Last updated: October 20, 2026 · Prices checked against Z.ai's list prices (via the LiteLLM price file) and Oxyy's live GLM pricing page on this date.
Disclosure: This guide is published by the Oxyy.ai team. Z.ai prices are Z.ai's own list prices; Oxyy is an independent gateway, not affiliated with Z.ai.
Quick answer: On Z.ai (Zhipu AI's international platform), GLM-5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens, and GLM-5.3-Flash costs $0.15 / $0.50. On Oxyy.ai the same models currently cost $0.56 / $1.76 and $0.06 / $0.20, a 60% discount. That's cheaper than every third-party GLM-5.3 host we checked, where the lowest price was $0.98 / $3.08.
| GLM model | Z.ai official (input / output per 1M) | Oxyy.ai 60% off | Cached input (Z.ai → Oxyy) | Context |
|---|---|---|---|---|
GLM-5.3 (glm-5.3) | $1.40 / $4.40 | $0.56 / $1.76 | $0.26 → $0.104 | 1M |
GLM-5.3-Flash (glm-5.3-flash) | $0.15 / $0.50 | $0.06 / $0.20 | $0.03 → $0.012 | 1M |
GLM-5.3-FlashX (glm-5.3-flashx) | $0.37 / $1.25* | $0.148 / $0.50 | → $0.030 | — |
GLM-5.2 (glm-5.2) | $1.40 / $4.40* | $0.56 / $1.76 | → $0.104 | 1.05M |
GLM-5 (glm-5) | $1.00 / $3.20* | $0.40 / $1.28 | → $0.080 | 200K |
| GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash | Free on Oxyy | |||
*Standard price as listed by Oxyy. GLM-5.3 and GLM-5.3-Flash official rates confirmed against Z.ai's list price in the LiteLLM price file. Oxyy prices from oxyy.ai/zai, checked October 20, 2026; the 60% discount is a current launch promotion.
Key Takeaways
- GLM-5.3 is Z.ai's flagship: $1.40 / $4.40 per 1M tokens, 1M-token context, up to 128K output tokens.
- GLM-5.3-Flash is the budget workhorse at $0.15 / $0.50, also with a 1M context.
- Oxyy charges 40% of standard price on 23 GLM models, plus free access to GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash.
- Oxyy beats every third-party host we checked. The cheapest other GLM-5.3 hosts (Sail, SCX.ai) charge $0.98 / $3.08; Oxyy charges $0.56 / $1.76.
- Cached input is cheap: $0.104 per 1M on GLM-5.3 through Oxyy, versus $0.26 on Z.ai.
- Oxyy lists 30 Z.ai models in total, including GLM image, OCR, speech-to-text and video models, all on one API key.
What Is GLM (Zhipu AI / Z.ai)?
GLM is the large language model family from Zhipu AI, sold internationally under the Z.ai brand. GLM models are open-weight, strong at coding and agentic tool use, and among the most cost-efficient models with a 1M-token context window. GLM-5.3 was released on August 14, 2026, and GLM-5.2 on June 16, 2026.
GLM-5.3 API Pricing
GLM-5.3 supports function calling, parallel tool calls, structured output, image input, reasoning, prompt caching and web search, with a 1,000,000-token context window and up to 128,000 output tokens.
GLM-5.3 Price by Provider (per 1M tokens)
| Provider | Input | Output | Cache read |
|---|---|---|---|
| Oxyy.ai | $0.56 | $1.76 | $0.104 |
| Sail | $0.98 | $3.08 | $0.18 |
| SCX.ai | $0.98 | $3.08 | $0.18 |
| CoralBricks | $1.12 | $4.40 | $0 |
| AIHubMix | $1.127 | $3.944 | $0.2817 |
| FriendliAI | $1.26 | $3.96 | $0.234 |
| Z.ai (official) | $1.40 | $4.40 | $0.26 |
| Fireworks, Together, Novita, Databricks, Baseten, Nebius | $1.40 | $4.40 | $0.14–$0.26 |
| Amazon Bedrock (global cross-region) | $1.68 | $5.28 | $0.312 |
| Inference APIs | $1.82 | $5.72 | $0.34 |
Third-party prices from the LiteLLM model price file, updated October 15, 2026. Oxyy price from oxyy.ai/zai, October 20, 2026.
