impulse

GLM 5 Turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios.

API id glm-5-turboReleased 15 Mar 2026 (Mar 2026)
Input / 1M
$1.20
at Novita AI
Output / 1M
$4.00
at Novita AI
Context window
203K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
Mar 2026
15 Mar 2026

Pricing

List prices at Novita AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.20$4.00
Cached input
80% off input
$0.24

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$574
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$490
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$874
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,840
Use your own numbers

Where to run it

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

HostIn / out per 1M
Novita AIInference
glm-5-turbo
$1.20 / $4.00

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

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

No host sells it for less than Novita AI.

Smaller Zhipu AI models

No cheaper Zhipu AI model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    11% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    21% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    34% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    89% less

Open-weight picks

  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    9% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    55% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    58% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    64% less

Call it

Using Novita AI's API.

Python
from litellm import completion

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

Quick answers

How much does GLM 5 Turbo cost?

On Novita AI, GLM 5 Turbo costs $1.20 per million input tokens and $4.00 per million output tokens. Cached input costs $0.24 per million tokens.

Which APIs offer GLM 5 Turbo?

GLM 5 Turbo runs on 1 API: Novita AI.

What is GLM 5 Turbo's context window?

203K tokens, with up to 131K tokens in one reply.

Is GLM 5 Turbo being retired?

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

What are cheaper alternatives to GLM 5 Turbo?

Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (11% less), Gemini 3.8 Flash on Google AI Studio (21% less) and Inkling on DeepInfra (9% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GLM 5 Turbo released?

Zhipu AI released it on 15 Mar 2026.

What is GLM 5 Turbo's API model id?

Use glm-5-turbo with Novita AI.

Sources

Raw catalog entry for glm-5-turbo on Novita AI
{
  "cache_read_input_token_cost": 2.4e-7,
  "input_cost_per_token": 0.0000012,
  "litellm_provider": "novita",
  "max_input_tokens": 202800,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 0.000004,
  "source": "https://api.novita.ai/v3/openai/models",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false
}