Yi 1.5 9B
01.AI · dense · 8.83B parameters · 4,096 context
Parameters
8.83B
Context Window
4K tokens
Architecture
Dense
Best GPU
A30
Cheapest API
$0.20/M
Quality Score
62/100
Intelligence Brief
Yi 1.5 9B is a 8.83B parameter DENSE model from 01.AI, featuring Grouped Query Attention (GQA) with 48 layers and 4,096 hidden dimensions. With a 4,096 token context window, it supports tools, structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 69, HumanEval 35, GSM8K 68. The most cost-effective API deployment is via 01ai at $0.20/M output tokens. For self-hosted inference, A30 delivers optimal throughput at $332/month.
Provider pricing
1 provider · canonical: 01ai| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| 01aicanonical | $0.200 | $0.200 | cheapest input · cheapest output |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- Yi 1.5 34BYi 1.5 · 34.4B$0.800/M out
- Yi Coder 9BYi Coder · 8.8B—
- Yi 6B 200KYi · 6B—
Qwen 2.5 14BQwen 2.5 · 14.8B$0.300/M out- Qwen 2.5 32BQwen 2.5 · 32.5B$0.800/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
17.7 GB
FP8 Weights
8.8 GB
INT4 Weights
4.4 GB
GPU Compatibility Matrix
Yi 1.5 9B is compatible with 90% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
285.3 tok/s
Latency (ITL)
3.5ms
Est. TTFT
1ms
Cost/Month
$332
Cost/M Tokens
$0.44
BF16 · 1 GPU · vllm
100/100
score
Throughput
308.2 tok/s
Latency (ITL)
3.2ms
Est. TTFT
1ms
Cost/Month
$370
Cost/M Tokens
$0.46
BF16 · 1 GPU · vllm
100/100
score
Throughput
286.2 tok/s
Latency (ITL)
3.5ms
Est. TTFT
1ms
Cost/Month
$180
Cost/M Tokens
$0.24
Deployment Options
API Deployment
01ai
$0.20/M
output tokens
Single GPU
A30
$332/mo
Min VRAM: 9 GB
Multi-GPU
RTX 3060 x2
174.3 tok/s
TP· $114/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| 01ai | $0.20 | $0.20 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| 01aiBest Value | $0.20 | $0.20 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.14
via 01ai
Medium (2K tok)
$0.56
via 01ai
Long (8K tok)
$2.00
via 01ai
Performance Estimates
Throughput by GPU
VRAM Breakdown (A30, BF16)
Precision Impact
bf16
17.7 GB
weights/GPU
~285.3 tok/s
fp8
8.8 GB
weights/GPU
int4
4.4 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Yi 1.5 9B
Self-Hosted Infrastructure
Similar Models
Yi Coder 9B
8.8B params · dense
Quality: 50
Eagle 2 9B
9B params · dense
Quality: 65
CodeGemma 7B
8.5B params · dense
Quality: 52
Gemma 2 9B
9.2B params · dense
Quality: 68
from $0.10/M
ChatGLM4 9B
9.4B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does Yi 1.5 9B need for inference?
Yi 1.5 9B requires approximately 17.7 GB of VRAM at BF16 precision, 8.8 GB at FP8, or 4.4 GB at INT4 quantization. Additional VRAM is needed for KV-cache (98304 bytes per token) and activations (~1.00 GB).
What is the best GPU for Yi 1.5 9B?
The top recommended GPU for Yi 1.5 9B is the A30 using BF16 precision. It achieves approximately 285.3 tokens/sec at an estimated cost of $332/month ($0.44/M tokens). Score: 100/100.
How much does Yi 1.5 9B inference cost?
Yi 1.5 9B API inference starts from $0.20/M input tokens and $0.20/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.