Claude Sonnet 5 Anthropic 1000000
💰 Total Cost Calculation (from Plugin)
Output: $0.005000 (rounded ~ $0.01)
Output: $0.005000 (rounded ~ $0.01)
Unit: $0.000000
Fees: $0.000000
Advanced Cost Breakdown (from Plugin)
Detailed Cost Analysis (from Plugin)
For 100,000 input tokens and 2,000 output tokens:
- Input Cost: $0.050000
- Output Cost: $0.005000 (rounded ~ $0.01)
- Total Cost: $0.032500 (rounded ~ $0.03)
- Cost per 1K tokens: $0.000319
- Tokens per dollar: 3,138,462 tokens
- Context Window: 1000000 tokens
Speed & Performance Analysis
With a processing speed of 460 tokens per second and 195ms time to first token:
- Processing Time: 3 minutes, 46.35 seconds
- Latency: 195 milliseconds to first token
- Base Throughput: 460 tokens/second
- Effective Throughput: 451 tokens/second (temperature-adjusted)
Best Use Cases
Want this applied to YOUR actual stack?
This calculator shows the math for Claude Sonnet 5. 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 OpenAI 1024000
💰 Total Cost Calculation (from Plugin)
Output: $0.015000 (rounded ~ $0.02)
Output: $0.015000 (rounded ~ $0.02)
Unit: $0.000000
Fees: $0.000000
Advanced Cost Breakdown (from Plugin)
Detailed Cost Analysis (from Plugin)
For 100,000 input tokens and 2,000 output tokens:
- Input Cost: $0.125000 (rounded ~ $0.13)
- Output Cost: $0.015000 (rounded ~ $0.02)
- Total Cost: $0.083750 (rounded ~ $0.08)
- Cost per 1K tokens: $0.000821
- Tokens per dollar: 1,217,910 tokens
- Context Window: 1024000 tokens
Speed & Performance Analysis
With a processing speed of 420 tokens per second and 210ms time to first token:
- Processing Time: 4 minutes, 7.89 seconds
- Latency: 210 milliseconds to first token
- Base Throughput: 420 tokens/second
- Effective Throughput: 412 tokens/second (temperature-adjusted)
Best Use Cases
Want this applied to YOUR actual stack?
This calculator shows the math for GPT-5.4. 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 Claude Sonnet 5| Rank | AI Model & Provider | Total Cost | vs Claude Sonnet 5 | vs GPT-5.4 |
|---|---|---|---|---|
| 🏆 |
Mistral Small 3
Mistral AI
|
$0.001525 Best Value | ↓ 95.3% cheaper | ↓ 98.2% cheaper |
| 🥈 |
Gemini 3.1 Flash Lite
Google
|
$0.004188 | ↓ 87.1% cheaper | ↓ 95% cheaper |
| 🥉 |
Gemini 3.5 Flash-Lite
Google
|
$0.005375 (rounded ~ $0.01) | ↓ 83.5% cheaper | ↓ 93.6% cheaper |
| #4 |
Gemini 2.5 Flash
Google
|
$0.005375 (rounded ~ $0.01) | ↓ 83.5% cheaper | ↓ 93.6% cheaper |
| #5 |
Mistral Large 3
Mistral AI
|
$0.007625 (rounded ~ $0.01) | ↓ 76.5% cheaper | ↓ 90.9% cheaper |
| #6 |
Gemini 3.8 Flash
Google
|
$0.012188 (rounded ~ $0.01) | ↓ 62.5% cheaper | ↓ 85.4% cheaper |
| #7 |
GPT-5.4 mini
OpenAI
|
$0.012563 (rounded ~ $0.01) | ↓ 61.3% cheaper | ↓ 85% cheaper |
| #8 |
o4-mini Deep Research
OpenAI
|
$0.015750 (rounded ~ $0.02) | ↓ 51.5% cheaper | ↓ 81.2% cheaper |
| #9 |
