DeepSeek V3
DeepSeek · text → text
It has been automatically upgraded to the latest released version, 250324. Automatically upgraded to the latest released version 250324.
Input$0.27 /M
Output$1.09 /M
← ModelsDeepSeek V3
GLM 5.2
DeepSeek V3 vs GLM 5.2
Output tokens cost $1.09 per million on DeepSeek V3 and $3.94 per million on GLM 5.2. Input tokens cost $0.27 per million on DeepSeek V3 and $1.13 per million on GLM 5.2. Cached input tokens are billed at $0.27 per million on DeepSeek V3 and $0.28 per million on GLM 5.2. Context lengths are 1,638,000 tokens on DeepSeek V3 and 1,000,000 tokens on GLM 5.2. Time to first token (TTFT) measured on AIHubMix is 1.2s on DeepSeek V3 and 0.6s on GLM 5.2. Measured output throughput is 66.5 tok/s on DeepSeek V3 and 41.5 tok/s on GLM 5.2. On the LMArena coding leaderboard DeepSeek V3 scores 1388 and GLM 5.2 scores 1505.
DeepSeek V3GLM 5.2+ Add model · 2/4
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
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
DeepSeek V3
GLM 5.2
Input /M
$0.27
$1.13
Output /M
$1.09
$3.94
Cache read /M
$0.27
$0.28
Context length
1,638,000
1,000,000
Max output
1,638,000
128,000
Time to First Token
1.2 s
0.6 s
Throughput
66.5 tok/s
41.5 tok/s
Modalities
text
text
Supported Parameters
toolsfunction callingstructured outputs
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.
DeepSeek-V3glm-5.2
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
DeepSeek-V3glm-5.2
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
DeepSeek-V3glm-5.2
1280136014401520
Overall
13591470
Coding
13881505
Math
13111475
Hard prompts
13501488
Instruction following
13441462
Multi-turn
13741470
Creative writing
13491450
Longer query
13751479
Chinese
13691516
English
13711477
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.
DeepSeek V3
$32.64 /mo
GLM 5.2
$127 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: DeepSeek V3, GLM 5.2?
DeepSeek V3: $1.09/M output tokens; GLM 5.2: $3.94/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
GLM 5.2: 1505; DeepSeek V3: 1388 (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?
DeepSeek V3 accepts 1,638,000 and GLM 5.2 accepts 1,000,000 input tokens. Maximum output per request is 1,638,000 tokens on DeepSeek V3 and 128,000 tokens on GLM 5.2.
Which one generates tokens faster?
DeepSeek V3 at 66.5 tok/s and GLM 5.2 at 41.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
DeepSeek V3 accepts text input and supports tool calling, function calling and structured outputs; GLM 5.2 accepts text input and supports thinking, tool calling, function calling and structured outputs.
Can I call DeepSeek V3 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.
AIHubMix