AIHubMixAIHubMix
← Models

Gemini 2.5 Pro Search vs GLM 5.2

Output tokens cost $10.00 per million on Gemini 2.5 Pro Search and $3.94 per million on GLM 5.2. Input tokens cost $1.25 per million on Gemini 2.5 Pro Search and $1.13 per million on GLM 5.2. Cached input tokens are billed at $0.13 per million on Gemini 2.5 Pro Search and $0.28 per million on GLM 5.2. Context lengths are 1,048,576 tokens on Gemini 2.5 Pro Search and 1,000,000 tokens on GLM 5.2. Time to first token (TTFT) measured on AIHubMix is 3.2s on Gemini 2.5 Pro Search and 0.6s on GLM 5.2. Measured output throughput is 101.3 tok/s on Gemini 2.5 Pro Search and 45.1 tok/s on GLM 5.2. On the LMArena coding leaderboard Gemini 2.5 Pro Search scores 1465 and GLM 5.2 scores 1505.

GoogleGemini 2.5 Pro SearchZ.AIGLM 5.2
+ Add model · 2/4
Google logo
Gemini 2.5 Pro Search
Google · text, image, audio, video, pdf → text

gemini-2.5-pro-search integrates Google's official search functionality; the search feature will have an additional separate fee log directly incorporated into the scoring, with detailed logs not displayed; this will be fixed and displayed later; only supports OpenAI-compatible formats for invocation, does not support Gemini SDK; for Gemini's native SDK, please set parameters directly using the official search parameters.

Input$1.25 /M
Output$10.00 /M
Details
Z.AI logo
GLM 5.2
Z.AI · text → text

GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.

Input$1.13 /M
Output$3.94 /M
Details

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Gemini 2.5 Pro Search
GLM 5.2
Input /M
$1.25
$1.13
Output /M
$10.00
$3.94
Cache read /M
$0.13
$0.28
Context length
1,048,576
1,000,000
Max output
65,536
128,000
Time to First Token
3.2 s
0.6 s
Throughput
101.3 tok/s
45.1 tok/s
Modalities
textimageaudiovideopdf
text
Supported Parameters
thinkingwebtoolsfunction callingstructured outputslong context
thinkingtoolsfunction callingstructured outputs
API Formats
chat_completions · claude_api
Released
-
June 16, 2026

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

gemini-2.5-pro-searchglm-5.2

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

gemini-2.5-pro-searchglm-5.2

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
gemini-2.5-pro-searchglm-5.2
1420146015001540
Overall
14461470
Coding
14651505
Math
14421475
Hard prompts
14581488
Instruction following
14391462
Multi-turn
14481470
Creative writing
14441450
Longer query
14571479
Chinese
14901516
English
14481477
WebDev Arena
gemini-2.5-pro-searchglm-5.2
1180130014201540
Overall
12041582
React
15941594
HTML
12121537
Gaming
16171617
Simulations
16061606
Data analytics
15421542

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

GLM 5.2
$127 /mo
Gemini 2.5 Pro Search
$225 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: Gemini 2.5 Pro Search, GLM 5.2?

GLM 5.2: $3.94/M output tokens; Gemini 2.5 Pro Search: $10.00/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

GLM 5.2: 1505; Gemini 2.5 Pro Search: 1465 (LMArena coding leaderboard).

Which responds faster?

GLM 5.2: 0.6s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

Gemini 2.5 Pro Search accepts 1,048,576 and GLM 5.2 accepts 1,000,000 input tokens. Maximum output per request is 65,536 tokens on Gemini 2.5 Pro Search and 128,000 tokens on GLM 5.2.

Which one generates tokens faster?

Gemini 2.5 Pro Search at 101.3 tok/s and GLM 5.2 at 45.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Gemini 2.5 Pro Search accepts text, image, audio, video and PDF input and supports thinking, web search, tool calling, function calling, structured outputs and long context; GLM 5.2 accepts text input and supports thinking, tool calling, function calling and structured outputs.

Can I call Gemini 2.5 Pro Search and GLM 5.2 with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.

kimi-k3vsqwen3.8-max-previewclaude-opus-5vsgpt-5.6-lunaclaude-opus-5vsclaude-sonnet-5gemini-3.1-pro-previewvsgpt-5.5glm-5.2vskimi-k3gemini-3.6-flashvsqwen3.8-maxdeepseek-v4-flashvsglm-5.2claude-opus-5vsgrok-4.5
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect