o4-mini vs DeepSeek-R1: Low-Cost Reasoning Comparison

o4-mini vs deepseek-r1
Complete Comparison: 50,000 input tokens × 15,000 output tokens
Comparison Mode
⚡ 75% Cached

Complete comparison of pricing, performance, and capabilities for 2 leading AI models with 75% Cached.

⚡ Caching Optimized (up to 98% savings)
Comparison Criteria o4-mini
OpenAI
deepseek-r1
DeepSeek
Calculation Results (Current Inputs) (75% cached)
Input Tokens 50,000 50,000
Output Tokens 15,000 15,000
Cost Breakdown
Input Cost $0.055000 (rounded ~ $0.06)Worst $0.027500 (rounded ~ $0.03)Best
Output Cost $0.066000 (rounded ~ $0.07)Worst $0.032850 (rounded ~ $0.03)Best
Unit Cost (Audio/OCR) $0.000000 $0.000000
Service Fees $0.000000 $0.000000
Total Cost $0.083875 (rounded ~ $0.08) Most Expensive $0.040138 Best Value
Processing Time 6 minutes, 4.90 seconds Fastest 9 minutes, 7.26 seconds Slowest
Tokens per Second 180Fastest 120Slowest
Time to First Token 280ms Worst 220ms Best
Cost per 1K tokens $0.001290Worst $0.000618Best
Tokens per Dollar 774,963Worst Value 1,619,433Best Value
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base) $1.100000Worst $0.550000Best
Output Cost / 1M (Base) $4.400000Worst $2.190000Best
Input Cost / 1M (Optimized) $1.100000Worst
Optimizations: No optimizations applied
$0.550000Best
Optimizations: No optimizations applied
Output Cost / 1M (Optimized) $4.400000Worst
Optimizations: No optimizations applied
$2.190000Best
Optimizations: No optimizations applied
Capabilities & Advanced Features
Images Support ✓ Supported ✗ Not Supported
Caching Support
75
✓ Supported ✓ Supported
Batch API Support ✓ Supported ✓ Supported
Tool Usage Support ✓ Supported ✗ Not Supported
Scroll horizontally to see all data

🔄 Compare Different AI Models

1

First Model

2

Second Model

Select providers and models above, then click "Compare Models" to update the comparison.
All other parameters will be preserved from the current comparison.

Click Recalculate to update after making changes

Select AI Model

o4-mini
OpenAIMax Context: 200,000 tokens
$1.1 / $4.4 per 1M tokens
▼
▼
Use Batch API (50% discount)
75%
Provider-specific multipliers applied after all calculations
Enable for cache discounts
Select platform to enforce context limits
Number of requests (max 1M). Summary view auto-enabled >10k.

Calculate Token Costs

$0.083875 Total Cost
$0.013750 Input Cost
$0.066000 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
65,000Total Tokens
$0.001290Cost per 1K
774,963Tokens per $
📊 Advanced Cost Breakdown

Processing Speed

6m 4s Processing Time
180 Tokens/Second
280ms Time to First Token
178 Effective Speed

Model Comparison

Select a model to see comparisons with competitors.

Model Information

Select a model to see detailed information.

🔄 Advanced Options

⚡ Optimization
Flat fee per session (e.g., $0.03 for Code Interpreter)
Hourly storage fee for cached data
First 50 hours free, $0.05/hour after
🧠 Reasoning & Thinking
Manual thinking tokens (billed at output rate)
🔧 Special Modes
Enable 6.0x Fast Mode multiplier
📚 Research & Citations
Enable $1.00/$4.00 rates + $10.00/1k search
Enable research tier pricing
Fee per source cited
🎤 Realtime Audio & Video
Session length for billing
📊 Multiple Models Detected: This page contains data for 2 models. See the detailed comparison table above, and switch between models using tabs below.

o4-mini OpenAI

$0.083875 (rounded ~ $0.08)
Total Cost
⚡ 75% Cached 🔧 Tools
👁️
Vision/Images
✓ Available
🎧
Audio Processing
✗ Not Available
🎥
Video Analysis
✗ Not Available
🔧
Tool Usage
✓ Available
📄
OCR Support
✗ Not Available
📊
Batch API
✓ Available
⚡
Caching
✓ Available
90% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.121000 (rounded ~ $0.12) Input: $0.055000 (rounded ~ $0.06)
Output: $0.066000 (rounded ~ $0.07)
Optimized Cost $0.083875 (rounded ~ $0.08) Input: $0.055000 (rounded ~ $0.06)
Output: $0.066000 (rounded ~ $0.07)
Unit: $0.000000
Fees: $0.000000
Total Savings $0.037125 (rounded ~ $0.04) 30.7% discount

