Cohere Embed English v3
Cohere · dense · 0.5B parameters · 512 context
Parameters
0.5B
Context Window
1K tokens
Architecture
Dense
Best GPU
B200 SXM
Cheapest API
$0.10/M
Intelligence Brief
Cohere Embed English v3 is a 0.5B parameter DENSE model from Cohere, featuring Multi-Head Attention (MHA) with 24 layers and 1,024 hidden dimensions. With a 512 token context window, it supports general text generation. The most cost-effective API deployment is via cohere at $0.10/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $4261/month.
Architecture Details
Memory Requirements
BF16 Weights
1.0 GB
FP8 Weights
0.5 GB
INT4 Weights
0.3 GB
GPU Compatibility Matrix
Cohere Embed English v3 is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4261
Cost/M Tokens
$0.46
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$4271
Cost/M Tokens
$0.46
BF16 · 1 GPU · tensorrt-llm
78/100
score
Throughput
3.5K tok/s
Latency (ITL)
0.3ms
Est. TTFT
0ms
Cost/Month
$6169
Cost/M Tokens
$0.67
Deployment Options
API Deployment
cohere
$0.10/M
output tokens
Single GPU
B200 SXM
$4261/mo
Min VRAM: 1 GB
Multi-GPU
B200 SXM
3.5K tok/s
Best available config
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| cohere | $0.10 | $0.10 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| cohereBest Value | $0.10 | $0.10 | $1 |
Cost per 1,000 Requests
Short (500 tok)
$0.07
via cohere
Medium (2K tok)
$0.28
via cohere
Long (8K tok)
$1.00
via cohere
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, BF16)
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Cohere Embed English v3
Self-Hosted Infrastructure
Similar Models
H2O Danube3 500M
0.5B params · dense
Quality: 50
Qwen 2.5 0.5B
0.5B params · dense
Quality: 50
InfoXLM Large
0.55B params · dense
Quality: 50
Multilingual E5 Large
0.56B params · dense
Quality: 50
BGE M3
0.568B params · dense
Quality: 50
from $0.01/M
Frequently Asked Questions
How much VRAM does Cohere Embed English v3 need for inference?
Cohere Embed English v3 requires approximately 1.0 GB of VRAM at BF16 precision, 0.5 GB at FP8, or 0.3 GB at INT4 quantization. Additional VRAM is needed for KV-cache (49152 bytes per token) and activations (~0.10 GB).
What is the best GPU for Cohere Embed English v3?
The top recommended GPU for Cohere Embed English v3 is the B200 SXM using BF16 precision. It achieves approximately 3.5K tokens/sec at an estimated cost of $4261/month ($0.46/M tokens). Score: 78/100.
How much does Cohere Embed English v3 inference cost?
Cohere Embed English v3 API inference starts from $0.10/M input tokens and $0.10/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.