impulse

GLM 5.3 Fast

API id GLM-5.3-Fast
Input / 1M
$2.10
at Baseten
Output / 1M
$6.60
at Baseten
Context window
1M
tokens
Max output
262K
tokens per reply
Hosts
4
5 listings
Released
-
date not published

Pricing

List prices at Baseten, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$2.10$6.60
Cached input
90% off input
$0.21

What it costs a month

At Baseten list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$955
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$792
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,328
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$6,624
Use your own numbers

Where to run it

4 hosts serve GLM 5.3 Fast. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
glm-5.3-fast
$1.12 / $4.40
−40% vs headline
WallyCloud
glm-5.3-fast
$2.10 / $6.60
BasetenInference
GLM-5.3-Fast
$2.10 / $6.60
Fireworks AIInference
glm-5p3-fast
$2.10 / $6.60
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
glm-5p3-fast
$2.10 / $6.60

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
ImagesText
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

  • CoralBricks
    glm-5.3-fast
    $1.12 / $4.40
    40% less

Smaller Zhipu AI models

  • GLM 5v Turbo
    Zhipu AI · on Z.ai
    $1.20 / $4.00
    Lacks structured
    41% less
  • GLM 5 Code
    Zhipu AI · on Z.ai
    $1.20 / $5.00
    Lacks vision, structured
    33% less

Other frontier labs

  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    7% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    7% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    38% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    94% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    34% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    47% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    79% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    84% less

Model line

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

  1. UndatedGLM 5.3 FastLatest$2.10 / $6.60
  2. UndatedGLM 5.2 Fast$2.10 / $6.60
  3. UndatedGLM 5.1 Fast$2.80 / $8.80

Call it

Using Baseten's API.

Python
from litellm import completion

response = completion(
    model="baseten/GLM-5.3-Fast",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 5.3 Fast cost?

On Baseten, GLM 5.3 Fast costs $2.10 per million input tokens and $6.60 per million output tokens. Cached input costs $0.21 per million tokens. The cheapest host is CoralBricks, at $1.12 per million input tokens and $4.40 per million output tokens.

Which APIs offer GLM 5.3 Fast?

GLM 5.3 Fast runs on 4 APIs: CoralBricks, Wally, Baseten and Fireworks AI.

What is GLM 5.3 Fast's context window?

1M tokens, with up to 262K tokens in one reply.

Is GLM 5.3 Fast being retired?

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

Is there a newer version of GLM 5.3 Fast?

No. GLM 5.3 Fast is the newest model in its line.

What are cheaper alternatives to GLM 5.3 Fast?

Models that cost less and keep most of what it can do: GLM 5v Turbo on Z.ai (41% less), Gemini 4 Hydrogen on Google AI Studio (7% less), Grok 4.7 on xAI (7% less) and Qwen4 Max on Together AI (34% less). GLM 5.3 Fast itself costs 40% less on CoralBricks. Savings are on a mix of 3 input tokens to 1 output token.

What is GLM 5.3 Fast's API model id?

Use GLM-5.3-Fast with Baseten. Other hosts use their own ids: glm-5.3-fast on CoralBricks, glm-5.3-fast on Wally, glm-5p3-fast on Fireworks AI.

Sources

Raw catalog entry for GLM-5.3-Fast on Baseten
{
  "cache_read_input_token_cost": 2.1e-7,
  "input_cost_per_token": 0.0000021,
  "litellm_provider": "baseten",
  "max_input_tokens": 1048576,
  "max_output_tokens": 262144,
  "mode": "chat",
  "output_cost_per_token": 0.0000066,
  "source": "https://inference.baseten.co/v1/models",
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true
}