
Provider pricing hub
GLM API pricing: Z.ai GLM-5.3, Flash and earlier models.
Z.ai's GLM API on RouterPlex costs $1.40 per 1M input tokens and $4.40 output for GLM-5.3, and $0.15/$0.50 for GLM-5.3 Flash, with 0% markup. The Flash launch promotion has ended. One key, no Z.ai account. Top-ups have a $0 fee, by card from $5 or crypto; balances stop at $0 and each key has a hard USD cap.
Prices checked 17 November 2026 from the live catalog. Z.ai's pricing page last checked 10 Nov 2026: docs.z.ai/guides/overview/pricing
8
Routes
$0.15
Cheapest input / 1M
Z.ai GLM family
Published catalog rates.
Agent-turn cost uses 100K input and 10K output. The catalog files Z.ai models under Zhipu.
| Model route | Context | Input / 1M | Cached input / 1M | Output / 1M | Agent turn |
|---|---|---|---|---|---|
GLM-4.7 Flash Abliterated glm-4.7-flash-abliterated | 200K | $0.12 | $0.09 | $0.60 | $0.018 |
| An abliterated build of Z.ai's GLM-4.7 Flash: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms. | |||||
GLM-5.3 Flash glm-5.3-flash | 1M | $0.15 | $0.03 | $0.50 | $0.020 |
| Z.ai ran a launch promotion at $0.075 input / $0.25 output per 1M tokens through September 9, 2026. RouterPlex bills the standard published list rate of $0.15 input / $0.50 output. | |||||
GLM-5.3 Flash Abliterated glm-5.3-flash-abliterated | 1M | Was $0.50, now $0.25, 50% off | Was $0.30, now $0.06, 80% off | Was $1.60, now $1.00, 38% off | $0.035 |
| An abliterated build of Z.ai's GLM-5.3 Flash: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms. | |||||
GLM-5.3 FlashX glm-5.3-flashx | 1M | $0.37 | $0.03 | $1.25 | $0.050 |
GLM-5.1 glm-5.1 | 256K | $1.40 | not offered | $4.40 | $0.18 |
GLM-5.2 glm-5.2 | 1M | $1.40 | $0.225 | $4.40 | $0.18 |
GLM-5.3 glm-5.3 | 1M | $1.40 | $0.26 | $4.40 | $0.18 |
GLM-5.3 Abliterated glm-5.3-abliterated | 1M | Was $4.00, now $2.00, 50% off | Was $0.70, now $0.30, 57% off | Was $6.00, now $4.00, 33% off | $0.24 |
| An abliterated build of Z.ai's GLM-5.3: the open weights with the refusal behaviour removed, served on RouterPlex through a third-party host. This is not the vendor's own model or price -- RouterPlex sets this rate. The model will answer requests the original declines, so you are responsible for how you use it under the RouterPlex terms. | |||||
GLM-4.7 Flash Abliterated, GLM-5.3 Flash Abliterated and GLM-5.3 Abliterated are third-party builds with a RouterPlex-set rate, not the vendor's list price, so they are left out of the price ranges, picks and FAQ answers on this page.
GLM pricing calculator
Same workload. Every GLM route.
Defaults are a 10K-in / 1K-out request, 3,000 times a month. Switch to the 100K / 10K agent turn for a coding loop, and set a cached share if your prompts repeat a long prefix.
Workload calculator
Catalog rates · USD · no markup
Share of each prompt that repeats a recent prefix (system prompt, files) and bills at the cached-input rate. Routes with no cached rate bill it as normal input.
Models in the estimate
4 selected| Route | Per request | Monthly | $100 buys |
|---|---|---|---|
| GLM-5.3 Flash Zhipu | $0.0020 | $6.00 | 50,000 req |
| GLM-5.3 FlashX Zhipu | $0.0050 | $14.85 | 20,202 req |
| GLM-5.2 Zhipu | $0.018 | $55.20 | 5,434 req |
| GLM-5.3 Zhipu | $0.018 | $55.20 | 5,434 req |
Estimates apply live catalog rates, including cached input, and switch to a route's long-context rate when the prompt reaches its threshold. Actual spend follows the tokens your client sends and the model returns. Image-generation routes are omitted because they are not a chat turn.
Z.ai vs RouterPlex
What Z.ai's own pages say, and what changes here.
Checked 2026-11-10 on docs.z.ai/guides/overview/pricing
- 01Z.ai's published input and output prices for GLM-5.3 Flash, GLM-5.2 and GLM-5.3 match the RouterPlex rates in the table above.
- 02Z.ai lists GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash as free on its own platform. They are not RouterPlex routes.
- 03Z.ai also sells the GLM Coding Plan, a monthly subscription for coding tools listed from $18/month on its quick start page. RouterPlex has no subscription: pay per token from a prepaid balance.
Call it
Use GLM from Claude Code or the OpenAI SDK.
Claude Code and the Anthropic SDK use https://api.routerplex.com. The OpenAI SDK, Cursor and Cline use https://api.routerplex.com/v1. Same key, same catalog id, same per-key budget. Swap glm-5.3-flash for any id in the table.
export ANTHROPIC_BASE_URL=https://api.routerplex.comexport ANTHROPIC_AUTH_TOKEN="$ROUTERPLEX_API_KEY"export ANTHROPIC_MODEL=glm-5.3-flashclaude
import osfrom openai import OpenAIclient = OpenAI(base_url="https://api.routerplex.com/v1",api_key=os.environ["ROUTERPLEX_API_KEY"],)reply = client.chat.completions.create(model="glm-5.3-flash",messages=[{"role": "user", "content": "Hello!"}],)print(reply.choices[0].message.content)
How to pick
GLM-5.3 or Flash: cost per turn.
