OpenAI compatible API · Attested · Public status

LGAI-EXAONE/K-EXAONE-236B-A23B vs Z.ai: GLM 5.2

LGAI-EXAONE/K-EXAONE-236B-A23B vs Z.ai: GLM 5.2: compare current API pricing, context, provider routes, privacy, p50 latency, and OpenAI-compatible access.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Compare routesProviders, price, context, and policy posture in one view.

Use auto when uptime mattersKeep a primary model and let fallback handle provider failures.

Same API shapeUse the OpenAI client and set the model you want.

Practical read

LGAI-EXAONE/K-EXAONE-236B-A23B has the lower cheapest prompt+completion route on TrustedRouter. Z.ai: GLM 5.2 has more provider fallback routes, while Z.ai: GLM 5.2 has the larger context window. Current TrustedRouter probes show Z.ai: GLM 5.2 with the lower p50 TTFT.

$1.05/1MLGAI-EXAONE/K-EXAONE-236B-A23B cheapest route

$2.289/1MZ.ai: GLM 5.2 cheapest route

2507 msLGAI-EXAONE/K-EXAONE-236B-A23B fastest measured p50 TTFT via friendli

1210 msZ.ai: GLM 5.2 fastest measured p50 TTFT via digitalocean

LGAI-EXAONE/K-EXAONE-236B-A23BZ.ai: GLM 5.2

Model idlgai-exaone/k-exaone-236b-a23bz-ai/glm-5.2

Publisher FriendliAI Z.AI

AI IQ — IQ 120#16

Context262,144 tokens1,048,576 tokens

Provider routes247

Cheapest route$1.05/1M$2.289/1M

Privacy postureprovider posture varieshas provider E2EE route

Fastest measured p50 TTFT2507 ms via friendli1210 ms via digitalocean

Highest measured throughputnot enough data207 tok/s via wafer

Recent route uptime range100.00%0.00% to 100.00%

Modes chat chat

LGAI-EXAONE/K-EXAONE-236B-A23B routes

Overview2 endpoints
PricingPrompt and completion rates
ProvidersAll serving providers

Z.ai: GLM 5.2 routes

Overview47 endpoints
PricingPrompt and completion rates
BenchmarksTrustedRouter and external sources
ProvidersAll serving providers

Related comparisons

Browse every comparison

MoonshotAI: Kimi K3 vs Z.ai: GLM 5.280 combined provider routes
MoonshotAI: Kimi K2.6 vs Z.ai: GLM 5.277 combined provider routes
DeepSeek: DeepSeek V4 Flash 0423 vs Z.ai: GLM 5.276 combined provider routes
DeepSeek: DeepSeek V4 Pro vs Z.ai: GLM 5.274 combined provider routes
OpenAI: gpt-oss-120b vs Z.ai: GLM 5.273 combined provider routes
Google: Gemma 4 31B vs Z.ai: GLM 5.271 combined provider routes
Z.ai: GLM 5.1 vs Z.ai: GLM 5.271 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs Z.ai: GLM 5.267 combined provider routes

Production choice

Pick a default model. Keep fallback enabled.

TrustedRouter is useful when you know the model you want, but still need provider rollover, budget limits, usage records, and a prompt path you can verify.

OpenAI clientPython

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-..."
)

response = client.chat.completions.create(
    model="lgai-exaone/k-exaone-236b-a23b",
    messages=messages,
)

Questions

Which should I use, LGAI-EXAONE/K-EXAONE-236B-A23B or Z.ai: GLM 5.2?

Is LGAI-EXAONE/K-EXAONE-236B-A23B or Z.ai: GLM 5.2 cheaper?

The current cheapest TrustedRouter route is $1.05/1M for LGAI-EXAONE/K-EXAONE-236B-A23B and $2.289/1M for Z.ai: GLM 5.2. The comparison uses current catalog prices and updates as provider pricing changes.

Is LGAI-EXAONE/K-EXAONE-236B-A23B or Z.ai: GLM 5.2 faster?

Current measured p50 time to first token is 2507 ms for LGAI-EXAONE/K-EXAONE-236B-A23B and 1210 ms for Z.ai: GLM 5.2. These are routed probe measurements, not vendor-advertised speeds, and update as new samples arrive.

Can I test LGAI-EXAONE/K-EXAONE-236B-A23B and Z.ai: GLM 5.2 with the same API?

Yes. Use the same OpenAI-compatible TrustedRouter base URL and API key, then change only the model id between lgai-exaone/k-exaone-236b-a23b and z-ai/glm-5.2. This makes side-by-side evals possible without maintaining two provider integrations.