Translation Cost Optimization: 100K-Token Per-Request Translation for Gemini 3.1 Flash vs GPT-5.4 mini

Gemini 3.1 Flash vs GPT-5.4 mini
Complete Comparison: 100,000 input tokens × 100,000 output tokens
Comparison Mode
⚡ 50% Cached

Complete comparison of pricing, performance, and capabilities for 2 leading AI models with 50% Cached.

⚡ Caching Optimized (up to 90% savings) 📊 Batch API
Comparison Criteria Gemini 3.1 Flash
Google
GPT-5.4 mini
OpenAI
Calculation Results (Current Inputs) (50% cached)
Input Tokens 100,000 100,000
Output Tokens 100,000 100,000
Cost Breakdown
Input Cost $0.025000 (rounded ~ $0.03)Worst $0.018750 (rounded ~ $0.02)Best
Output Cost $0.150000Worst $0.112500 (rounded ~ $0.11)Best
Unit Cost (Audio/OCR) $0.000000 $0.000000
Service Fees $0.000000 $0.000000
Total Cost $0.163750 (rounded ~ $0.16) Most Expensive $0.122813 (rounded ~ $0.12) Best Value
Processing Time 4 minutes, 17.68 seconds Fastest 6 minutes, 52.18 seconds Slowest
Tokens per Second 800Fastest 500Slowest
Time to First Token 100ms Best 180ms Worst
Cost per 1K tokens $0.000819Worst $0.000614Best
Tokens per Dollar 1,221,374Worst Value 1,628,499Best Value
Cost per 1 Million Tokens (Informational)
Input Cost / 1M (Base) $0.250000Worst $0.187500 (rounded ~ $0.19)Best
Output Cost / 1M (Base) $1.500000Worst $1.125000 (rounded ~ $1.13)Best
Input Cost / 1M (Optimized) $0.125000 (rounded ~ $0.13)Worst
Optimizations: 50.0% batch
$0.093750 (rounded ~ $0.09)Best
Optimizations: 50.0% batch
Output Cost / 1M (Optimized) $0.750000Worst
Optimizations: 50.0% batch
$0.562500 (rounded ~ $0.56)Best
Optimizations: 50.0% batch
Capabilities & Advanced Features
Images Support ✓ Supported ✓ Supported
Video Support ✓ Supported ✗ Not Supported
Audio Support ✓ Supported ✗ Not Supported
Caching Support
50
✓ Supported ✓ Supported
Batch API Support ✓ Supported ✓ Supported
Tool Usage Support ✓ Supported ✓ 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

Gemini 3.1 Flash
GoogleMax Context: 1,000,000 tokens
$0.5 / $3 per 1M tokens (Tier 1)
State-dependent pricing active. Current tier: Standard
▼
▼
Use Batch API (50% discount)
50%
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

$0.163750 Total Cost
$0.012500 Input Cost
$0.150000 Output Cost
$0.000000 Unit Cost
$0.000000 Search Cost
$0.000000 Request Fee
$0.000000 Tool Fee
$0.000000 Code Execution
200,000Total Tokens
$0.000819Cost per 1K
1,221,374Tokens per $
🔄 Dynamic Tier Pricing Active: Using Standard pricing (tier1) based on token volume.
📊 Advanced Cost Breakdown

Processing Speed

4m 17s Processing Time
800 Tokens/Second
100ms Time to First Token
777 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.

Gemini 3.1 Flash Google 1000000

$0.163750 (rounded ~ $0.16)
Total Cost
⚡ 50% Cached 📊 Batch API
👁️
Vision/Images
✓ Available
🎧
Audio Processing
✓ Available
🎥
Video Analysis
✓ Available
🔧
Tool Usage
✓ Available
📄
OCR Support
✗ Not Available
📊
Batch API
✓ Available
⚡
Caching
✓ Available
90% savings

💰 Total Cost Calculation (from Plugin)

Base Cost (No Optimizations) $0.175000 (rounded ~ $0.18) Input: $0.025000 (rounded ~ $0.03)
Output: $0.150000
Optimized Cost $0.163750 (rounded ~ $0.16) Input: $0.025000 (rounded ~ $0.03)
Output: $0.150000
Unit: $0.000000
Fees: $0.000000
Total Savings $0.011250 (rounded ~ $0.01) 6.4% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount
📊 Dynamic Tier
Standard
tier1 pricing based on 0 tokens

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 100,000 output tokens:

  • Input Cost: $0.025000 (rounded ~ $0.03)
  • Output Cost: $0.150000
  • Total Cost: $0.163750 (rounded ~ $0.16)
  • Cost per 1K tokens: $0.000819
  • Tokens per dollar: 1,221,374 tokens
  • Context Window: 1000000 tokens

Speed & Performance Analysis

With a processing speed of 800 tokens per second and 100ms time to first token:

  • Processing Time: 4 minutes, 17.68 seconds
  • Latency: 100 milliseconds to first token
  • Base Throughput: 800 tokens/second
  • Effective Throughput: 777 tokens/second (temperature-adjusted)

Best Use Cases

High-throughput translation pipelines requiring consistent tone and structured data output.

