{T}
TokenMath.net
Verified against DeepSeek Official API Pricing
DeepSeekreasoningGenerally AvailableActive Production

DeepSeek-V4.1-Reasoner Token Counter & Cost Calculator

Deep-thinking reasoning tier with 98% prefix-cache discount and 50% diurnal off-peak pricing

Standard Input / 1M
$0.28
Prompt tokens
Cached Input / 1M
$0.028
Prompt caching rate
Output / 1M
$0.42
Generation completion
Context Window
256k
Max out: 384k
API & Developer Integration Details
generally available
API Model Stringdeepseek-reasoner
Provider & FamilyDeepSeek (deepseek)
Prompt Caching Rules64 min tokens (98% off)
Long-Context TiersStandard flat rate throughout full window
First-party audit timestamp: 2026-09-23 04:43 UTCOfficial Documentation

Interactive Cost & Token Simulator for DeepSeek-V4.1-Reasoner

Live Calculation
Input Tokens2,500
Output Tokens800
Requests / Day5,000
Prompt Caching Ratio (50%)$0.028/M cached rate
Cost / Request$0.00072
Daily Spend (5,000 reqs)$3.605
Monthly Run-Rate (30d)$108.15

Standard Workload Cost Scenarios

ScenarioInput TokensOutput TokensUncached CostWith Prompt Caching
Short Chat Query1,000500$0.00049$0.00024
Document Summarization10,0002,000$0.00364$0.00112
Codebase & Context Analysis100,00020,000$0.0364$0.0112
Batch Corpus Processing1,000,000100,000$0.3220$0.0700
Technical Architecture & Pricing VerificationVerified: 2026-09-23 04:43 UTC
Model ArchitectureDeepSeek-V4.1-Reasoner
Provider OrganizationDeepSeek
Tokenizer EncodingDeepSeek Byte-Level BPE (102k vocabulary)
API ConnectivityOpenAI-compatible REST API (/v1/chat/completions) with disk-backed KV cache.
Batch API 50% DiscountSupported (50% off input & output)
0
Tier 1 Rate Quota (Free-Tier Reference)200 RPM · 2M TPM

Tier 1 (free tier) reference limits — your account's actual quota may be higher.

Blended 3:1 Cost / 1M Tokens$0.32
DeepSeek reasoning tier with tiered peak/off-peak schedule. Off-peak (50% off): $0.25 in / $0.005 cache hit / $1.25 out. Prefix caching at 64-token granularity with up to a 98% read discount.DeepSeek Official API Pricing

Verified Pricing History

2026-09-23 04:43 UTC: $/M input · $/M output
September 2026: $0.5/M input · $2.5/M output ($0.01/M cached)
DeepSeek-V4.1-Reasoner launch with 98% prefix-cache discount.

When to Choose DeepSeek-V4.1-Reasoner

Ideal for production workloads demanding reasoning capabilities, deep context depth (256k tokens), and reliability from DeepSeek. Excellent when predictable tokenomics and prompt caching support are paramount.

When Another Model May Be Better

If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.

Frequently Asked Questions About DeepSeek-V4.1-Reasoner

How much does 1 million tokens cost with DeepSeek-V4.1-Reasoner?

For DeepSeek-V4.1-Reasoner, 1 million input tokens costs $0.28, while 1 million output tokens costs $0.42. If using prompt caching, repetitive input prefixes are discounted to $0.028 per million.

What is the context window for DeepSeek-V4.1-Reasoner?

DeepSeek-V4.1-Reasoner features a maximum context window of 262,144 tokens (~196,608 words), with a maximum output limit of 384,000 tokens per completion.

Which tokenizer does DeepSeek-V4.1-Reasoner use?

DeepSeek-V4.1-Reasoner utilizes the DeepSeek Byte-Level BPE (102k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.

Does DeepSeek-V4.1-Reasoner support prompt caching discounts?

Yes. DeepSeek-V4.1-Reasoner supports prompt caching with a cached input rate of $0.028/1M (saving up to 90% on repeated input context).