DeepSeek V4.1 Flash Ultrafast
deepseek-v4p1-flash-1017-ultrafastPricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.40 | $9.60 | |
| Cached input 98% off input | $0.048 | 98% off input |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,228
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$933
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,480
- Overnight batch20,000 requests a day, 4K in / 0.4K out$8,064
Where to run it
1 host serve DeepSeek V4.1 Flash Ultrafast. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
| $2.40 / $9.60 | deepseek-v4p1-flash-1017-ultrafast |
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 Fireworks AI.
Smaller DeepSeek models
No cheaper DeepSeek model keeps its key capabilities.
Other frontier labs
- 5% less
- 5% less
- 5% less
- 29% less
Open-weight picks
- 5% less
- 46% less
- 59% less
- 88% less
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/deepseek-v4p1-flash-1017-ultrafast",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does DeepSeek V4.1 Flash Ultrafast cost?
On Fireworks AI, DeepSeek V4.1 Flash Ultrafast costs $2.40 per million input tokens and $9.60 per million output tokens. Cached input costs $0.048 per million tokens.
Which APIs offer DeepSeek V4.1 Flash Ultrafast?
DeepSeek V4.1 Flash Ultrafast runs on 1 API: Fireworks AI.
What is DeepSeek V4.1 Flash Ultrafast's context window?
1M tokens, with up to 393K tokens in one reply.
Is DeepSeek V4.1 Flash Ultrafast being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to DeepSeek V4.1 Flash Ultrafast?
Models that cost less and keep most of what it can do: GPT-6.2 Sol on OpenAI (5% less), Gemini 4 Carbon on Google AI Studio (5% less) and Kimi K3.1 Pro on Databricks (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is DeepSeek V4.1 Flash Ultrafast's API model id?
Use deepseek-v4p1-flash-1017-ultrafast with Fireworks AI.
Sources
Raw catalog entry for deepseek-v4p1-flash-1017-ultrafast on Fireworks AI
{
"cache_read_input_token_cost": 4.8e-8,
"input_cost_per_token": 0.0000024,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 0.0000096,
"source": "https://docs.fireworks.ai/serverless/pricing.md",
"supports_function_calling": true,
"supports_mid_conversation_system": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
}