Want this applied to YOUR actual stack?

This calculator shows the math for Gemini 3.1 Flash. 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 →

GPT-5.4 mini OpenAI

$0.122813 (rounded ~ $0.12)
Total Cost
⚡ 50% Cached 📊 Batch API
👁️
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) $0.131250 (rounded ~ $0.13) Input: $0.018750 (rounded ~ $0.02)
Output: $0.112500 (rounded ~ $0.11)
Optimized Cost $0.122813 (rounded ~ $0.12) Input: $0.018750 (rounded ~ $0.02)
Output: $0.112500 (rounded ~ $0.11)
Unit: $0.000000
Fees: $0.000000
Total Savings $0.008438 (rounded ~ $0.01) 6.4% discount

Advanced Cost Breakdown (from Plugin)

📊 Batch API
50.0% off
Asynchronous processing discount

Detailed Cost Analysis (from Plugin)

For 100,000 input tokens and 100,000 output tokens:

  • Input Cost: $0.018750 (rounded ~ $0.02)
  • Output Cost: $0.112500 (rounded ~ $0.11)
  • Total Cost: $0.122813 (rounded ~ $0.12)
  • Cost per 1K tokens: $0.000614
  • Tokens per dollar: 1,628,499 tokens
  • Context Window: 400000 tokens

Speed & Performance Analysis

With a processing speed of 500 tokens per second and 180ms time to first token:

  • Processing Time: 6 minutes, 52.18 seconds
  • Latency: 180 milliseconds to first token
  • Base Throughput: 500 tokens/second
  • Effective Throughput: 485 tokens/second (temperature-adjusted)

Best Use Cases

High-throughput translation pipelines requiring consistent tone and structured data output.

Want this applied to YOUR actual stack?

This calculator shows the math for GPT-5.4 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 →