GLM-5.3-Flash API Pricing
GLM-5.3-Flash is built for high-volume, low-latency work: coding sub-tasks, classification, extraction and chat. It has a 1,048,576-token context window and supports function calling, image and video input, reasoning and caching.
| Provider | Input | Output | Cache read |
|---|---|---|---|
| Oxyy.ai | $0.06 | $0.20 | $0.012 |
| Sail | $0.11 | $0.35 | $0.02 |
| AIHubMix | $0.1127 | $0.3944 | $0.02817 |
| Z.ai (official) | $0.15 | $0.50 | $0.03 |
| Inference APIs | $0.20 | $0.66 | $0.04 |
Full GLM Price List on Oxyy (Text Models)
| Model | Standard input / output | Oxyy input / output (per 1M) |
|---|---|---|
| GLM-5.3 | $1.40 / $4.40 | $0.56 / $1.76 |
| GLM-5.2 | $1.40 / $4.40 | $0.56 / $1.76 |
| GLM-5.1 | $1.40 / $4.40 | $0.56 / $1.76 |
| GLM-5-Code | $1.20 / $5.00 | $0.48 / $2.00 |
| GLM-5-Turbo | $1.20 / $4.00 | $0.48 / $1.60 |
| GLM-5 | $1.00 / $3.20 | $0.40 / $1.28 |
| GLM-5.3-FlashX | $0.37 / $1.25 | $0.148 / $0.50 |
| GLM-5.3-Flash | $0.15 / $0.50 | $0.06 / $0.20 |
| GLM-4.7 | $0.60 / $2.20 | $0.24 / $0.88 |
| GLM-4.7-FlashX | $0.07 / $0.40 | $0.028 / $0.16 |
| GLM-4.5-X | $2.20 / $8.90 | $0.88 / $3.56 |
| GLM-4.5 | $0.60 / $2.20 | $0.24 / $0.88 |
| GLM-4.5-Air | $0.20 / $1.10 | $0.08 / $0.44 |
| GLM-4-32B-0414-128K | $0.10 / $0.10 | $0.04 / $0.04 |
| GLM-OCR | $0.03 / $0.03 | $0.012 / $0.012 |
| GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash | Free | |
Image and video models on Oxyy: CogView-4 at $0.004 per image, GLM-Image at $0.006 per image, CogVideoX-3 at $0.08 per generation. GLM-ASR-2512 speech-to-text is $0.012 (one rate for input and output).
Which GLM Model Should You Use?
| Need | Best pick | Price on Oxyy (per 1M) |
|---|---|---|
| Best quality for coding agents | GLM-5.3 | $0.56 / $1.76 |
| Cheapest capable coding model | GLM-5.3-Flash | $0.06 / $0.20 |
| Reasoning on a budget | GLM-4.7 | $0.24 / $0.88 |
| Long documents, lowest cost | GLM-4-32B-0414-128K | $0.04 / $0.04 |
| Images in, text out (OCR) | GLM-OCR | $0.012 / $0.012 |
| Prototyping for free | GLM-4.7-Flash | Free |
GLM API Cost Calculator: Monthly Examples
| Workload (per month) | GLM-5.3 on Z.ai | GLM-5.3 on Oxyy | You save |
|---|---|---|---|
| Chatbot: 10M input + 2M output | $22.80 | $9.12 | $13.68 |
| RAG app: 100M input + 10M output | $184.00 | $73.60 | $110.40 |
| Coding agent: 500M input + 20M output | $788.00 | $315.20 | $472.80 |
For the coding-agent workload, that's $5,673.60 saved per year on one seat. With prompt caching, the bill drops further: cached input on GLM-5.3 costs $0.104 per 1M on Oxyy.