These notes only use catalog fields: price, context, and mode. They are not quality rankings.
Cheapest per agent turn
GLM-5.3 Flash costs about $0.020 for a 100K-in / 10K-out turn at $0.15 / $0.50 per 1M.
Flash is the volume route
GLM-5.3 costs about 9.2x GLM-5.3 Flash per agent turn. Start a Claude Code loop on Flash and move hard tasks up when your own evals say so.
No promo to expire
Z.ai ran a GLM-5.3 Flash launch promotion at $0.075 input / $0.25 output per 1M through September 9, 2026. It has ended; RouterPlex bills the standard rate, $0.15 / $0.50.
Setup notes for GLM-5.3 and Claude Code Router, plus the OpenAI-compatible API guide. Compare the rest of the catalog on all model pricing, the cheapest-first ledger, or RouterPlex vs OpenRouter.
Before you bill production
GLM pricing, in questions.
01How much does the GLM API cost?+
As of 17 November 2026, Z.ai GLM routes on RouterPlex cost $0.15 to $1.40 per 1M input tokens and $0.50 to $4.40 per 1M output tokens with 0% markup: GLM-5.3 Flash is $0.15 / $0.50, GLM-5.3 FlashX is $0.37 / $1.25, GLM-5.2 is $1.40 / $4.40 and GLM-5.3 is $1.40 / $4.40. Top-ups have a $0 fee and the balance stops at $0.
02Is GLM-5.3 Flash still on promotion?+
No. Z.ai ran a GLM-5.3 Flash launch promotion at $0.075 input / $0.25 output per 1M through September 9, 2026. It has ended; RouterPlex bills the standard rate, $0.15 / $0.50.
03GLM-5.3 or GLM-5.3 Flash: how big is the price gap?+
GLM-5.3 is $1.40 / $4.40 per 1M and GLM-5.3 Flash is $0.15 / $0.50, about $0.18 against $0.020 per 100K-in / 10K-out agent turn (9.2x). Both list 1M context. This page does not rank quality.
04How do I get a Z.ai GLM API key?+
On RouterPlex you do not need a Z.ai account: sign up, verify your email, and create a key in the dashboard (you can set a hard USD budget on it). Call https://api.routerplex.com/v1 with the OpenAI SDK, or point Claude Code at https://api.routerplex.com, with model "glm-5.3-flash". The same key reaches every other model in the catalog. If you want a direct Z.ai key instead, Z.ai's quick start says to register on the Z.ai Open Platform, top up on its billing page, and create a key on its API Keys page. (Source: docs.z.ai/guides/overview/quick-start, checked 2026-11-10.)
05Is there a free GLM API tier on RouterPlex?+
No. RouterPlex has no free tier. Eligible verified accounts get $1 of test credit once, no card, and it never expires. After that you top up from $5 by card, or with crypto, with a $0 top-up fee; the balance stops at $0, so a GLM loop cannot run up a bill. Z.ai's own price list shows GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash as free on its platform; those models are not RouterPlex routes. (Source: docs.z.ai/guides/overview/pricing, checked 2026-11-10.)
06Which GLM model id should I use?+
Send the catalog id exactly as written: "glm-5.3-flash" (GLM-5.3 Flash), "glm-5.3-flashx" (GLM-5.3 FlashX), "glm-5.2" (GLM-5.2) and "glm-5.3" (GLM-5.3). The cheapest per agent turn is "glm-5.3-flash". The page URL slug (for example /models/glm-5-3-flash) is not the API id; the id keeps its dots and case. Anything else returns model_not_found.
07How does GLM cache pricing work?+
Cached input is the part of a prompt the provider has already processed in a recent request with the same prefix, such as a long system prompt or a repeated file. It bills at the cached-input rate instead of the full input rate: $0.03 per 1M on GLM-5.3 Flash (input $0.15), $0.03 per 1M on GLM-5.3 FlashX (input $0.37), $0.225 per 1M on GLM-5.2 (input $1.40) and $0.26 per 1M on GLM-5.3 (input $1.40). Set a cached share in the calculator above to see the effect.
08What is the GLM Coding Plan, and how is it different?+
The GLM Coding Plan is Z.ai's monthly subscription for coding tools, listed "from $18/month", and it uses its own dedicated endpoint. RouterPlex is pay per token from a prepaid balance with no subscription. (Source: docs.z.ai/guides/overview/quick-start, checked 2026-11-10.)
09Does GLM-5.3 work in Claude Code?+
Yes. Set ANTHROPIC_BASE_URL to https://api.routerplex.com, use your RouterPlex key as ANTHROPIC_AUTH_TOKEN, and set ANTHROPIC_MODEL to "glm-5.3" or "glm-5.3-flash". The OpenAI SDK uses https://api.routerplex.com/v1 with the same key.
Route GLM from one balance
Try GLM-5.3 Flash in Claude Code with $1, no card.
Try it with $1 of test credit, no card. Guided setup shows the exact Claude Code config for GLM-5.3 Flash.
Eligible verified accounts get the $1 once. It never expires.