Price · per million tokens, USD
Get a key| Tokens | Z.ai list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $3.80 | — |
| Cached input | — | $0.80 | — |
| Output | — | $10.20 | — |
No list price on record.
Real-model check: Steady since Oct 20
GLM 5: what it is · from Z.ai’s own model card, read 2026-10-20
Z.ai’s GLM-5, built for complex systems engineering and long-horizon agent work. It scales GLM-4.5’s 355B parameters to 744B, trains on 28.5T tokens and uses DeepSeek Sparse Attention. It is served as glm-5 at $3.80 input and $10.20 output per million tokens, on the same key as every other model in the catalog.
| GLM 5 | |
|---|---|
| Developer | Z.ai |
| Parameters | 744B total, 40B active per token |
| Context | 202,752 tokens in its config |
| License | MIT |
| Published | 2026-02-11 |
| Downloads, 30 days to 2026-10-20 | 907,939 |
| Source | zai-org/GLM-5 |
From zai-org/GLM-5, read 2026-10-20.
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"glm-5","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'GLM 5 next to Z.ai’s other models · per million tokens, live
| Model | Here, in / out | 1,000 chat turns |
|---|---|---|
| GLM 5.3 FlashX | $0.0488 / $0.1625 | $0.18 |
| GLM 5.3 Flash | $0.09 / $0.15 | $0.26 |
| GLM-5.3 Flash Uncensored | $0.1086 / $0.3802 | $0.41 |
| GLM-4.7 Flash Uncensored | $0.12 / $0.60 | $0.54 |
| GLM 5.2 | $0.24 / $0.60 | $0.78 |
| GLM-5.3 Uncensored | $0.282 / $0.846 | $0.99 |
| GLM 5.3 | $0.3276 / $1.0296 | $1.17 |
| GLM 5.1 | $0.3824 / $1.2017 | $1.37 |
| GLM-5.3 Flash Cybersecurity | $0.525 / $1.75 | $1.93 |
| GLM-5.3 Flash Abliterated | $0.88 / $0.88 | $2.20 |
| GLM-5.3 Flash Apex Abliterated | $0.60 / $2.00 | $2.20 |
| GLM 4.5 Air | $0.56 / $3.44 | $2.84 |
| GLM 5.2 Uncensored | $1.095 / $4.68 | $4.53 |
| GLM-4.6 Derestricted v5 | $1.40 / $5.25 | $5.43 |
| GLM 4.7 Uncensored | $1.527 / $7.27 | $6.69 |
| GLM-5.3 Abliterated | $2.25 / $4.50 | $6.75 |
| GLM 5 | $3.80 / $10.20 | $12.70 |
| GLM-5.3 Flash Code Uncensored | $6.00 / $6.00 | $15.00 |
| GLM 5V Turbo | $4.80 / $16.00 | $17.60 |
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for GLM 5: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $3.80 input and $10.20 output per million tokens, that is $7.60 + $5.10 = $12.70, paid from prepaid credit with no subscription.
GLM 5 API key · base URL and setup
- Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
- Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
- Send glm-5 as the model. The same key calls every other model in the catalog.
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="glm-5",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'glm-5',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"glm-5","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from Z.ai
GLM 5 questions
GLM 5 is a model from Z.ai. Through UplinkSwitch it answers the OpenAI SDK on one key as glm-5.
$3.80 per million input tokens and $10.20 per million output tokens, with cached input at $0.80.
It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0089.
glm-5. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls GLM 5 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
Every day each model gets the same test prompt, and the results are public on /proof. GLM 5's latest result: Steady since Oct 20.
Yes: glm-5 on the OpenAI format at https://api.uplinkswitch.com/v1, $3.80 input and $10.20 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
744B total, 40B active per token, per zai-org/GLM-5.
202,752 tokens in its config, per zai-org/GLM-5.
Its weights are open on Hugging Face (zai-org/GLM-5); the license is MIT.
$1.27 for 100 chat turns of 2,000 input and 500 output tokens each, at $3.80 input and $10.20 output per million tokens, from prepaid credit with no subscription.
GLM-5 is the large 2026 flagship; GLM-4.5 Air is the compact 106B model from July 2025. GLM 5 is $3.80 / $10.20 per million tokens in / out, $12.70 for 1,000 chat turns; GLM 4.5 Air is $0.56 / $3.44 per million tokens in / out, $2.84 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.