Claude Haiku 4.5
Anthropic
|
$0.016250 (rounded ~ $0.02) | ↓ 50% cheaper | ↓ 80.6% cheaper |
| #10 |
Gemini 3.1 Flash
Google
|
$0.016750 (rounded ~ $0.02) | ↓ 48.5% cheaper | ↓ 80% cheaper |
| #11 |
GPT-5.6 Luna
OpenAI
|
$0.016750 (rounded ~ $0.02) | ↓ 48.5% cheaper | ↓ 80% cheaper |
| #12 |
o4-mini
OpenAI
|
$0.017325 (rounded ~ $0.02) | ↓ 46.7% cheaper | ↓ 79.3% cheaper |
| #13 |
Gemini 3.6 Flash
Google
|
$0.024375 (rounded ~ $0.02) | ↓ 25% cheaper | ↓ 70.9% cheaper |
| #14 |
Gemini 3.5 Flash
Google
|
$0.025125 (rounded ~ $0.03) | ↓ 22.7% cheaper | ↓ 70% cheaper |
| #15 |
GPT-5.3 Codex Spark
OpenAI
|
$0.031063 (rounded ~ $0.03) | ↓ 4.4% cheaper | ↓ 62.9% cheaper |
| #16 |
GPT-5.3 Instant
OpenAI
|
$0.031063 (rounded ~ $0.03) | ↓ 4.4% cheaper | ↓ 62.9% cheaper |
| #17 |
GPT-5.6 Terra
OpenAI
|
$0.041875 (rounded ~ $0.04) | ↑ 28.8% more | ↓ 50% cheaper |
| #18 |
Gemini 2.5 Pro
Google
|
$0.044375 (rounded ~ $0.04) | ↑ 36.5% more | ↓ 47% cheaper |
| #19 |
Claude Sonnet 4.6
Anthropic
|
$0.048750 (rounded ~ $0.05) | ↑ 50% more | ↓ 41.8% cheaper |
| #20 |
Grok 4.3
xAI
|
$0.059000 (rounded ~ $0.06) | ↑ 81.5% more | ↓ 29.6% cheaper |
| #21 |
Grok 4.20 Beta
xAI
|
$0.059000 (rounded ~ $0.06) | ↑ 81.5% more | ↓ 29.6% cheaper |
| #22 |
Gemini 3.1 Pro
Google
|
$0.067000 (rounded ~ $0.07) | ↑ 106.2% more | ↓ 20% cheaper |
| #23 |
Claude Opus 4.7
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 150% more | ↓ 3% cheaper |
| #24 |
Claude Opus 5
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 150% more | ↓ 3% cheaper |
| #25 |
Claude Opus 4.8
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 150% more | ↓ 3% cheaper |
| #26 |
Claude Opus 4.6
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 150% more | ↓ 3% cheaper |
| #27 |
GPT-5.4
OpenAI
|
$0.083750 (rounded ~ $0.08) | ↑ 157.7% more | Same price |
| #28 |
GPT-5.4 Thinking
OpenAI
|
$0.083750 (rounded ~ $0.08) | ↑ 157.7% more | Same price |
| #29 |
GPT-5.5 Instant
OpenAI
|
$0.083750 (rounded ~ $0.08) | ↑ 157.7% more | Same price |
| #30 |
GPT-5.6 Sol
OpenAI
|
$0.083750 (rounded ~ $0.08) | ↑ 157.7% more | Same price |
| #31 |
Claude Fable 5.1
Anthropic
|
$0.153125 (rounded ~ $0.15) | ↑ 371.2% more | ↑ 82.8% more |
| #32 |
Claude Mythos 5.1
Anthropic
|
$0.153125 (rounded ~ $0.15) | ↑ 371.2% more | ↑ 82.8% more |
| #33 |
o3 Deep Research
OpenAI
|
$0.157500 (rounded ~ $0.16) | ↑ 384.6% more | ↑ 88.1% more |
| #34 |
Claude Fable 5
Anthropic
|
$0.162500 (rounded ~ $0.16) | ↑ 400% more | ↑ 94% more |
| #35 |
Claude Mythos 5
Anthropic
|
$0.162500 (rounded ~ $0.16) | ↑ 400% more | ↑ 94% more |
| #36 |
GPT-5.5
OpenAI
|
$0.167500 (rounded ~ $0.17) | ↑ 415.4% more | ↑ 100% more |
| #37 |
o3 Pro
OpenAI
|
$0.315000 (rounded ~ $0.32) | ↑ 869.2% more | ↑ 276.1% more |
| #38 |
GPT-6 Astra
OpenAI
|
$0.325000 (rounded ~ $0.33) | ↑ 900% more | ↑ 288.1% more |