✨ Market Recommendations AI Model Registry

← Back to Gemini 3.1 Flash
📋 Active Input Parameters
Input Tokens: 100,000
Output Tokens: 100,000
Batch API: Enabled (50% discount)
Cached Tokens: 50%
Rank AI Model & Provider Total Cost vs Gemini 3.1 Flash vs GPT-5.4 mini
🏆 Devstral Small 2
Mistral AI
 $0.008875 (rounded ~ $0.01) Best Value ↓ 94.6% cheaper ↓ 92.8% cheaper
🥈 Nemotron 3 Super
NVIDIA
 $0.024625 (rounded ~ $0.02) ↓ 85% cheaper ↓ 79.9% cheaper
🥉 Devstral 2
Mistral AI
 $0.028000 (rounded ~ $0.03) ↓ 82.9% cheaper ↓ 77.2% cheaper
#4 Gemini 3.1 Flash Lite
Google
 $0.040938 ↓ 75% cheaper ↓ 66.7% cheaper
#5 Mistral Large 3
Mistral AI
 $0.044375 (rounded ~ $0.04) ↓ 72.9% cheaper ↓ 63.9% cheaper
#6 Gemini 3.5 Flash-Lite
Google
 $0.066625 (rounded ~ $0.07) ↓ 59.3% cheaper ↓ 45.8% cheaper
#7 Gemini 2.5 Flash
Google
 $0.066625 (rounded ~ $0.07) ↓ 59.3% cheaper ↓ 45.8% cheaper
#8 Gemini 3.8 Flash
Google
 $0.104063 (rounded ~ $0.10) ↓ 36.5% cheaper ↓ 15.3% cheaper
#9 GPT-5.4 mini
OpenAI
 $0.122813 (rounded ~ $0.12) ↓ 25% cheaper Same price
#10 o4-mini
OpenAI
 $0.125125 (rounded ~ $0.13) ↓ 23.6% cheaper ↑ 1.9% more
#11 Claude Haiku 4.5
Anthropic
 $0.138750 (rounded ~ $0.14) ↓ 15.3% cheaper ↑ 13% more
#12 GPT-5.6 Luna
OpenAI
 $0.163750 (rounded ~ $0.16) Same price ↑ 33.3% more
#13 Gemini 3.6 Flash
Google
 $0.208125 (rounded ~ $0.21) ↑ 27.1% more ↑ 69.5% more
#14 Gemini 3.5 Flash
Google
 $0.245625 (rounded ~ $0.25) ↑ 50% more ↑ 100% more
#15 Grok 4.3
xAI
 $0.255000 (rounded ~ $0.26) ↑ 55.7% more ↑ 107.6% more
#16 Grok 4.20 Beta
xAI
 $0.255000 (rounded ~ $0.26) ↑ 55.7% more ↑ 107.6% more
#17 Claude Sonnet 5
Anthropic
 $0.277500 (rounded ~ $0.28) ↑ 69.5% more ↑ 126% more
#18 GPT-5.3 Codex Spark
OpenAI
 $0.374063 (rounded ~ $0.37) ↑ 128.4% more ↑ 204.6% more
#19 GPT-5.6 Terra
OpenAI
 $0.409375 ↑ 150% more ↑ 233.3% more
#20 Claude Sonnet 4.6
Anthropic
 $0.416250 (rounded ~ $0.42) ↑ 154.2% more ↑ 238.9% more
#21 Gemini 2.5 Pro
Google
 $0.534375 (rounded ~ $0.53) ↑ 226.3% more ↑ 335.1% more
#22 Gemini 3.1 Pro
Google
 $0.655000 (rounded ~ $0.66) ↑ 300% more ↑ 433.3% more
#23 Claude Opus 4.7
Anthropic
 $0.693750 (rounded ~ $0.69) ↑ 323.7% more ↑ 464.9% more
#24 Claude Opus 5
Anthropic
 $0.693750 (rounded ~ $0.69) ↑ 323.7% more ↑ 464.9% more
#25 Claude Opus 4.8
Anthropic
 $0.693750 (rounded ~ $0.69) ↑ 323.7% more ↑ 464.9% more
#26 Claude Opus 4.6
Anthropic
 $0.693750 (rounded ~ $0.69) ↑ 323.7% more ↑ 464.9% more
#27 GPT-5.4
OpenAI
 $0.818750 (rounded ~ $0.82) ↑ 400% more ↑ 566.7% more
#28 GPT-5.4 Thinking
OpenAI
 $0.818750 (rounded ~ $0.82) ↑ 400% more ↑ 566.7% more
#29 GPT-5.5 Instant
OpenAI
 $0.818750 (rounded ~ $0.82) ↑ 400% more ↑ 566.7% more
#30 GPT-5.6 Sol
OpenAI
 $0.818750 (rounded ~ $0.82) ↑ 400% more ↑ 566.7% more
#31 o3 Deep Research
OpenAI
 $1.137500 (rounded ~ $1.14) ↑ 594.7% more ↑ 826.2% more
#32 Claude Fable 5.1
Anthropic
 $1.378125 (rounded ~ $1.38) ↑ 741.6% more ↑ 1022.1% more
#33 Claude Mythos 5.1
Anthropic
 $1.378125 (rounded ~ $1.38) ↑ 741.6% more ↑ 1022.1% more
#34 Claude Fable 5
Anthropic
 $1.387500 (rounded ~ $1.39) ↑ 747.3% more ↑ 1029.8% more
#35 Claude Mythos 5
Anthropic
 $1.387500 (rounded ~ $1.39) ↑ 747.3% more ↑ 1029.8% more
#36 GPT-5.5
OpenAI
 $1.637500 (rounded ~ $1.64) ↑ 900% more ↑ 1233.3% more
#37 o3 Pro
OpenAI
 $2.275000 (rounded ~ $2.28) ↑ 1289.3% more ↑ 1752.4% more
#38 GPT-6 Astra
OpenAI
 $2.775000 (rounded ~ $2.78) ↑ 1594.7% more ↑ 2159.5% more
#39 GPT-6 Astra
OpenAI
 $2.775000 (rounded ~ $2.78) ↑ 1594.7% more ↑ 2159.5% more
🏆

Devstral Small 2
Mistral AI

$0.008875 (rounded ~ $0.01)
vs Gemini 3.1 Flash: ↓ 94.6%
vs GPT-5.4 mini: ↓ 92.8%
🥈

Nemotron 3 Super
NVIDIA

$0.024625 (rounded ~ $0.02)
vs Gemini 3.1 Flash: ↓ 85%
vs GPT-5.4 mini: ↓ 79.9%
🥉