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 15,000 output tokens:

  • Input Cost: $0.055000 (rounded ~ $0.06)
  • Output Cost: $0.066000 (rounded ~ $0.07)
  • Total Cost: $0.083875 (rounded ~ $0.08)
  • Cost per 1K tokens: $0.001290
  • Tokens per dollar: 774,963 tokens
  • Context Window: 200000 tokens

Speed & Performance Analysis

With a processing speed of 180 tokens per second and 280ms time to first token:

  • Processing Time: 6 minutes, 4.90 seconds
  • Latency: 280 milliseconds to first token
  • Base Throughput: 180 tokens/second
  • Effective Throughput: 178 tokens/second (temperature-adjusted)

Best Use Cases

CodingMathLogical Troubleshooting

Want this applied to YOUR actual stack?

This calculator shows the math for o4-mini. Your decision needs more — current infrastructure, compliance requirements, actual workload patterns, volume tiers — that change which model is right for you.

Get a $39 personalized AI Architecture Audit. PDF tailored to your stack, delivered in under 60 seconds. 7-day no-questions-asked refund.

Get my instant AI audit — $39 →

deepseek-r1 DeepSeek

$0.040138
Total Cost
⚠️ This model is now in Legacy mode. Results are based on last-known pricing.
⚡ 75% Cached 🔧 Tools
👁️
Vision/Images
✗ Not Available
🎧
Audio Processing
✗ Not Available
🎥
Video Analysis
✗ Not Available
🔧
Tool Usage
✗ Not Available requested
📄
OCR Support
✗ Not Available
📊
Batch API
✓ Available
⚡
Caching
✓ Available
98% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.060350 Input: $0.027500 (rounded ~ $0.03)
Output: $0.032850 (rounded ~ $0.03)
Optimized Cost $0.040138 Input: $0.027500 (rounded ~ $0.03)
Output: $0.032850 (rounded ~ $0.03)
Unit: $0.000000
Fees: $0.000000
Total Savings $0.020213 33.5% discount

Detailed Cost Analysis (from Plugin)

For 50,000 input tokens and 15,000 output tokens:

  • Input Cost: $0.027500 (rounded ~ $0.03)
  • Output Cost: $0.032850 (rounded ~ $0.03)
  • Total Cost: $0.040138
  • Cost per 1K tokens: $0.000618
  • Tokens per dollar: 1,619,433 tokens
  • Context Window: 163840 tokens

Speed & Performance Analysis

With a processing speed of 120 tokens per second and 220ms time to first token:

  • Processing Time: 9 minutes, 7.26 seconds
  • Latency: 220 milliseconds to first token
  • Base Throughput: 120 tokens/second
  • Effective Throughput: 119 tokens/second (temperature-adjusted)

Best Use Cases

CodingMathLogical Troubleshooting

Want this applied to YOUR actual stack?

This calculator shows the math for deepseek-r1. Your decision needs more — current infrastructure, compliance requirements, actual workload patterns, volume tiers — that change which model is right for you.

Get a $39 personalized AI Architecture Audit. PDF tailored to your stack, delivered in under 60 seconds. 7-day no-questions-asked refund.

