Fireworks AI • US-Hosted High-Speed Reasoning

DeepSeek R1 Fast (Fireworks AI) API Pricing & Cost Calculator

Best suited for: US/EU compliance enterprises needing DeepSeek R1 reasoning at 3x speed. Standard input costs $3.000 per 1M tokens ($1.500 with prompt caching) and output costs $8.00 per 1M tokens.

Deploy DeepSeek R1 Fast (Fireworks AI) on Fireworks AI →
Standard Input / 1M
$3.000
Cached Input / 1M
$1.500
Output Tokens / 1M
$8.00
Context Window
160,000 tok
Throughput Speed
150 tok/s
Est. 5k Req/Day Spend
$1323.75/mo

Token Volume Cost Conversion Table (DeepSeek R1 Fast (Fireworks AI))

Token Volume Approx. English Words Un-cached Input Cost Cached Input Cost Output Generation Cost
10,000 tokens~7,500 words$0.0300$0.0150$0.0800
100,000 tokens~75,000 words$0.3000$0.1500$0.8000
1,000,000 tokens~750,000 words$3.0000$1.5000$8.0000
10,000,000 tokens~7,500,000 words$30.0000$15.0000$80.0000
100,000,000 tokens~75,000,000 words$300.0000$150.0000$800.0000

Compare DeepSeek R1 Fast (Fireworks AI) Against Other Frontier APIs

DeepSeek R1 Fast (Fireworks AI) vs GPT-4oCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs GPT-4o miniCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs OpenAI o3-miniCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Claude 3.7 SonnetCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Claude 3.5 HaikuCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Gemini 2.5 ProCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Gemini 2.5 FlashCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Gemini 2.0 Flash-LiteCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs DeepSeek-V3 (Chat)Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs DeepSeek-R1 (Reasoner)Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Llama 3.3 70B Versatile (Groq)Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Llama 3.1 8B Instant (Groq)Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Qwen 2.5 Coder 32B (Together AI)Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Mistral Large 2Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Mistral Small 3Compare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Perplexity Sonar ProCompare pricing, caching & speed DeepSeek R1 Fast (Fireworks AI) vs Cohere Command R+Compare pricing, caching & speed