| #39 |
GPT-5.2 Pro
OpenAI
|
$0.372750 (rounded ~ $0.37) | ↑ 1046.9% more | ↑ 345.1% more |
| #40 |
GPT-5.2 Pro
OpenAI
|
$0.372750 (rounded ~ $0.37) | ↑ 1046.9% more | ↑ 345.1% more |
Mistral Small 3 Mistral AI
Gemini 3.1 Flash Lite Google
Gemini 3.5 Flash-Lite Google
Gemini 2.5 Flash Google
Mistral Large 3 Mistral AI
Gemini 3.8 Flash Google
GPT-5.4 mini OpenAI
o4-mini Deep Research OpenAI
Claude Haiku 4.5 Anthropic
Gemini 3.1 Flash Google
GPT-5.6 Luna OpenAI
o4-mini OpenAI
Gemini 3.6 Flash Google
Gemini 3.5 Flash Google
GPT-5.3 Codex Spark OpenAI
GPT-5.3 Instant OpenAI
GPT-5.6 Terra OpenAI
Gemini 2.5 Pro Google
Claude Sonnet 4.6 Anthropic
Grok 4.3 xAI
Grok 4.20 Beta xAI
Gemini 3.1 Pro Google
Claude Opus 4.7 Anthropic
Claude Opus 5 Anthropic
Claude Opus 4.8 Anthropic
Claude Opus 4.6 Anthropic
GPT-5.4 OpenAI
GPT-5.4 Thinking OpenAI
GPT-5.5 Instant OpenAI
GPT-5.6 Sol OpenAI
Claude Fable 5.1 Anthropic
Claude Mythos 5.1 Anthropic
o3 Deep Research OpenAI
Claude Fable 5 Anthropic
Claude Mythos 5 Anthropic
GPT-5.5 OpenAI
o3 Pro OpenAI
GPT-6 Astra OpenAI
GPT-5.2 Pro OpenAI
GPT-5.2 Pro OpenAI
Choosing the Right Model for Contract Extraction
For legal engineers tasked with extracting specific clauses—such as termination, liability, or governing law—from 50-page contracts, the choice between Claude Sonnet 5 and GPT-5.4 often comes down to the specific nature of your agentic workflow. Both models excel at structured data extraction, but they behave differently under complex, multi-step instructions.
Claude Sonnet 5 is widely regarded as a balanced production model. Its primary strength lies in its ability to follow long-form instruction sets while maintaining a high degree of fidelity to the source document. It is particularly effective at generating clean, structured JSON outputs, which is critical for downstream pipeline integration in legal tech stacks. When reviewing a 100K-token batch, Sonnet 5 tends to be more concise, which can reduce output overhead without sacrificing the nuance required for legal interpretation.
GPT-5.4, conversely, offers deeper agentic capabilities. If your contract review pipeline requires more than just extraction—such as automatically running a script to verify dates, calculating liability caps, or navigating internal document management systems via tool calls—GPT-5.4 is the stronger candidate. Its reasoning effort is configurable, allowing you to scale up depth for high-stakes documents that require cross-referencing multiple exhibits. For a legal engineer, the trade-off is often between Sonnet 5’s efficient, instruction-following consistency and GPT-5.4’s versatility in multi-step analytical workflows. Start by benchmarking both on your most difficult contract templates to see which model handles your specific legal playbook requirements more consistently.