GLM5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
glm5.3Released 18 Aug 2026 (Aug 2026)Pricing
List prices at Sarvam, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.34 | $4.15 | |
| Cached input 84% off input | $0.213 | 84% off input |
What it costs a month
At Sarvam list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$612
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$522
- Coding agent1,000 requests a day, 40K in / 2K out, cached$910
- Overnight batch20,000 requests a day, 4K in / 0.4K out$4,213
Where to run it
1 host serve GLM5.3. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
SarvamCloud glm5.3 | $1.34 / $4.15 | glm5.3 |
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
- Effort settings the source lists
- lowhighmax
- Features
- Parallel tool callsPrompt caching
- Open weights
- License: otherRuns in about 1808 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
No host sells it for less than Sarvam.
Smaller Zhipu AI models
- 7% less
Other frontier labs
- 2% less
- 27% less
- 39% less
- 90% less
Open-weight picks
- 16% less
- 58% less
- 61% less
- 66% less
Model line
Newer and older versions, at each lab's own price.
Call it
Using Sarvam's API.
from litellm import completion
response = completion(
model="sarvam/glm5.3",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GLM5.3 cost?
On Sarvam, GLM5.3 costs $1.34 per million input tokens and $4.15 per million output tokens. Cached input costs $0.213 per million tokens.
Which APIs offer GLM5.3?
GLM5.3 runs on 1 API: Sarvam.
What is GLM5.3's context window?
1M tokens, with up to 1M tokens in one reply.
Is GLM5.3 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of GLM5.3?
Yes. GLM 5.3 is the newest model in this line, released on 18 Aug 2026.
What are cheaper alternatives to GLM5.3?
Models that cost less and keep most of what it can do: GLM 5v Turbo on Z.ai (7% less), GPT-6.1 Terra on OpenAI (2% less), Gemini 3.8 Flash on Google AI Studio (27% less) and Inkling on DeepInfra (16% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GLM5.3 released?
Zhipu AI released it on 18 Aug 2026.
What is GLM5.3's API model id?
Use glm5.3 with Sarvam.
Sources
Raw catalog entry for glm5.3 on Sarvam
{
"cache_read_input_token_cost": 2.127659574e-7,
"input_cost_per_token": 0.000001340425532,
"litellm_provider": "sarvam",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 0.00000414893617,
"reasoning_effort_levels": [
"low",
"high",
"max"
],
"source": "https://www.sarvam.ai/token-factory/pricing",
"supports_audio_input": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_video_input": false,
"supports_vision": false
}