GLM-5.2 vs GPT-5.4
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Z.AI
3 providers:
Fireworks $1.40/$4.40
Together $1.40/$4.40
Z.AI $1.40/$4.40
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current flagship Open weights | Current flagship |
| Released | Jun 13, 2026 | Aug 15, 2025 |
| Pricing per million tokens | ||
| Input | $1.40/Mtok | $2.50/Mtok |
| Output | $4.40/Mtok | $15.00/Mtok |
| Blended avg | $2.15/Mtok | $5.63/Mtok |
| Cached input | $0.260/Mtok | $0.250/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks sources: Vellum LLM Leaderboard / OpenAI model card, Artificial Analysis | ||
| Avg benchmark score | 76 | 78.7 |
| Perf / dollar | 35.3 | 14 |
| GPQA Diamond | 91.2 | 88 |
| SWE-Bench Verified | 45 vendor | 75 |
| Humanity's Last Exam | 54.7 | 40.2 |
| ARC-AGI 2 | 30 vendor | 50 |
| AIME 2025 | 70 vendor | 95.5 |
| MMMLU | 80 vendor | 88 |
| BFCL | 70 vendor | 85 |
| HumanEval | 84 vendor | 94.5 |
| MATH 500 | 76 vendor | 92 |
| Terminal-Bench 2.1 | 81 | — |
| MCP Atlas | 77 | — |
| AIME 2026 | 99.2 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 52.6 | 53.1 |
| AA Agentic Index | 45.7 | 44.2 |
| AA-Omniscience Index (−100–100) | 4.4 | 5.8 |
| LMSYS Chatbot Arena | 1469.4 ELO | 1465.5 ELO |
| GDPval-AA v2 | 1506.1 ELO | — |
| Providers | ||
| Available from |
Fireworks — $1.40/$4.40/Mtok
Together — $1.40/$4.40/Mtok
Z.AI — $1.40/$4.40/Mtok
|
OpenAI — $2.50/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GLM-5.2 | GPT-5.4 | Savings |
|---|---|---|---|
| 1M tokens | $2.15 | $5.63 | $3.48 (61.9%) |
| 10M tokens | $21.5 | $56.25 | $34.75 (61.8%) |
| 100M tokens | $215 | $562.5 | $347.5 (61.8%) |
| 1000M tokens | $2150 | $5625 | $3475 (61.8%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $2.15/Mtok blended vs $5.63 — 61.8% less on the same 50/50 token mix
- you want open weights — self-host it, fine-tune it, or exit the API entirely; GPT-5.4 is closed
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.250/Mtok — 90% off its list input price
- raw capability matters more than price: 78.7 vs 76 average benchmark score
The cheaper option here — GLM-5.2 costs $2.15/Mtok blended on Z.AI.
Summary
GLM-5.2 by Z.AI costs $1.40/Mtok input and $4.40/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
GPT-5.4 by OpenAI costs $2.50/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, GLM-5.2 is 61.8% cheaper than GPT-5.4.
On benchmarks, GPT-5.4 scores higher (78.7 vs 76) on average. In terms of value, GLM-5.2 has better performance per dollar (35.3 vs 14).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.