GLM 4.6 with Jev
GLM 4.6 is a model from Z.ai, released 2025-09-30. It costs $0.430 per million input tokens and $1.75 per million output tokens, reads up to 205K tokens of context, and writes up to 16,384 tokens in one reply. Through llm11, set model to z-ai/glm-4.6.
- Input price
- $0.430 / 1M
- Output price
- $1.75 / 1M
- Context window
- 205K tokens
- Max output
- 16K tokens
- Cached input
- $0.080 / 1M
- Released
- 2025-09-30
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 48% of the 332 priced models we can call cost more.
Using GLM 4.6 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. GLM 4.6 does the answering when Jev sends it work, or when you name it yourself. At list price GLM 4.6 falls in the llm11-balanced band, but no pack routes to it because Z.ai is not one of the labs the packs draw from. You can still pin it: pass z-ai/glm-4.6 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for GLM 4.6 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00056 | $0.565 |
| Question over retrieved documents | 4,000 / 500 | $0.00260 | $2.60 |
| Long document summary | 30,000 / 1,000 | $0.015 | $14.65 |
Cheaper models to try
The catalogue has no benchmark score for GLM 4.6, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Mistral Large 3 2512 | $0.500 | $1.50 | 262K | |
| Qwen Qwen3 VL 30B A3B ThinkingRetires 2026-10-09 | $0.200 | $2.40 | 262K | |
| Qwen Qwen3 30B A3B Thinking 2507Retires 2026-10-09 | $0.200 | $2.40 | 82K | |
| Qwen Qwen3 235B A22B Thinking 2507Retires 2026-10-09 | $0.230 | $2.30 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="z-ai/glm-4.6",
messages=[{"role": "user", "content": "Hello"}],
)More from Z.ai
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GLM 5.3 Prime | $2.80 | $8.80 | 1M | |
| GLM 5.3 FlashX | $0.370 | $1.25 | 1.05M | |
| GLM 5.3 Flash | $0.150 | $0.500 | 1.31M | |
| GLM 5.3 | $0.190 | $4.00 | 1.31M | |
| GLM 5.2 | $0.234 | $4.40 | 1.05M | |
| GLM 5.1 | $0.965 | $3.03 | 205K |
Questions
- What is GLM 4.6 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. GLM 4.6 does the answering when Jev sends it work, or when you name it yourself. At list price GLM 4.6 falls in the llm11-balanced band, but no pack routes to it because Z.ai is not one of the labs the packs draw from. You can still pin it: pass z-ai/glm-4.6 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is GLM 4.6 a System One model?
- No. GLM 4.6 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does GLM 4.6 cost?
- $0.430 per million input tokens and $1.75 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00260, so a thousand of them is about $2.60. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the GLM 4.6 context window?
- 204,800 tokens, with up to 16,384 tokens in a single reply.
- Does GLM 4.6 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use GLM 4.6 through llm11?
- Yes. Set model to z-ai/glm-4.6 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to GLM 4.6?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price GLM 4.6 falls in the llm11-balanced band, but no pack routes to it because Z.ai is not one of the labs the packs draw from. You can still pin it: pass z-ai/glm-4.6 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to GLM 4.6?
- Nearest in price and below it: Mistral Mistral Large 3 2512 at $0.500 in and $1.50 out, Qwen Qwen3 VL 30B A3B Thinking at $0.200 in and $2.40 out and Qwen Qwen3 30B A3B Thinking 2507 at $0.200 in and $2.40 out. The catalogue has no benchmark score for GLM 4.6, so this is a price ordering. It does not claim these answer as well.