Tier: reasoning
Context: 64K
Cheapest Host: DeepInfra (Serverless)
Deprecation Alert: 2026-07-24
DeepSeek R1 (671B Reasoning) API Pricing Calculator & Cheapest Provider
Live unit economics and multi-provider host arbitrage for DeepSeek R1 (671B Reasoning) (deepseek/deepseek-r1).
Input tokens cost $0.50/1M, output tokens cost
$2.15/1M, and prompt cache reads drop to
$0.14/1M.
Input / Output / Cache Read
$0.50 / $2.15
Per 1M tokens · Cache Read: $0.14/1M
10,000 DAU Monthly Bill
$12,492/mo
Drops to $9,090/mo at 75% prompt cache hit rate
Speed & Context Spec
128 tok/s
Context: 64,000 · Max Out: 16,000
1. Multi-Provider Host Arbitrage Table for DeepSeek R1 (671B Reasoning)
Compare every verified inference provider hosting DeepSeek R1 (671B Reasoning) by input price, output price, cache read discount, and throughput speed:
| Provider / Endpoint | Input / 1M | Output / 1M | Cache Read / 1M | Throughput | 10K DAU Monthly Bill | Action |
|---|---|---|---|---|---|---|
| DeepInfra (Serverless) Lowest Price | $0.50 | $2.15 | $0.14 | 76 tok/s | $12,492/mo | Deploy (Get $50 Free API Credits) → |
| Fireworks AI (Fast R1) | $0.55 | $2.19 | $0.28 | 128 tok/s | $13,237/mo | Deploy ($50 Free FireAttention Credits) → |
| Together AI | $0.55 | $2.19 | $0.28 | 88 tok/s | $13,237/mo | Deploy ($25 Free Inference Credits) → |
| DeepSeek Official (75% Off-Peak) | $0.55 | $2.19 | $0.14 | 52 tok/s | $13,237/mo | Deploy (US-Hosted Zero-Logging via DeepInfra) → |
2. Monthly SaaS Spend by DAU Scale & Prompt Cache Hit Rate
Exact monthly spend projections across 1,000 DAU, 10,000 DAU, and 50,000 DAU with 0%, 50%, 75%, and 90% prompt caching:
| Active Users (DAU) | Uncached (0% Hit) | 50% Cache Hit | 75% Cache Hit (RAG) | 90% Cache Hit (Agents) |
|---|---|---|---|---|
| 1,000 DAU (1.55B tok/mo) | $1,249/mo | $1,022/mo | $909.00/mo | $840.96/mo |
| 10,000 DAU (15.5B tok/mo) | $12,492/mo | $10,224/mo | $9,090/mo | $8,410/mo |
| 50,000 DAU (77.4B tok/mo) | $62,460/mo | $51,120/mo | $45,450/mo | $42,048/mo |
3. Frequently Asked Questions (DeepSeek R1 (671B Reasoning))
How much does the DeepSeek R1 (671B Reasoning) API cost per 1M tokens?
DeepSeek R1 (671B Reasoning) (DeepInfra) costs $0.50 per 1M input tokens, $2.15 per 1M output tokens, and $0.14 per 1M cached input tokens. Its context window is 64K (64,000 tokens) with 16,000 max output tokens.
What is the cheapest inference provider for DeepSeek R1 (671B Reasoning)?
Among 4 verified endpoints, DeepInfra (Serverless) offers the lowest blended pricing at $0.50/1M input and $2.15/1M output (76 tok/s). For maximum throughput, Fireworks AI (Fast R1) delivers 128 tokens/sec.
How much does DeepSeek R1 (671B Reasoning) cost per month at 1,000, 10,000, and 50,000 DAU?
On a standard SaaS production workload (12 requests/user/day, 3,500 input + 800 output tokens), DeepSeek R1 (671B Reasoning) costs $1,249/month at 1,000 DAU, $12,492/month at 10,000 DAU, and $62,460/month at 50,000 DAU. Enabling 75% prompt caching reduces the 10,000 DAU bill to $9,090/month.
4. Compare DeepSeek R1 (671B Reasoning) Against Alternative Models
DeepSeek R1 (671B Reasoning) vs OpenAI o3-mini
Side-by-side DAU cost & cache savings →
DeepSeek R1 (671B Reasoning) vs OpenAI o1 (Frontier Reasoning)
Side-by-side DAU cost & cache savings →
DeepSeek R1 (671B Reasoning) vs Claude 3.7 Sonnet (Extended Thinking)
Side-by-side DAU cost & cache savings →
DeepSeek R1 (671B Reasoning) vs Qwen QwQ-32B (Reasoning)
Side-by-side DAU cost & cache savings →
Perplexity Sonar Reasoning Pro vs DeepSeek R1 (671B Reasoning)
Side-by-side DAU cost & cache savings →
DeepSeek V3 (0324) Pricing Calculator
$0.24/1M in · $0.79/1M out →
Claude 3.7 Sonnet Pricing Calculator
$3.00/1M in · $15.00/1M out →
GPT-4o Pricing Calculator
$2.50/1M in · $10.00/1M out →
Gemini 2.5 Pro Pricing Calculator
$1.25/1M in · $10.00/1M out →
OpenAI o3-mini Pricing Calculator
$1.10/1M in · $4.40/1M out →
GPT-4.1 (1M Context Frontier) Pricing Calculator
$2.00/1M in · $8.00/1M out →