impulse

GLM 5

Open weights

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.

API id glm-5Released 11 Feb 2026 (Feb 2026)
Input / 1M
$1.00
at Z.ai
Output / 1M
$3.20
at Z.ai
Context window
200K
tokens
Max output
128K
tokens per reply
Hosts
9
12 listings
Released
Feb 2026
11 Feb 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$1.00$3.20
Cached input
80% off input
$0.20
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$468
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$403
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$720
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,168
Use your own numbers

Where to run it

9 hosts serve GLM 5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Z.aiLab API
glm-5
$1.00 / $3.20
GMI CloudInference
GLM-5-FP8
$0.60 / $1.92
−40% vs headline
DeepInfraInference
GLM-5
$0.60 / $2.08
−37% vs headline
BasetenInference
GLM-5
$0.95 / $3.15
−3% vs headline
glm-5
$1.00 / $3.20
glm-5-maas
$1.00 / $3.20
zai.glm-5
$1.00 / $3.20
Together AIInference
GLM-5
$1.00 / $3.20
Novita AIInference
glm-5
$1.00 / $3.20
Show 3 more listings: regions, snapshots and variants
Amazon Bedrock
us-east-1
zai.glm-5
$1.00 / $3.20
us-west-2
zai.glm-5
$1.00 / $3.20
Mantle
zai.glm-5
$1.00 / $3.20

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 1809.3 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

  • GMI Cloud
    GLM-5-FP8
    $0.60 / $1.92
    40% less
  • DeepInfra
    GLM-5
    $0.60 / $2.08
    37% less
  • Baseten
    GLM-5
    $0.95 / $3.15
    3% less

Smaller Zhipu AI models

No cheaper Zhipu AI model keeps its key capabilities.

Other frontier labs

  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    3% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    19% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    70% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    87% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    44% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    45% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    49% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    56% less

Model line

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

  1. Aug 2026GLM 5.3Latest$1.40 / $4.40
  2. Jun 2026GLM 5.2$1.40 / $4.40
  3. Apr 2026GLM 5.1$1.40 / $4.40
  4. Feb 2026GLM 5This page$1.00 / $3.20
  5. UndatedGLM 4.7.251222Not listed
  6. Dec 2025GLM 4.7$0.60 / $2.20
  7. Sep 2025GLM 4.6$0.60 / $2.20
  8. Jul 2025GLM 4.5$0.60 / $2.20

Call it

Using Z.ai's API.

Python
from litellm import completion

response = completion(
    model="zai/glm-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 5 cost?

On Z.ai, GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens. Cached input costs $0.20 per million tokens. The cheapest host is GMI Cloud, at $0.60 per million input tokens and $1.92 per million output tokens.

Which APIs offer GLM 5?

GLM 5 runs on 9 APIs: Z.ai, GMI Cloud, DeepInfra, Baseten, StreamLake, Vertex AI, Amazon Bedrock, Together AI and Novita AI.

What is GLM 5's context window?

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

Is GLM 5 being retired?

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

Is there a newer version of GLM 5?

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

What are cheaper alternatives to GLM 5?

Models that cost less and keep most of what it can do: Gemini 3.8 Flash on Google AI Studio (3% less), Grok Build 0.1 on xAI (19% less) and Motif 3 on ai& (44% less). GLM 5 itself costs 40% less on GMI Cloud. Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 5 released?

Zhipu AI released it on 11 Feb 2026.

What is GLM 5's API model id?

Use glm-5 with Z.ai. Other hosts use their own ids: GLM-5-FP8 on GMI Cloud, GLM-5 on DeepInfra, GLM-5 on Baseten, glm-5-maas on Vertex AI.

Sources

Raw catalog entry for glm-5 on Z.ai
{
  "cache_creation_input_token_cost": 0,
  "cache_read_input_token_cost": 2e-7,
  "input_cost_per_token": 0.000001,
  "output_cost_per_token": 0.0000032,
  "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"
}