impulse

GLM 5.3 Spot

API id glm-5p3-spot
Input / 1M
$0.98
at Fireworks AI
Output / 1M
$3.08
at Fireworks AI
Context window
1M
tokens
Max output
128K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.98$3.08
Cached input
81% off input
$0.182

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$453
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$390
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$690
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$3,091
Use your own numbers

Where to run it

1 host serve GLM 5.3 Spot. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
glm-5p3-spot
$0.98 / $3.08

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 Fireworks AI.

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
    0% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    17% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    69% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    87% less

Open-weight picks

  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    43% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    47% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    54% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    58% less

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/glm-5p3-spot",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GLM 5.3 Spot cost?

On Fireworks AI, GLM 5.3 Spot costs $0.98 per million input tokens and $3.08 per million output tokens. Cached input costs $0.182 per million tokens.

Which APIs offer GLM 5.3 Spot?

GLM 5.3 Spot runs on 1 API: Fireworks AI.

What is GLM 5.3 Spot's context window?

1M tokens, with up to 128K tokens in one reply.

Is GLM 5.3 Spot being retired?

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

What are cheaper alternatives to GLM 5.3 Spot?

Models that cost less and keep most of what it can do: Gemini 3.8 Flash on Google AI Studio (0% less), Grok Build 0.1 on xAI (17% less) and GLM 5.3 on CLF AI Gateway (43% less). Savings are on a mix of 3 input tokens to 1 output token.

What is GLM 5.3 Spot's API model id?

Use glm-5p3-spot with Fireworks AI.

Sources

Raw catalog entry for glm-5p3-spot on Fireworks AI
{
  "cache_read_input_token_cost": 1.82e-7,
  "input_cost_per_token": 9.8e-7,
  "litellm_provider": "fireworks_ai",
  "max_input_tokens": 1048576,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.00000308,
  "source": "https://api.fireworks.ai/v1/serverless/models",
  "supports_function_calling": true,
  "supports_mid_conversation_system": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false
}