Updated minutes ago
Cohere Embed English v3
Cohere · dense · 0.5B parameters · 512 context
Quality50.0
Architecture Details
TypeDENSE
Total Parameters0.5B
Active Parameters0.5B
Layers24
Hidden Dimension1,024
Attention Heads16
KV Heads16
Head Dimension64
Vocab Size256,000
Memory Requirements
BF16 Weights
1.0 GB
FP8 Weights
0.5 GB
INT4 Weights
0.3 GB
KV-Cache per Token49152 bytes
Activation Estimate0.10 GB
Fits on (single-node)
B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16
GPU Recommendations
B200 SXMgood
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Cost/Month
$4261
Cost/M Tokens
$0.46
B100 SXMgood
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Cost/Month
$4271
Cost/M Tokens
$0.46
GB200 NVL72 (per GPU)good
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Cost/Month
$6169
Cost/M Tokens
$0.67
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| cohere | $0.10 | $0.10 | Cheapest |
Capabilities
Features
✗ Tool Use✗ Vision✗ Code✗ Math✗ Reasoning✗ Multilingual✗ Structured Output
Supported Frameworks
Supported Precisions
BF16 (default)