DeepSeek V4.1 Flash Fast Fp4
deepseek-v4.1-flash-fast-fp4Pricing
List prices at CoralBricks, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.01 | $1.20 | |
| Cached input 100% off input | $0.00 | 100% off input | |
| Cache write, 5 minutes | $0.09 |
What it costs a month
At CoralBricks list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$92.10
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$45.60
- Coding agent1,000 requests a day, 40K in / 2K out, cached$75.60
- Overnight batch20,000 requests a day, 4K in / 0.4K out$312
Where to run it
1 host serve DeepSeek V4.1 Flash Fast Fp4. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
CoralBricksCloud deepseek-v4.1-flash-fast-fp4 | $0.01 / $1.20 | deepseek-v4.1-flash-fast-fp4 |
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
No host sells it for less than CoralBricks.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 35% less
- 35% less
- 15% less
Open-weight picks
- 18% less
- 42% less
- 54% less
- 54% less
Call it
Using CoralBricks's API.
from litellm import completion
response = completion(
model="coralbricks/deepseek-v4.1-flash-fast-fp4",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4.1 Flash Fast Fp4 cost?
On CoralBricks, DeepSeek V4.1 Flash Fast Fp4 costs $0.01 per million input tokens and $1.20 per million output tokens.
Which APIs offer DeepSeek V4.1 Flash Fast Fp4?
DeepSeek V4.1 Flash Fast Fp4 runs on 1 API: CoralBricks.
What is DeepSeek V4.1 Flash Fast Fp4's context window?
1M tokens, with up to 1M tokens in one reply.
Is DeepSeek V4.1 Flash Fast Fp4 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4.1 Flash Fast Fp4?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (35% less), GPT-6 Luna on OpenAI (35% less) and Qwen3.8 27B on EmpirioLabs AI (18% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4.1 Flash Fast Fp4's API model id?
Use deepseek-v4.1-flash-fast-fp4 with CoralBricks.
Sources
Raw catalog entry for deepseek-v4.1-flash-fast-fp4 on CoralBricks
{
"cache_creation_input_token_cost": 9e-8,
"cache_read_input_token_cost": 0,
"input_cost_per_token": 1e-8,
"litellm_provider": "coralbricks",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 0.0000012,
"source": "https://www.coralbricks.ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses",
"/v1/messages"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
}