GLM-5
Zhipu AI · dense · 200B parameters · 128,000 context
Parameters
200B
Context Window
125K tokens
Architecture
Dense
Best GPU
B200 SXM
Cheapest API
$0.00/M
Intelligence Brief
GLM-5 is a 200B parameter DENSE model from Zhipu AI, featuring Grouped Query Attention (GQA) with 80 layers and 12,288 hidden dimensions. With a 128,000 token context window, it supports tools, vision, structured output, code, math, multilingual, reasoning. The most cost-effective API deployment is via fireworks at $0.00/M output tokens. For self-hosted inference, B200 SXM delivers optimal throughput at $8522/month.
Provider pricing
7 providers · canonical: zhipu| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| fireworks | free | free | cheapest input · cheapest output |
| zai | free | free | cheapest input · cheapest output |
| featherless | free | free | cheapest input · cheapest output |
| openrouter | $0.600 | $1.92 | — |
| together | $1.00 | $3.20 | — |
| novita | $1.00 | $3.20 | — |
| zhipucanonical | $2.00 | $6.00 | — |
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
3 suggestions
Mistral Large 2411Mistral Large · 123B$6.00/M out
DeepSeek R1DeepSeek R1 · 37B$2.00/M out- DeepSeek V3-0324DeepSeek V3 · 37Bfree/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
400.0 GB
FP8 Weights
200.0 GB
INT4 Weights
100.0 GB
Fits on (single GPU) — most practical first
GPU Compatibility Matrix
GLM-5 is compatible with 8% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 2 GPUs · tensorrt-llm
98/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$8522
Cost/M Tokens
$11.58
FP8 · 2 GPUs · tensorrt-llm
98/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$8541
Cost/M Tokens
$11.61
FP8 · 2 GPUs · tensorrt-llm
95/100
score
Throughput
280.0 tok/s
Latency (ITL)
3.6ms
Est. TTFT
1ms
Cost/Month
$5106
Cost/M Tokens
$6.94
Deployment Options
API Deployment
fireworks
$0.00/M
output tokens
Single GPU
B200 NVL (pair)
$9965/mo
Min VRAM: 200 GB
Multi-GPU
B200 SXM x2
280.0 tok/s
TP· $8522/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| fireworks | $0.00 | $0.00 | Cheapest |
| zai | $0.00 | $0.00 | |
| featherless | $0.00 | $0.00 | |
| openrouter | $0.60 | $1.92 | |
| together | $1.00 | $3.20 | |
| novita | $1.00 | $3.20 | |
| zhipu | $2.00 | $6.00 |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| fireworksBest Value | $0.00 | $0.00 | $0 |
| zai | $0.00 | $0.00 | $0 |
| featherless | $0.00 | $0.00 | $0 |
| openrouter | $0.60 | $1.92 | $13 |
| together | $1.00 | $3.20 | $21 |
| novita | $1.00 | $3.20 | $21 |
| zhipu | $2.00 | $6.00 | $40 |
Cost per 1,000 Requests
Short (500 tok)
$0.00
via fireworks
Medium (2K tok)
$0.00
via fireworks
Long (8K tok)
$0.00
via fireworks
Performance Estimates
Throughput by GPU
VRAM Breakdown (B200 SXM, FP8)
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
Supported Frameworks
Supported Precisions
Where to Deploy GLM-5
Self-Hosted Infrastructure
Similar Models
Yi-Lightning
200B params · moe
Quality: 50
from $0.99/M
Claude Opus 4
200B params · dense
Quality: 90
from $75.00/M
GPT-4 Turbo
200B params · moe
Quality: 80
from $30.00/M
GPT-4o
200B params · moe
Quality: 85
from $10.00/M
o1
200B params · moe
Quality: 93
from $60.00/M
Frequently Asked Questions
How much VRAM does GLM-5 need for inference?
GLM-5 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 (327680 bytes per token) and activations (~4.00 GB).
What is the best GPU for GLM-5?
The top recommended GPU for GLM-5 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: 98/100.
How much does GLM-5 inference cost?
GLM-5 API inference starts from $0.00/M input tokens and $0.00/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.