Devstral 2
Mistral AI

$0.028000 (rounded ~ $0.03)
vs Gemini 3.1 Flash: ↓ 82.9%
vs GPT-5.4 mini: ↓ 77.2%
#4

Gemini 3.1 Flash Lite
Google

$0.040938
vs Gemini 3.1 Flash: ↓ 75%
vs GPT-5.4 mini: ↓ 66.7%
#5

Mistral Large 3
Mistral AI

$0.044375 (rounded ~ $0.04)
vs Gemini 3.1 Flash: ↓ 72.9%
vs GPT-5.4 mini: ↓ 63.9%
#6

Gemini 3.5 Flash-Lite
Google

$0.066625 (rounded ~ $0.07)
vs Gemini 3.1 Flash: ↓ 59.3%
vs GPT-5.4 mini: ↓ 45.8%
#7

Gemini 2.5 Flash
Google

$0.066625 (rounded ~ $0.07)
vs Gemini 3.1 Flash: ↓ 59.3%
vs GPT-5.4 mini: ↓ 45.8%
#8

Gemini 3.8 Flash
Google

$0.104063 (rounded ~ $0.10)
vs Gemini 3.1 Flash: ↓ 36.5%
vs GPT-5.4 mini: ↓ 15.3%
#9

GPT-5.4 mini
OpenAI

$0.122813 (rounded ~ $0.12)
vs Gemini 3.1 Flash: ↓ 25%
vs GPT-5.4 mini: Same
#10

o4-mini
OpenAI

$0.125125 (rounded ~ $0.13)
vs Gemini 3.1 Flash: ↓ 23.6%
vs GPT-5.4 mini: ↑ 1.9%
#11

Claude Haiku 4.5
Anthropic

$0.138750 (rounded ~ $0.14)
vs Gemini 3.1 Flash: ↓ 15.3%
vs GPT-5.4 mini: ↑ 13%
#12

GPT-5.6 Luna
OpenAI

$0.163750 (rounded ~ $0.16)
vs Gemini 3.1 Flash: Same
vs GPT-5.4 mini: ↑ 33.3%
#13

Gemini 3.6 Flash
Google

$0.208125 (rounded ~ $0.21)
vs Gemini 3.1 Flash: ↑ 27.1%
vs GPT-5.4 mini: ↑ 69.5%
#14

Gemini 3.5 Flash
Google

$0.245625 (rounded ~ $0.25)
vs Gemini 3.1 Flash: ↑ 50%
vs GPT-5.4 mini: ↑ 100%
#15

Grok 4.3
xAI

$0.255000 (rounded ~ $0.26)
vs Gemini 3.1 Flash: ↑ 55.7%
vs GPT-5.4 mini: ↑ 107.6%
#16

Grok 4.20 Beta
xAI

$0.255000 (rounded ~ $0.26)
vs Gemini 3.1 Flash: ↑ 55.7%
vs GPT-5.4 mini: ↑ 107.6%
#17

Claude Sonnet 5
Anthropic

$0.277500 (rounded ~ $0.28)
vs Gemini 3.1 Flash: ↑ 69.5%
vs GPT-5.4 mini: ↑ 126%
#18

GPT-5.3 Codex Spark
OpenAI

$0.374063 (rounded ~ $0.37)
vs Gemini 3.1 Flash: ↑ 128.4%
vs GPT-5.4 mini: ↑ 204.6%
#19

GPT-5.6 Terra
OpenAI

$0.409375
vs Gemini 3.1 Flash: ↑ 150%
vs GPT-5.4 mini: ↑ 233.3%
#20

Claude Sonnet 4.6
Anthropic

$0.416250 (rounded ~ $0.42)
vs Gemini 3.1 Flash: ↑ 154.2%
vs GPT-5.4 mini: ↑ 238.9%
#21

Gemini 2.5 Pro
Google

$0.534375 (rounded ~ $0.53)
vs Gemini 3.1 Flash: ↑ 226.3%
vs GPT-5.4 mini: ↑ 335.1%
#22

Gemini 3.1 Pro
Google

$0.655000 (rounded ~ $0.66)
vs Gemini 3.1 Flash: ↑ 300%
vs GPT-5.4 mini: ↑ 433.3%
#23

Claude Opus 4.7
Anthropic

$0.693750 (rounded ~ $0.69)
vs Gemini 3.1 Flash: ↑ 323.7%
vs GPT-5.4 mini: ↑ 464.9%
#24

Claude Opus 5
Anthropic

$0.693750 (rounded ~ $0.69)
vs Gemini 3.1 Flash: ↑ 323.7%
vs GPT-5.4 mini: ↑ 464.9%
#25

