Updated minutes ago
01.AI

Yi-Lightning

01.AI · moe · 200B parameters · 16,384 context

Quality
50.0
Calculate ROI →Compare with othersFine-Tune This Model →

Parameters

200B

Context Window

16K tokens

Architecture

MoE

Best GPU

B200 SXM

Cheapest API

$0.99/M

Intelligence Brief

Yi-Lightning is a 200B parameter Mixture-of-Experts (32 experts, 4 active) model from 01.AI, featuring Grouped Query Attention (GQA) with 64 layers and 6,144 hidden dimensions. With a 16,384 token context window, it supports tools, structured output, code, math, multilingual, reasoning. The most cost-effective API deployment is via 01ai at $0.99/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $8522/month.

Architecture Details

TypeMOE
Total Parameters200B
Active Parameters22B
Layers64
Hidden Dimension6,144
Attention Heads48
KV Heads8
Head Dimension128
Vocab Size64,000
Total Experts32
Active Experts4

Memory Requirements

BF16 Weights

400.0 GB

FP8 Weights

200.0 GB

INT4 Weights

100.0 GB

KV-Cache per Token131072 bytes
Activation Estimate2.00 GB

Fits on (single GPU) — most practical first

BEST FITInstinct MI250X128GBINT4Gaudi 3128GBINT4Gaudi 3 HL-325L128GBINT4H200 SXM141GBINT4B200 SXM180GBINT4H100 NVL 94GB (per GPU pair)188GBINT4B100 SXM192GBINT4GB200 NVL72 (per GPU)192GBINT4GB300 NVL72 (per GPU)192GBINT4Instinct MI300X192GBINT4Groq LPU230GBINT4Instinct MI325X256GBFP8

GPU Compatibility Matrix

Yi-Lightning is compatible with 8% of GPU configurations across 41 GPUs at 3 precision levels.

BF16 (Full)
FP8 (Half)
INT4 (Quarter)
Blackwell(7 GPUs)
B200 NVL (pair)360GB
✗
44%
72%
B300288GB
✗
31%
65%
B100 SXM192GB
✗
✗
48%
GB200 NVL72 (per GPU)192GB
✗
✗
48%
Hopper(7 GPUs)
H100 NVL 94GB (per GPU pair)188GB
✗
✗
47%
H200 SXM141GB
✗
✗
29%
H2096GB
✗
✗
✗
GH20096GB
✗
✗
✗
Ada Lovelace(11 GPUs)
L40S48GB
✗
✗
✗
L4048GB
✗
✗
✗
RTX 6000 Ada48GB
✗
✗
✗
L2048GB
✗
✗
✗
Ampere(16 GPUs)
A100 80GB SXM80GB
✗
✗
✗
A100 80GB PCIe80GB
✗
✗
✗
A1664GB
✗
✗
✗
RTX A600048GB
✗
✗
✗
Legend:No fitVery tightTightModerateGoodExcellent

GPU Recommendations

B200 SXMoptimal

FP8 · 2 GPUs · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8522

Cost/M Tokens

$11.58

Use this config →
B100 SXMoptimal

FP8 · 2 GPUs · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$8541

Cost/M Tokens

$11.61

Use this config →
GB200 NVL72 (per GPU)optimal

FP8 · 2 GPUs · tensorrt-llm

100/100

score

Throughput

280.0 tok/s

Latency (ITL)

3.6ms

Est. TTFT

1ms

Cost/Month

$12337

Cost/M Tokens

$16.77

Use this config →

Deployment Options

API

API Deployment

01ai

$0.99/M

output tokens

Self-Hosted

Single GPU

B200 NVL (pair)

$9965/mo

Min VRAM: 200 GB

Scale

Multi-GPU

B200 SXM x2

280.0 tok/s

TP· $8522/mo

Open Full Calculator →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
01ai$0.99$0.99
Cheapest

Cost Analysis

ProviderInput $/MOutput $/M~Monthly Cost
01aiBest Value$0.99$0.99$10

Cost per 1,000 Requests

Short (500 tok)

$0.69

via 01ai

Medium (2K tok)

$2.77

via 01ai

Long (8K tok)

$9.90

via 01ai

Performance Estimates

Throughput by GPU

B200 SXM
280.0 tok/s
B100 SXM
280.0 tok/s
GB200 NVL72 (per GPU)
280.0 tok/s

VRAM Breakdown (B200 SXM, FP8)

Weights
Weights 100.0 GBKV-Cache 2.1 GBActivations 16.0 GBOverhead 5.0 GB

Precision Impact

bf16

200.0 GB

weights/GPU

fp8

100.0 GB

weights/GPU

~280.0 tok/s

int4

50.0 GB

weights/GPU

Capabilities

Features

✓ Tool Use✗ Vision✓ Code✓ Math✓ Reasoning✓ Multilingual✓ Structured Output

Supported Frameworks

vllmsglang

Supported Precisions

BF16 (default)FP8INT4

Where to Deploy Yi-Lightning

Similar Models

Yi-Large

102.6B params · moe

Quality: 74

from $3.00/M

Larger context, Higher quality, More expensiveCompare →

Claude Opus 4

200B params · dense

Quality: 90

from $75.00/M

Larger context, Higher quality, More expensiveCompare →

GPT-4o

200B params · moe

Quality: 85

from $10.00/M

Larger context, Higher quality, More expensiveCompare →

GPT-4 Turbo

200B params · moe

Quality: 80

from $30.00/M

Larger context, Higher quality, More expensiveCompare →

o1

200B params · moe

Quality: 93

from $60.00/M

Larger context, Higher quality, More expensiveCompare →

Frequently Asked Questions

How much VRAM does Yi-Lightning need for inference?

Yi-Lightning requires approximately 400.0 GB of VRAM at BF16 precision, 200.0 GB at FP8, or 100.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (131072 bytes per token) and activations (~2.00 GB).

What is the best GPU for Yi-Lightning?

The top recommended GPU for Yi-Lightning is the B200 SXM (x2) using FP8 precision. It achieves approximately 280.0 tokens/sec at an estimated cost of $8522/month ($11.58/M tokens). Score: 100/100.

How much does Yi-Lightning inference cost?

Yi-Lightning API inference starts from $0.99/M input tokens and $0.99/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.