impulse

GLM 5.1

Open weights

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.

API id glm-5.1Released 7 Apr 2026 (Apr 2026)
A newer model in this line is out: GLM 5.3, released 18 Aug 2026.
FriendliAI retires it on 20 Nov 2026 (in 2 days). 13 hosts keep serving it.
Input / 1M
$1.40
at Z.ai
Output / 1M
$4.40
at Z.ai
Context window
200K
tokens
Max output
128K
tokens per reply
Hosts
14
15 listings
Released
Apr 2026
7 Apr 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$1.40$4.40
Cached input
81% off input
$0.26
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$647
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$557
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$986
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$4,416
Use your own numbers

Where to run it

14 hosts serve GLM 5.1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Z.aiLab API
glm-5.1
$1.40 / $4.40
glm-5-1
$0.825 / $3.30
−33% vs headline
DeepInfraInference
GLM-5.1
$1.05 / $3.50
−23% vs headline
Novita AIInference
glm-5.1
$1.38 / $4.40
−1% vs headline
glm-5.1
$1.40 / $4.40
glm-5.1
$1.40 / $4.40
Qwen CloudLab API
glm-5.1
$1.40 / $4.40
glm-5.1
$1.40 / $4.40
FriendliAIInference
GLM-5.1
$1.40 / $4.40
Retires 20 Nov 2026
GLM-5.1
$1.40 / $4.40
Together AIInference
GLM-5.1
$1.40 / $4.40
GMI CloudInference
GLM-5.1-FP8
$1.40 / $4.40
Fireworks AIInference
glm-5p1
$1.40 / $4.40
glm-5.1
$1.89 / $5.94
+35% vs headline
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
glm-5p1
$1.40 / $4.40

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

  • EmpirioLabs AI
    glm-5-1
    $0.825 / $3.30
    33% less
  • DeepInfra
    GLM-5.1
    $1.05 / $3.50
    23% less

Smaller Zhipu AI models

  • GLM 5v Turbo
    Zhipu AI · on Z.ai
    $1.20 / $4.00
    Has every key capability
    12% less

Other frontier labs

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    7% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    30% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    42% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    91% less

Open-weight picks

  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    7% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    20% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    60% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    63% 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 5.1This page$1.40 / $4.40
  4. Feb 2026GLM 5$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-5.1",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 5.1 cost?

On Z.ai, GLM 5.1 costs $1.40 per million input tokens and $4.40 per million output tokens. Cached input costs $0.26 per million tokens. The cheapest host is EmpirioLabs AI, at $0.825 per million input tokens and $3.30 per million output tokens.

Which APIs offer GLM 5.1?

GLM 5.1 runs on 14 APIs: Z.ai, EmpirioLabs AI, DeepInfra, Novita AI, Alibaba DashScope, Qianwen AI Platform, Qwen Cloud, StreamLake, FriendliAI and 5 more.

What is GLM 5.1's context window?

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

Is GLM 5.1 being retired?

FriendliAI retires it on 20 Nov 2026. 13 hosts keep serving it.

Is there a newer version of GLM 5.1?

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

What are cheaper alternatives to GLM 5.1?

Models that cost less and keep most of what it can do: GLM 5v Turbo on Z.ai (12% less), GPT-6.1 Terra on OpenAI (7% less), Gemini 3.8 Flash on Google AI Studio (30% less) and Muse Spark Open on Baseten (7% less). GLM 5.1 itself costs 33% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 5.1 released?

Zhipu AI released it on 7 Apr 2026.

What is GLM 5.1's API model id?

Use glm-5.1 with Z.ai. Other hosts use their own ids: glm-5-1 on EmpirioLabs AI, GLM-5.1 on DeepInfra, GLM-5.1 on FriendliAI, GLM-5.1 on Nebius AI Studio.

Sources

Raw catalog entry for glm-5.1 on Z.ai
{
  "cache_creation_input_token_cost": 0,
  "cache_read_input_token_cost": 2.6e-7,
  "input_cost_per_token": 0.0000014,
  "output_cost_per_token": 0.0000044,
  "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"
}