Claude Opus 4.8
Anthropic

$0.693750 (rounded ~ $0.69)
vs Gemini 3.1 Flash: ↑ 323.7%
vs GPT-5.4 mini: ↑ 464.9%
#26

Claude Opus 4.6
Anthropic

$0.693750 (rounded ~ $0.69)
vs Gemini 3.1 Flash: ↑ 323.7%
vs GPT-5.4 mini: ↑ 464.9%
#27

GPT-5.4
OpenAI

$0.818750 (rounded ~ $0.82)
vs Gemini 3.1 Flash: ↑ 400%
vs GPT-5.4 mini: ↑ 566.7%
#28

GPT-5.4 Thinking
OpenAI

$0.818750 (rounded ~ $0.82)
vs Gemini 3.1 Flash: ↑ 400%
vs GPT-5.4 mini: ↑ 566.7%
#29

GPT-5.5 Instant
OpenAI

$0.818750 (rounded ~ $0.82)
vs Gemini 3.1 Flash: ↑ 400%
vs GPT-5.4 mini: ↑ 566.7%
#30

GPT-5.6 Sol
OpenAI

$0.818750 (rounded ~ $0.82)
vs Gemini 3.1 Flash: ↑ 400%
vs GPT-5.4 mini: ↑ 566.7%
#31

o3 Deep Research
OpenAI

$1.137500 (rounded ~ $1.14)
vs Gemini 3.1 Flash: ↑ 594.7%
vs GPT-5.4 mini: ↑ 826.2%
#32

Claude Fable 5.1
Anthropic

$1.378125 (rounded ~ $1.38)
vs Gemini 3.1 Flash: ↑ 741.6%
vs GPT-5.4 mini: ↑ 1022.1%
#33

Claude Mythos 5.1
Anthropic

$1.378125 (rounded ~ $1.38)
vs Gemini 3.1 Flash: ↑ 741.6%
vs GPT-5.4 mini: ↑ 1022.1%
#34

Claude Fable 5
Anthropic

$1.387500 (rounded ~ $1.39)
vs Gemini 3.1 Flash: ↑ 747.3%
vs GPT-5.4 mini: ↑ 1029.8%
#35

Claude Mythos 5
Anthropic

$1.387500 (rounded ~ $1.39)
vs Gemini 3.1 Flash: ↑ 747.3%
vs GPT-5.4 mini: ↑ 1029.8%
#36

GPT-5.5
OpenAI

$1.637500 (rounded ~ $1.64)
vs Gemini 3.1 Flash: ↑ 900%
vs GPT-5.4 mini: ↑ 1233.3%
#37

o3 Pro
OpenAI

$2.275000 (rounded ~ $2.28)
vs Gemini 3.1 Flash: ↑ 1289.3%
vs GPT-5.4 mini: ↑ 1752.4%
#38

GPT-6 Astra
OpenAI

$2.775000 (rounded ~ $2.78)
vs Gemini 3.1 Flash: ↑ 1594.7%
vs GPT-5.4 mini: ↑ 2159.5%
#39

GPT-6 Astra
OpenAI

$2.775000 (rounded ~ $2.78)
vs Gemini 3.1 Flash: ↑ 1594.7%
vs GPT-5.4 mini: ↑ 2159.5%
✨ 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.

For teams managing large-scale product catalogs, the choice between Gemini 3.1 Flash and GPT-5.4 mini often hinges on balancing throughput with linguistic nuance. Translation pipelines require models that can handle diverse, structured data—like product descriptions, technical specs, and SEO meta-tags—without hallucinations or formatting drift.

Gemini 3.1 Flash is frequently favored in high-volume, automated environments where latency is a primary concern. Its native architecture excels at processing long-form product documentation in a single pass, making it an efficient candidate for bulk localization tasks. The model’s ability to maintain context across massive datasets ensures that consistent brand terminology is applied across multiple languages, reducing the need for manual post-editing.

On the other hand, GPT-5.4 mini offers a distinct advantage for teams prioritizing tight instruction following and structured output generation. For catalogs where strict adherence to JSON schemas or specific XML formatting is non-negotiable, this model provides high reliability. It excels at nuanced tasks like adapting cultural references or maintaining specific SEO keyword density, which are critical for international market penetration. While both models are highly capable, the decision often comes down to the specific operational constraints of your pipeline—whether your priority is raw speed and throughput or the precision of complex, multi-step translation instructions.

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

Gemini 3.1 Flash currently costs $0.50 / $3.00 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 →