Get my instant AI audit — $39 →

✨ Market Recommendations AI Model Registry

← Back to o4-mini
📋 Active Input Parameters
Input Tokens: 50,000
Output Tokens: 15,000
Cached Tokens: 75%
Tools: Enabled
Rank AI Model & Provider Total Cost vs o4-mini vs deepseek-r1
🏆 Mistral Small 3
Mistral AI
 $0.006125 (rounded ~ $0.01) Best Value ↓ 92.7% cheaper ↓ 84.7% cheaper
🥈 Grok Code Fast 1
xAI
 $0.025750 (rounded ~ $0.03) ↓ 69.3% cheaper ↓ 35.8% cheaper
🥉 Gemini 3.1 Flash Lite
Google
 $0.026563 (rounded ~ $0.03) ↓ 68.3% cheaper ↓ 33.8% cheaper
#4 Mistral Large 3
Mistral AI
 $0.030625 ↓ 63.5% cheaper ↓ 23.7% cheaper
#5 Gemini 3.5 Flash-Lite
Google
 $0.042375 (rounded ~ $0.04) ↓ 49.5% cheaper ↑ 5.6% more
#6 Gemini 2.5 Flash
Google
 $0.042375 (rounded ~ $0.04) ↓ 49.5% cheaper ↑ 5.6% more
#7 Grok Build 0.1
xAI
 $0.046250 (rounded ~ $0.05) ↓ 44.9% cheaper ↑ 15.2% more
#8 Gemini 3.1 Flash
Google
 $0.053125 (rounded ~ $0.05) ↓ 36.7% cheaper ↑ 32.4% more
#9 Kimi K2.5
Moonshot AI
 $0.056325 (rounded ~ $0.06) ↓ 32.8% cheaper ↑ 40.3% more
#10 Grok 4.3
xAI
 $0.057813 (rounded ~ $0.06) ↓ 31.1% cheaper ↑ 44% more
#11 Grok 4.20 Beta
xAI
 $0.057813 (rounded ~ $0.06) ↓ 31.1% cheaper ↑ 44% more
#12 Gemini 3.8 Flash
Google
 $0.068438 (rounded ~ $0.07) ↓ 18.4% cheaper ↑ 70.5% more
#13 o4-mini Deep Research
OpenAI
 $0.076250 (rounded ~ $0.08) ↓ 9.1% cheaper ↑ 90% more
#14 Kimi K2.6
Moonshot AI
 $0.077931 (rounded ~ $0.08) ↓ 7.1% cheaper ↑ 94.2% more
#15 Kimi K2.7 Code
Moonshot AI
 $0.077931 (rounded ~ $0.08) ↓ 7.1% cheaper ↑ 94.2% more
#16 GPT-5.4 mini
OpenAI
 $0.079688 ↓ 5% cheaper ↑ 98.5% more
#17 Claude Haiku 4.5
Anthropic
 $0.091250 (rounded ~ $0.09) ↑ 8.8% more ↑ 127.3% more
#18 GPT-5.6 Luna
OpenAI
 $0.106250 (rounded ~ $0.11) ↑ 26.7% more ↑ 164.7% more
#19 Grok 4.6
xAI
 $0.122500 (rounded ~ $0.12) ↑ 46.1% more ↑ 205.2% more
#20 Grok 4.5
xAI
 $0.122500 (rounded ~ $0.12) ↑ 46.1% more ↑ 205.2% more
#21 Gemini 3.6 Flash
Google
 $0.136875 (rounded ~ $0.14) ↑ 63.2% more ↑ 241% more
#22 Gemini 3.5 Flash
Google
 $0.159375 ↑ 90% more ↑ 297.1% more
#23 Gemini 2.5 Pro
