DeepSeek V4p1 Flash 1017 Ultrafast API Pricing

By DeepSeek · 1 providerfireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafastCompare

Input / output: $2.40 / $9.60 per 1M tokens
Cache read: $0.048 / 1M
Context: 1M tokens
Max output: 384K tokens
Added: Nov 4, 2026

As of November 7, 2026, DeepSeek V4p1 Flash 1017 Ultrafast costs $2.40 per 1M input tokens and $9.60 per 1M output tokens on Fireworks AI, with cache reads at $0.048 per 1M tokens. It has a 1,048,576-token context window and returns up to 393,216 tokens per response.

Prices updated November 4, 2026Checked November 7, 2026

DeepSeek V4p1 Flash 1017 Ultrafast pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

DeepSeek V4p1 Flash 1017 Ultrafast prices by provider in US dollars, token prices per 1M tokens, as of November 7, 2026. Source: LiteLLM model price file.
Provider	Model name in LiteLLM	Input	Output	Cache read	Context
Fireworks AI	`fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast`	$2.40	$9.60	$0.048	1M

What DeepSeek V4p1 Flash 1017 Ultrafast costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Fireworks AI

$9.60

100 long-document requests with 100,000 input and 2,000 output tokens each

Fireworks AI

$25.92

DeepSeek V4p1 Flash 1017 Ultrafast cost calculator

At Fireworks AI's price ($2.40 input, $9.60 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $72.00 a day, about $2,160 a month. Change the numbers for your workload, or compare it with other models.

Input tokens per requestOutput tokens per requestRequests per day

Per request: $0.0072
Per day: $72.00
Per month (30 days): $2,160

DeepSeek V4p1 Flash 1017 Ultrafast features

Input: text, image. Output: text.

Function calling
Structured output
Image input
Reasoning
Prompt caching

Use DeepSeek V4p1 Flash 1017 Ultrafast with LiteLLM

Call DeepSeek V4p1 Flash 1017 Ultrafast through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK

from litellm import completion

response = completion(
    model="fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast",
    messages=[{"role": "user", "content": "Hello!"}],
)

Proxy config.yaml

model_list:
  - model_name: deepseek-v4p1-flash-1017-ultrafast
    litellm_params:
      model: fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast
      api_key: os.environ/FIREWORKS_AI_API_KEY

Call the proxy

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "deepseek-v4p1-flash-1017-ultrafast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek V4p1 Flash 1017 Ultrafast FAQ

How much does DeepSeek V4p1 Flash 1017 Ultrafast cost?

DeepSeek V4p1 Flash 1017 Ultrafast costs $2.40 per 1M input tokens and $9.60 per 1M output tokens on Fireworks AI, with cache reads at $0.048 per 1M tokens.

What is the context window of DeepSeek V4p1 Flash 1017 Ultrafast?

DeepSeek V4p1 Flash 1017 Ultrafast has a 1,048,576-token context window and returns up to 393,216 tokens per response.

Which providers offer DeepSeek V4p1 Flash 1017 Ultrafast?

DeepSeek V4p1 Flash 1017 Ultrafast is available from Fireworks AI through LiteLLM, using the model name fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast.

How do I call DeepSeek V4p1 Flash 1017 Ultrafast with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does DeepSeek V4p1 Flash 1017 Ultrafast support?

DeepSeek V4p1 Flash 1017 Ultrafast supports function calling, structured output, image input, reasoning and prompt caching.

When did LiteLLM add DeepSeek V4p1 Flash 1017 Ultrafast?

DeepSeek V4p1 Flash 1017 Ultrafast was added to LiteLLM's model price file on November 4, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:

docs.fireworks.ai/serverless/pricing.md

LiteLLM docs: Fireworks AI.

Provider pages: Fireworks AI.