_per_token": 6e-7,
"litellm_provider": "baseten",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0000024,
"source": "https://inference.baseten.co/v1/models",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}