Google
 $0.170313 ↑ 103.1% more ↑ 324.3% more
#24 Claude Sonnet 5
Anthropic
 $0.182500 (rounded ~ $0.18) ↑ 117.6% more ↑ 354.7% more
#25 Gemini 3.1 Pro
Google
 $0.212500 (rounded ~ $0.21) ↑ 153.4% more ↑ 429.4% more
#26 GPT-5.3 Codex Spark
OpenAI
 $0.238438 (rounded ~ $0.24) ↑ 184.3% more ↑ 494.1% more
#27 GPT-5.3 Instant
OpenAI
 $0.238438 (rounded ~ $0.24) ↑ 184.3% more ↑ 494.1% more
#28 GPT-5.4
OpenAI
 $0.265625 (rounded ~ $0.27) ↑ 216.7% more ↑ 561.8% more
#29 GPT-5.4 Thinking
OpenAI
 $0.265625 (rounded ~ $0.27) ↑ 216.7% more ↑ 561.8% more
#30 GPT-5.6 Terra
OpenAI
 $0.265625 (rounded ~ $0.27) ↑ 216.7% more ↑ 561.8% more
#31 Claude Sonnet 4.6
Anthropic
 $0.273750 (rounded ~ $0.27) ↑ 226.4% more ↑ 582% more
#32 Claude Opus 4.7
Anthropic
 $0.456250 (rounded ~ $0.46) ↑ 444% more ↑ 1036.7% more
#33 Claude Opus 5
Anthropic
 $0.456250 (rounded ~ $0.46) ↑ 444% more ↑ 1036.7% more
#34 Claude Opus 4.8
Anthropic
 $0.456250 (rounded ~ $0.46) ↑ 444% more ↑ 1036.7% more
#35 Claude Opus 4.6
Anthropic
 $0.456250 (rounded ~ $0.46) ↑ 444% more ↑ 1036.7% more
#36 GPT-5.5
OpenAI
 $0.531250 (rounded ~ $0.53) ↑ 533.4% more ↑ 1223.6% more
#37 GPT-5.5 Instant
OpenAI
 $0.531250 (rounded ~ $0.53) ↑ 533.4% more ↑ 1223.6% more
#38 GPT-5.6 Sol
OpenAI
 $0.531250 (rounded ~ $0.53) ↑ 533.4% more ↑ 1223.6% more
#39 o3 Deep Research
OpenAI
 $0.762500 (rounded ~ $0.76) ↑ 809.1% more ↑ 1799.7% more
#40 Claude Fable 5.1
Anthropic
 $0.884375 (rounded ~ $0.88) ↑ 954.4% more ↑ 2103.4% more
#41 Claude Mythos 5.1
Anthropic
 $0.884375 (rounded ~ $0.88) ↑ 954.4% more ↑ 2103.4% more
#42 Claude Fable 5
Anthropic
 $0.912500 (rounded ~ $0.91) ↑ 987.9% more ↑ 2173.4% more
#43 Claude Mythos 5
Anthropic
 $0.912500 (rounded ~ $0.91) ↑ 987.9% more ↑ 2173.4% more
#44 GPT-6 Astra
OpenAI
 $0.912500 (rounded ~ $0.91) ↑ 987.9% more ↑ 2173.4% more
#45 o3 Pro
OpenAI
 $1.525000 (rounded ~ $1.53) ↑ 1718.2% more ↑ 3699.4% more
#46 GPT-5.2 Pro
OpenAI
 $2.861250 (rounded ~ $2.86) ↑ 3311.3% more ↑ 7028.6% more
#47 GPT-5.2 Pro
OpenAI
 $2.861250 (rounded ~ $2.86) ↑ 3311.3% more ↑ 7028.6% more
🏆

