impulse

GLM 4.6

Open weights

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex…

API id glm-4.6Released 30 Sep 2025 (Sep 2025)
Input / 1M
$0.60
at Z.ai
Output / 1M
$2.20
at Z.ai
Context window
200K
tokens
Max output
128K
tokens per reply
Hosts
8
8 listings
Released
Sep 2025
30 Sep 2025

Pricing

List prices at Z.ai, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.60$2.20
Cached input
82% off input
$0.11
Cache write, 5 minutes$0.00

What it costs a month

At Z.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$301
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$250
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$440
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,968
Use your own numbers

Where to run it

8 hosts serve GLM 4.6. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Z.aiLab API
glm-4.6
$0.60 / $2.20
glm-4.6
$0.45 / $1.80
−21% vs headline
DeepInfraInference
GLM-4.6
$0.50 / $2.00
−12% vs headline
GMI CloudInference
GLM-4.6
$0.60 / $2.00
−5% vs headline
Fireworks AIInference
glm-4p6
$0.55 / $2.19
−4% vs headline
Novita AIInference
glm-4.6
$0.55 / $2.20
−4% vs headline
BasetenInference
GLM-4.6
$0.60 / $2.20
Together AIInference
GLM-4.6
$0.60 / $2.20

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching
Open weights
License: MIT
Runs in about 856.3 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • Vercel AI Gateway
    glm-4.6
    $0.45 / $1.80
    21% less
  • DeepInfra
    GLM-4.6
    $0.50 / $2.00
    13% less
  • GMI Cloud
    GLM-4.6
    $0.60 / $2.00
    5% less
  • Fireworks AI
    glm-4p6
    $0.55 / $2.19
    4% less
  • Novita AI
    glm-4.6
    $0.55 / $2.20
    4% less

Smaller Zhipu AI models

No cheaper Zhipu AI model keeps its key capabilities.

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    15% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    54% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    80% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    80% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    13% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    14% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    21% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    31% less

Model line

Newer and older versions, at each lab's own price.

  1. Aug 2026GLM 5.3Latest$1.40 / $4.40
  2. Aug 2026GLM5.3$1.34 / $4.15
  3. Jun 2026GLM 5.2$1.40 / $4.40
  4. Apr 2026GLM 5.1$1.40 / $4.40
  5. Feb 2026GLM 5$1.00 / $3.20
  6. UndatedGLM 4.7.251222Not listed
  7. Dec 2025GLM 4.7$0.60 / $2.20
  8. Sep 2025GLM 4.6This page$0.60 / $2.20

Call it

Using Z.ai's API.

Python
from litellm import completion

response = completion(
    model="zai/glm-4.6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 4.6 cost?

On Z.ai, GLM 4.6 costs $0.60 per million input tokens and $2.20 per million output tokens. Cached input costs $0.11 per million tokens. The cheapest host is Vercel AI Gateway, at $0.45 per million input tokens and $1.80 per million output tokens.

Which APIs offer GLM 4.6?

GLM 4.6 runs on 8 APIs: Z.ai, Vercel AI Gateway, DeepInfra, GMI Cloud, Fireworks AI, Novita AI, Baseten and Together AI.

What is GLM 4.6's context window?

200K tokens, with up to 128K tokens in one reply.

Is GLM 4.6 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of GLM 4.6?

Yes. GLM 5.3 is the newest model in this line, released on 18 Aug 2026.

What are cheaper alternatives to GLM 4.6?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (15% less), GPT-5.4 Nano on OpenAI (54% less) and Motif 3 on ai& (13% less). GLM 4.6 itself costs 21% less on Vercel AI Gateway. Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 4.6 released?

Zhipu AI released it on 30 Sep 2025.

What is GLM 4.6's API model id?

Use glm-4.6 with Z.ai. Other hosts use their own ids: GLM-4.6 on DeepInfra, GLM-4.6 on GMI Cloud, glm-4p6 on Fireworks AI, GLM-4.6 on Baseten.

Sources

Raw catalog entry for glm-4.6 on Z.ai
{
  "cache_creation_input_token_cost": 0,
  "cache_read_input_token_cost": 1.1e-7,
  "input_cost_per_token": 6e-7,
  "output_cost_per_token": 0.0000022,
  "litellm_provider": "zai",
  "max_input_tokens": 200000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_tool_choice": true,
  "source": "https://docs.z.ai/guides/overview/pricing"
}