GLM-5.2: API Pricing, Context Window & Benchmarks
GLM-5.2 is a language model from ZAI, released in June 2026, with a 1.0M-token context window, and pricing from $0.950/M input and $3.00/M output.
GLM-5.2 is Z.AI's flagship foundation model built for long-horizon tasks, delivering a solid 1M-token context that stably sustains long, messy coding-agent trajectories. It improves substantially over GLM-5.1, becoming the strongest
GLM-5.2 benchmarks
Rankings
Quality Tracker
GLM-5.2 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026GLM-5.2 pricing
Providers
GLM-5.2 starts at $0.950 per million input tokens and $3.00 per million output tokens via DeepInfra. See all 6 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.950 | $3.00 | $1.25 | 1.0M/131.1K | 2.23/21.99 | 79/5 | 100.00%(1,345) | / |
 Fireworks | $1.40 | $4.40 | $1.84 | 1.0M/131.1K | 2.24/11.94 | 145/8 | 68.52%(486) | / |
 FriendliAI | $1.40 | $4.40 | $1.84 | 1.0M/131.1K | 1.74/5.83 | 233/14 | 99.53%(5,269) | / |
 Novita | $1.40 | $4.40 | $1.84 | 1.0M/131.1K | 6.95/22.16 | 58/5 | 48.34%(391) | / |
 Together | $1.40 | $4.40 | $1.84 | 1.0M/131.1K | 0.85/5.14 | 227/22 | 84.90%(1,477) | / |
 ZAI | $1.40 | $4.40 | $1.84 | 1.0M/128.0K | 0.00/0.00 | —/— | 0.00%(278) | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
GLM-5.2 model size
GLM-5.2 has 753 billion parameters. See how it compares to other models in the same parameter range.
GLM-5.2 context window
Input and output token limits for GLM-5.2, plus how it ranks on long-context understanding.
GLM-5.2 API
Run a request to see the response
Use it in your code
Billed at $0.95 input / $3.00 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="glm-5.2",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
GLM-5.2 latency
GLM-5.2 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
GLM-5.2 examples
Recent arena outputs from GLM-5.2, picked from the highest-ranked matchups.
GLM-5.2 license
GLM-5.2 is released under the MIT license, which permits commercial use, has 753.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 753.0B
MIT License - allows commercial use
GLM-5.2 resources
Official sources for GLM-5.2: api documentation, official playground, paper or system card, official launch post, source repository, model weights.
GLM-5.2 vs other models
The most-compared alternatives to GLM-5.2 are GLM-5.1, Claude Opus 4.6, Gemini 3 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GLM-5.2
Models ranked just above and below GLM-5.2 by LLM Stats score.
FAQ
Common questions about GLM-5.2.