Skip to content
OpenKey

GLM 5

Z.aiReleased Feb 11, 2026

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Context window
203K tokens
Input
text
Output
text
Tokenizer
Other
Released
Feb 11, 2026
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.600$0.018$0.618
Output$1.92$0.058$1.98
Cache read$0.120$0.0036$0.124

Benchmarks

Design Arena

CategoryEloWin rateRank
androidnativeagents124462%#6
Full-stackagents119052.8%#13
godotgamedevagents123754.8%#3
Mobile appsagents122253.1%#10
3Dmodels130756.8%#15
ASCII artmodels119247.7%#26
Codemodels129555.6%#16
Data vizmodels126952.9%#22
Game devmodels129957.4%#15
SVGmodels122554.4%#19
UI componentsmodels128754.1%#21
Websitesmodels129055.1%#18

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • reasoning
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model z-ai/glm-5.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="z-ai/glm-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "z-ai/glm-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GLM 5 cost via API?
Through OpenKey, GLM 5 costs $0.618 per 1M input tokens and $1.98 per 1M output tokens. That is the provider price ($0.600 / $1.92) plus a flat 3% fee — nothing else.
What is GLM 5's context window?
GLM 5 accepts up to 203K tokens of context.
Is GLM 5 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "z-ai/glm-5" using any OpenAI SDK — only the base URL and API key change.
What inputs does GLM 5 support?
GLM 5 accepts text input and produces text output.

More from Z.ai

All Z.ai models →