DeepSeek V4 DeepSeek 1000000
💰 Total Cost Calculation (from Plugin)
Output: $0.000870
Output: $0.000870
Unit: $0.000000
Fees: $0.000000
Detailed Cost Analysis (from Plugin)
For 250,000 input tokens and 1,000 output tokens:
- Input Cost: $0.108750 (rounded ~ $0.11)
- Output Cost: $0.000870
- Total Cost: $0.109620
- Cost per 1K tokens: $0.000437
- Tokens per dollar: 2,289,728 tokens
- Context Window: 1000000 tokens
Speed & Performance Analysis
With a processing speed of 300 tokens per second and 180ms time to first token:
- Processing Time: 14 minutes, 13.58 seconds
- Latency: 180 milliseconds to first token
- Base Throughput: 300 tokens/second
- Effective Throughput: 294 tokens/second (temperature-adjusted)
Best Use Cases
Want this applied to YOUR actual stack?
This calculator shows the math for DeepSeek V4. 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 DeepSeek V4| Rank | AI Model & Provider | Total Cost | vs DeepSeek V4 |
|---|---|---|---|
| 🏆 |
Devstral Small 2
Mistral AI
|
$0.006325 (rounded ~ $0.01) Best Value | ↓ 94.2% cheaper |
| 🥈 |
Grok Code Fast 1
xAI
|
$0.012875 (rounded ~ $0.01) | ↓ 88.3% cheaper |
| 🥉 |
Gemini 3.1 Flash Lite
Google
|
$0.016000 (rounded ~ $0.02) | ↓ 85.4% cheaper |
| #4 |
Nemotron 3 Super
Mistral AI
|
$0.018955 (rounded ~ $0.02) | ↓ 82.7% cheaper |
| #5 |
Gemini 2.5 Flash
Google
|
$0.019375 | ↓ 82.3% cheaper |
| #6 |
Llama 4 Scout
Meta AI
|
$0.020300 | ↓ 81.5% cheaper |
| #7 |
Devstral 2
Mistral AI
|
$0.025225 (rounded ~ $0.03) | ↓ 77% cheaper |
| #8 |
Mistral Large 3
Mistral AI
|
$0.031625 (rounded ~ $0.03) | ↓ 71.2% cheaper |
| #9 |
Llama 4 Maverick (400B)
Meta AI
|
$0.038100 (rounded ~ $0.04) | ↓ 65.2% cheaper |
| #10 |
GPT-5.4 mini
OpenAI
|
$0.048000 (rounded ~ $0.05) | ↓ 56.2% cheaper |
| #11 |
Claude Haiku 4.5
Anthropic
|
$0.063750 (rounded ~ $0.06) | ↓ 41.8% cheaper |
| #12 |
Grok 4.3
xAI
|
$0.078750 (rounded ~ $0.08) | ↓ 28.2% cheaper |
| #13 |
Gemini 3.5 Flash
Google
|
$0.096000 (rounded ~ $0.10) | ↓ 12.4% cheaper |
| #14 |
Grok 4.20 Beta
xAI
|
$0.126500 (rounded ~ $0.13) | ↑ 15.4% more |
| #15 |
Gemini 3.1 Flash
Google
|
$0.128000 (rounded ~ $0.13) | ↑ 16.8% more |
| #16 |
Claude Sonnet 4.6
Anthropic
|
$0.191250 (rounded ~ $0.19) | ↑ 74.5% more |
| #17 |
Claude Opus 4.7
Anthropic
|
$0.318750 (rounded ~ $0.32) | ↑ 190.8% more |
| #18 |
Claude Opus 4.8
Anthropic
|
$0.318750 (rounded ~ $0.32) | ↑ 190.8% more |
| #19 |
Claude Opus 4.6
Anthropic
|
$0.318750 (rounded ~ $0.32) | ↑ 190.8% more |
| #20 |
GPT-5.4
OpenAI
|
$0.320000 | ↑ 191.9% more |
| #21 |
GPT-5.4 Thinking
OpenAI
|
$0.320000 | ↑ 191.9% more |
| #22 |
Gemini 2.5 Pro
Google
|
$0.320000 | ↑ 191.9% more |
| #23 |
GPT-5.5 Instant
OpenAI
|
$0.320000 | ↑ 191.9% more |
| #24 |
Gemini 3.1 Pro
Google
|
$0.509000 (rounded ~ $0.51) | ↑ 364.3% more |
| #25 |
GPT-5.5
OpenAI
|
$1.272500 (rounded ~ $1.27) | ↑ 1060.8% more |
| #26 |
GPT-5.5 Pro
OpenAI
|
$1.920000 | ↑ 1651.5% more |
| #27 |
GPT-5.5 Pro
OpenAI
|
$1.920000 | ↑ 1651.5% more |
Devstral Small 2 Mistral AI
Grok Code Fast 1 xAI
Gemini 3.1 Flash Lite Google
Nemotron 3 Super Mistral AI
Gemini 2.5 Flash Google
Llama 4 Scout Meta AI
Devstral 2 Mistral AI
Mistral Large 3 Mistral AI
Llama 4 Maverick (400B) Meta AI
GPT-5.4 mini OpenAI
Claude Haiku 4.5 Anthropic
Grok 4.3 xAI
Gemini 3.5 Flash Google
Grok 4.20 Beta xAI
Gemini 3.1 Flash Google
Claude Sonnet 4.6 Anthropic
Claude Opus 4.7 Anthropic
Claude Opus 4.8 Anthropic
Claude Opus 4.6 Anthropic
GPT-5.4 OpenAI
GPT-5.4 Thinking OpenAI
Gemini 2.5 Pro Google
GPT-5.5 Instant OpenAI
Gemini 3.1 Pro Google
GPT-5.5 OpenAI
GPT-5.5 Pro OpenAI
GPT-5.5 Pro OpenAI
Low-Cost High-Throughput Auditing
Evaluate the cost of processing 50GB of raw financial logs. DeepSeek V4’s Engram memory allows for massive context retrieval at a fraction of the cost of Western models.