Mistral Small 3
Mistral AI

$0.006125 (rounded ~ $0.01)
vs o4-mini: ↓ 92.7%
vs deepseek-r1: ↓ 84.7%
🥈

Grok Code Fast 1
xAI

$0.025750 (rounded ~ $0.03)
vs o4-mini: ↓ 69.3%
vs deepseek-r1: ↓ 35.8%
🥉

Gemini 3.1 Flash Lite
Google

$0.026563 (rounded ~ $0.03)
vs o4-mini: ↓ 68.3%
vs deepseek-r1: ↓ 33.8%
#4

Mistral Large 3
Mistral AI

$0.030625
vs o4-mini: ↓ 63.5%
vs deepseek-r1: ↓ 23.7%
#5

Gemini 3.5 Flash-Lite
Google

$0.042375 (rounded ~ $0.04)
vs o4-mini: ↓ 49.5%
vs deepseek-r1: ↑ 5.6%
#6

Gemini 2.5 Flash
Google

$0.042375 (rounded ~ $0.04)
vs o4-mini: ↓ 49.5%
vs deepseek-r1: ↑ 5.6%
#7

Grok Build 0.1
xAI

$0.046250 (rounded ~ $0.05)
vs o4-mini: ↓ 44.9%
vs deepseek-r1: ↑ 15.2%
#8

Gemini 3.1 Flash
Google

$0.053125 (rounded ~ $0.05)
vs o4-mini: ↓ 36.7%
vs deepseek-r1: ↑ 32.4%
#9

Kimi K2.5
Moonshot AI

$0.056325 (rounded ~ $0.06)
vs o4-mini: ↓ 32.8%
vs deepseek-r1: ↑ 40.3%
#10

Grok 4.3
xAI

$0.057813 (rounded ~ $0.06)
vs o4-mini: ↓ 31.1%
vs deepseek-r1: ↑ 44%
#11

Grok 4.20 Beta
xAI

$0.057813 (rounded ~ $0.06)
vs o4-mini: ↓ 31.1%
vs deepseek-r1: ↑ 44%
#12

Gemini 3.8 Flash
Google

$0.068438 (rounded ~ $0.07)
vs o4-mini: ↓ 18.4%
vs deepseek-r1: ↑ 70.5%
#13

o4-mini Deep Research
OpenAI

$0.076250 (rounded ~ $0.08)
vs o4-mini: ↓ 9.1%
vs deepseek-r1: ↑ 90%
#14

Kimi K2.6
Moonshot AI

$0.077931 (rounded ~ $0.08)
vs o4-mini: ↓ 7.1%
vs deepseek-r1: ↑ 94.2%
#15

Kimi K2.7 Code
Moonshot AI

$0.077931 (rounded ~ $0.08)
vs o4-mini: ↓ 7.1%
vs deepseek-r1: ↑ 94.2%
#16

GPT-5.4 mini
OpenAI

$0.079688
vs o4-mini: ↓ 5%
vs deepseek-r1: ↑ 98.5%
#17

Claude Haiku 4.5
Anthropic

$0.091250 (rounded ~ $0.09)
vs o4-mini: ↑ 8.8%
vs deepseek-r1: ↑ 127.3%
#18

GPT-5.6 Luna
OpenAI

$0.106250 (rounded ~ $0.11)
vs o4-mini: ↑ 26.7%
vs deepseek-r1: ↑ 164.7%
#19

Grok 4.6
xAI

$0.122500 (rounded ~ $0.12)
vs o4-mini: ↑ 46.1%
vs deepseek-r1: ↑ 205.2%
#20

Grok 4.5
xAI

$0.122500 (rounded ~ $0.12)
vs o4-mini: ↑ 46.1%
vs deepseek-r1: ↑ 205.2%
#21

Gemini 3.6 Flash
Google

$0.136875 (rounded ~ $0.14)
vs o4-mini: ↑ 63.2%
vs deepseek-r1: ↑ 241%
#22

Gemini 3.5 Flash
Google

$0.159375
vs o4-mini: ↑ 90%
vs deepseek-r1: ↑ 297.1%
#23

Gemini 2.5 Pro
Google

$0.170313
vs o4-mini: ↑ 103.1%
vs deepseek-r1: ↑ 324.3%
#24

Claude Sonnet 5
Anthropic

$0.182500 (rounded ~ $0.18)
vs o4-mini: ↑ 117.6%
vs deepseek-r1: ↑ 354.7%
#25

Gemini 3.1 Pro
Google

$0.212500 (rounded ~ $0.21)
vs o4-mini: ↑ 153.4%
vs deepseek-r1: ↑ 429.4%
#26

GPT-5.3 Codex Spark
OpenAI

$0.238438 (rounded ~ $0.24)
vs o4-mini: ↑ 184.3%
vs deepseek-r1: ↑ 494.1%
#27

GPT-5.3 Instant
OpenAI

$0.238438 (rounded ~ $0.24)
vs o4-mini: ↑ 184.3%
vs deepseek-r1: ↑ 494.1%
#28

GPT-5.4
OpenAI

$0.265625 (rounded ~ $0.27)
vs o4-mini: ↑ 216.7%
vs deepseek-r1: ↑ 561.8%
#29

GPT-5.4 Thinking
OpenAI

$0.265625 (rounded ~ $0.27)
vs o4-mini: ↑ 216.7%
vs deepseek-r1: ↑ 561.8%
#30

GPT-5.6 Terra
OpenAI

$0.265625 (rounded ~ $0.27)
vs o4-mini: ↑ 216.7%
vs deepseek-r1: ↑ 561.8%
#31

Claude Sonnet 4.6
Anthropic

$0.273750 (rounded ~ $0.27)
vs o4-mini: ↑ 226.4%
vs deepseek-r1: ↑ 582%
#32

Claude Opus 4.7
Anthropic

$0.456250 (rounded ~ $0.46)
vs o4-mini: ↑ 444%
vs deepseek-r1: ↑ 1036.7%
#33

Claude Opus 5
Anthropic

$0.456250 (rounded ~ $0.46)
vs o4-mini: ↑ 444%
vs deepseek-r1: ↑ 1036.7%
#34

Claude Opus 4.8
Anthropic

$0.456250 (rounded ~ $0.46)
vs o4-mini: ↑ 444%
vs deepseek-r1: ↑ 1036.7%
#35

Claude Opus 4.6
Anthropic

$0.456250 (rounded ~ $0.46)
vs o4-mini: ↑ 444%
vs deepseek-r1: ↑ 1036.7%
#36

GPT-5.5
OpenAI

$0.531250 (rounded ~ $0.53)
vs o4-mini: ↑ 533.4%
vs deepseek-r1: ↑ 1223.6%
#37

GPT-5.5 Instant
OpenAI

$0.531250 (rounded ~ $0.53)
vs o4-mini: ↑ 533.4%
vs deepseek-r1: ↑ 1223.6%
#38

GPT-5.6 Sol
OpenAI

$0.531250 (rounded ~ $0.53)
vs o4-mini: ↑ 533.4%
vs deepseek-r1: ↑ 1223.6%
#39

o3 Deep Research
OpenAI

