Updated minutes ago
GPT-4.5 Preview
OpenAI · moe · 1500B parameters · 128,000 context
Quality93.0
Architecture Details
TypeMOE
Total Parameters1500B
Active Parameters300B
Layers120
Hidden Dimension16,384
Attention Heads128
KV Heads16
Head Dimension128
Vocab Size200,000
Total Experts16
Active Experts2
Memory Requirements
BF16 Weights
3000.0 GB
FP8 Weights
1500.0 GB
INT4 Weights
750.0 GB
KV-Cache per Token3932160 bytes
Activation Estimate20.00 GB
Fits on (single-node)
B200 NVL (pair)x3 INT4Instinct MI325Xx4 INT4B300x4 INT4Groq LPUx4 INT4B200 SXMx5 INT4B100 SXMx5 INT4GB200 NVL72 (per GPU)x5 INT4GB300 NVL72 (per GPU)x5 INT4
GPU Recommendations
B200 SXMgood
BF16 · 32 GPUs · tensorrt-llm
63/100
score
Throughput
140.0 tok/s
Cost/Month
$136352
Cost/M Tokens
$370.60
B100 SXMgood
BF16 · 32 GPUs · tensorrt-llm
63/100
score
Throughput
140.0 tok/s
Cost/Month
$136656
Cost/M Tokens
$371.43
GB200 NVL72 (per GPU)good
BF16 · 32 GPUs · tensorrt-llm
63/100
score
Throughput
140.0 tok/s
Cost/Month
$197392
Cost/M Tokens
$536.51
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openai | $75.00 | $150.00 | Cheapest |
Quality Benchmarks
MMLU90.0
HumanEval76.0
GSM8K96.0
MT-Bench91.0
Capabilities
Features
✓ Tool Use✓ Vision✓ Code✓ Math✓ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
Supported Precisions
BF16 (default)