How to Call GLM-5.3 Through Oxyy (3 Lines)
.env
OXYY_API_KEY=sk-oxyy-your-keyPython
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.oxyy.ai/v1", api_key=os.environ["OXYY_API_KEY"])
resp = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Refactor this function to be async."}],
)
print(resp.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.oxyy.ai/v1", apiKey: process.env.OXYY_API_KEY });
const resp = await client.chat.completions.create({
model: "glm-5.3-flash",
messages: [{ role: "user", content: "Summarize this log file." }],
});In Cline, Kilo Code, Zoo Code or any OpenAI-compatible tool: choose "OpenAI Compatible", set the base URL to https://api.oxyy.ai/v1, paste your Oxyy key and enter glm-5.3 as the model ID.
Why Use Oxyy for GLM?
- 60% off every GLM rate, including cached input (current launch promo; the discount changed from 70% to 60% on September 24, 2026)
- 30 Z.ai models on one key, plus GPT, Claude, Gemini, Grok, DeepSeek and Kimi
- 3 free GLM models for prototyping
- Prices checked daily and published on oxyy.ai/zai with a public price-change log
- No subscription, no minimum, credits never expire, and a free starting balance on signup
- OpenAI, Anthropic and Gemini SDKs work unchanged
Final Verdict
GLM-5.3 is already one of the best-value 1M-context models at Z.ai's $1.40 / $4.40 list price. Through Oxyy it costs $0.56 / $1.76, which is 43% less than the cheapest other third-party host we found and 60% less than Z.ai itself. For high-volume work, GLM-5.3-Flash at $0.06 / $0.20 is hard to beat.
Start using GLM-5.3 at 60% off with a free Oxyy balance →
Related: GLM-5.3 on Oxyy · GLM-5.3-Flash · DeepSeek API pricing · All Oxyy prices
Frequently Asked Questions
How much does the GLM API cost?
On Z.ai, GLM-5.3 costs $1.40 input and $4.40 output per 1M tokens, and GLM-5.3-Flash costs $0.15 / $0.50. On Oxyy, the same models currently cost $0.56 / $1.76 and $0.06 / $0.20.
What is the cheapest GLM-5.3 API provider?
Oxyy.ai, at $0.56 input and $1.76 output per 1M tokens during its current 60% promotion. The cheapest other third-party hosts we found, Sail and SCX.ai, charge $0.98 / $3.08.
Is the Zhipu AI API the same as Z.ai?
Yes. Z.ai is the international brand of Zhipu AI, the company behind the GLM model family.
Are there free GLM models?
Yes. GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash are free to call on Oxyy.
What is the context window of GLM-5.3?
GLM-5.3 has a 1,000,000-token context window and can return up to 128,000 tokens per response.
How much does cached input cost on GLM-5.3?
Cached input on GLM-5.3 costs $0.26 per 1M tokens on Z.ai and $0.104 per 1M tokens on Oxyy.
Can I use GLM with the OpenAI SDK?
Yes. Set the base URL to https://api.oxyy.ai/v1, use your Oxyy API key and pass a model ID such as glm-5.3 to the chat completions endpoint.
What is the difference between GLM-5.3 and GLM-5.3-Flash?
GLM-5.3 is the flagship model for the hardest coding and agent tasks. GLM-5.3-Flash is a faster, much cheaper model for high-volume work, at about a tenth of the price.
Is the Oxyy GLM discount permanent?
The 60% discount is a current launch promotion. Oxyy publishes a price-change log on its GLM page; the discount changed from 70% to 60% on September 24, 2026.
Can I use GLM-5.3 in Cline or Claude-style coding agents?
Yes. Any tool that supports an OpenAI-compatible endpoint can use GLM-5.3 through Oxyy by setting the base URL to https://api.oxyy.ai/v1 and the model ID to glm-5.3.