$0.762500 (rounded ~ $0.76)
vs o4-mini: ↑ 809.1%
vs deepseek-r1: ↑ 1799.7%
#40

Claude Fable 5.1
Anthropic

$0.884375 (rounded ~ $0.88)
vs o4-mini: ↑ 954.4%
vs deepseek-r1: ↑ 2103.4%
#41

Claude Mythos 5.1
Anthropic

$0.884375 (rounded ~ $0.88)
vs o4-mini: ↑ 954.4%
vs deepseek-r1: ↑ 2103.4%
#42

Claude Fable 5
Anthropic

$0.912500 (rounded ~ $0.91)
vs o4-mini: ↑ 987.9%
vs deepseek-r1: ↑ 2173.4%
#43

Claude Mythos 5
Anthropic

$0.912500 (rounded ~ $0.91)
vs o4-mini: ↑ 987.9%
vs deepseek-r1: ↑ 2173.4%
#44

GPT-6 Astra
OpenAI

$0.912500 (rounded ~ $0.91)
vs o4-mini: ↑ 987.9%
vs deepseek-r1: ↑ 2173.4%
#45

o3 Pro
OpenAI

$1.525000 (rounded ~ $1.53)
vs o4-mini: ↑ 1718.2%
vs deepseek-r1: ↑ 3699.4%
#46

GPT-5.2 Pro
OpenAI

$2.861250 (rounded ~ $2.86)
vs o4-mini: ↑ 3311.3%
vs deepseek-r1: ↑ 7028.6%
#47

GPT-5.2 Pro
OpenAI

$2.861250 (rounded ~ $2.86)
vs o4-mini: ↑ 3311.3%
vs deepseek-r1: ↑ 7028.6%
✨ How recommendations work (v8.6.0): We scan all active models in the registry and only include those that support ALL your current inputs. For token-based models, we check if they can handle your token counts. For special pricing models (OCR, video, audio), we verify they have the correct pricing structure. Features marked requested were in your inputs but not supported by that model. Now using official provider pricing without reseller markups.

The Smart-Small Model Revolution

Reasoning models no longer require massive budgets. We compare OpenAI’s o4-mini against the open-source powerhouse DeepSeek-R1. This analysis focuses on ‘Thinking Token’ efficiency: which model solves complex math and logic problems with the fewest wasted cycles?

Frequently Asked Questions

How accurate are these AI model cost calculations?
Our calculations are based on official pricing from each provider (Google, OpenAI, Anthropic, Meta, xAI, Perplexity, DeepSeek, Mistral) and are updated regularly. We account for all factors including multimodal inputs, caching discounts, batch API pricing, tool usage multipliers, OCR processing, audio minutes, silence fees, and research mode pricing. Note: Reseller markups and dedicated instance multipliers have been removed to reflect official provider pricing.
How does prompt caching work?
Caching discounts vary by provider: Google and OpenAI offer 90% discounts on cached input tokens. Anthropic uses write (1.25x) and read (0.10x) multipliers. Savings are applied to the token portion only, not unit-based fees.
How do Market Recommendations work (v8.6.0)?
Our recommendation engine scans the entire model registry and only includes models that support ALL your current input parameters (tokens, images, video, audio, OCR, tools, batch API, etc.). It calculates exact costs with your settings and sorts by price, showing you the best value options that can handle your complete workflow. Special pricing models (OCR, video, audio, image generation) are properly handled and only appear when their specific input types are requested. v8.6.0 removes reseller markups (20% buffer) and dedicated instance multipliers to reflect official provider pricing.
What is the YemHub AI Calculator Tool?
The YemHub AI Calculator is the most comprehensive tool for estimating costs and comparing performance metrics across 50+ AI models. It calculates token-based pricing, analyzes multimodal processing, accounts for state-dependent pricing (context cliffs, tiered tunnels), provides optimization recommendations, and now offers intelligent market matching to find the best alternatives for your specific needs.

Related model pricing

o4-mini currently costs $1.10 / $4.40 per 1M tokens. These are the models worth pricing against it, taken live from the tracked registry.

Compare across providers

Other models from the same provider

See every tracked AI pricing change →