The Known Good Updated 25 Jul 2026
DeepSeek: DeepSeek V4 Pro vs Z.ai: GLM 5.1 ·DeepSeek vs Z.ai

DeepSeek: DeepSeek V4 Pro vs Z.ai: GLM 5.1 — head-to-head comparison

DeepSeek: DeepSeek V4 Pro profile Z.ai: GLM 5.1 profile All comparisons
DeepSeek: DeepSeek V4 Pro — DeepSeek
Quality
#6 of 61
93based on 3 of 6 evaluations
Known Good Index
Speed
#182 of 316
45.2
Output tokens per second
Price
#145 of 340
$0.54
Blended per 1M tokens
In $0.43 · Out $0.87
Cache hit price
#12 of 206
$0.004
per 1M tokens (−99%)
Context
#25 of 345
1.05M
tokens (~1,600 pages)
Z.ai: GLM 5.1 — Z.ai
Quality
#12 of 61
88based on 3 of 6 evaluations
Known Good Index
Speed
#154 of 316
53.4
Output tokens per second
Price
#221 of 340
$1.48
Blended per 1M tokens
In $0.97 · Out $3.04
Cache hit price
#136 of 206
$0.18
per 1M tokens (−81%)
Context
#195 of 345
205k
tokens (~300 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V4 Pro scores 93 and Z.ai: GLM 5.1 scores 88 — a 5-point lead for DeepSeek: DeepSeek V4 Pro. They share 3 published evaluations, with DeepSeek: DeepSeek V4 Pro ahead on 3 and Z.ai: GLM 5.1 ahead on 0.

Blended pricing is $0.54 per 1M tokens for DeepSeek: DeepSeek V4 Pro and $1.48 for Z.ai: GLM 5.1 — DeepSeek: DeepSeek V4 Pro is about 2.7× cheaper.

Throughput is 45 tokens per second for DeepSeek: DeepSeek V4 Pro and 53 for Z.ai: GLM 5.1, with time to first token at 2.0s and 1.9s. DeepSeek: DeepSeek V4 Pro accepts 1.05M tokens of context against 205k.

DeepSeek: DeepSeek V4 Pro is open weights under Open weights (unrestricted); Z.ai: GLM 5.1 is proprietary. 24 tracked hosts serve one or both, and 13 serve both.

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Known Good Index 93 based on 3 of 6 evaluations 88 based on 3 of 6 evaluations
Blended $/1M $0.54 $1.48
Output tok/s 45 53
Context window 1.05M 205k
Providers 18 19
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Known Good Index 93 88
Mathematics Index 97 92
Science Index 94 89
Agentic Index 89 82
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: DeepSeek V4 Pro · marker = Z.ai: GLM 5.1 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond90 / 85
MATH / AIME97 / 92
SWE-bench Verified78 / 74

Right-hand figures read DeepSeek: DeepSeek V4 Pro / Z.ai: GLM 5.1. DeepSeek: DeepSeek V4 Pro leads on 3 of 3, Z.ai: GLM 5.1 on 0.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Text Arena 1,449 1,465
Text Arena (style controlled) 1,457 1,470
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Input $/1M $0.43 $0.97
Output $/1M $0.87 $3.04
Blended $/1M $0.54 $1.48
Cache read $/1M $0.004 $0.179
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Context window 1.05M 205k
Max output tokens 384k 128k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricDeepSeek: DeepSeek V4 ProZ.ai: GLM 5.1
Output tokens/s 45 53
Time to first token 2.0s 1.9s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

24 hosts · 13 serve both
Full provider benchmarks →
Provider DeepSeek: DeepSeek V4 Pro blendedDeepSeek: DeepSeek V4 Pro tok/s Z.ai: GLM 5.1 blendedZ.ai: GLM 5.1 tok/s
BaseTen $2.17 110 — —
Fireworks $2.17 66 $2.15 90
Novita $1.46 66 $2.13 52
DeepInfra $1.62 65 $1.66 66
GMICloud $0.85 62 $1.50 77
Venice $2.06 61 $2.37 80
Baidu · first party $0.78 58 $1.50 51
Together $2.17 53 — —
Alibaba · first party $1.77 52 — —
AtlasCloud $2.10 46 $1.94 42
Wafer $1.50 45 $1.55 50
DeepSeek · first party $0.54 44 — —
SiliconFlow $1.91 41 $1.83 62
StreamLake $0.84 41 $1.48 25
CoreWeave $2.17 28 $2.15 120
Ionstream $1.41 20 — —
DigitalOcean $1.74 6 $1.81 21
Parasail $2.17 — $2.15 71
Friendli — — $2.15 109
Crusoe — — $2.00 91
Chutes — — $1.50 48
Z.AI · first party — — $2.15 37
Nebius — — $2.15 26
Phala — — $1.96 —

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →