impulse

Fw Glm 5.2 Fast

API id FW-GLM-5.2-Fast
Input / 1M
$2.31
at Azure AI Foundry
Output / 1M
$7.26
at Azure AI Foundry
Context window
1M
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$2.31$7.26
Cached input
90% off input
$0.231

What it costs a month

At Azure AI Foundry list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,050
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$871
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,461
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$7,286
Use your own numbers

Where to run it

1 host serve Fw Glm 5.2 Fast. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
FW-GLM-5.2-Fast
$2.31 / $7.26

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 Azure AI Foundry.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    15% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    15% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    44% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    94% less

Open-weight picks

  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
    15% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    44% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    51% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    76% less

Call it

Using Azure AI Foundry's API.

Python
from litellm import completion

response = completion(
    model="azure_ai/FW-GLM-5.2-Fast",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Fw Glm 5.2 Fast cost?

On Azure AI Foundry, Fw Glm 5.2 Fast costs $2.31 per million input tokens and $7.26 per million output tokens. Cached input costs $0.231 per million tokens.

Which APIs offer Fw Glm 5.2 Fast?

Fw Glm 5.2 Fast runs on 1 API: Azure AI Foundry.

What is Fw Glm 5.2 Fast's context window?

1M tokens, with up to 131K tokens in one reply.

Is Fw Glm 5.2 Fast being retired?

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

What are cheaper alternatives to Fw Glm 5.2 Fast?

Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (15% less), Grok 4.7 on xAI (15% less) and Qwen3.8.2 4T A95B on DeepInfra (15% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Fw Glm 5.2 Fast's API model id?

Use FW-GLM-5.2-Fast with Azure AI Foundry.

Sources

Raw catalog entry for FW-GLM-5.2-Fast on Azure AI Foundry
{
  "cache_read_input_token_cost": 2.31e-7,
  "input_cost_per_token": 0.00000231,
  "litellm_provider": "azure_ai",
  "max_input_tokens": 1048576,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 0.00000726,
  "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
  "supports_function_calling": true,
  "supports_pdf_input": false,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_tool_choice": true
}