GLM-5-Turbo is a Z.AI foundation model deeply optimized for the OpenClaw agent scenario.
- Input
- text $1.2/M
- Output
- text $4/M
- Cache read
- $0.24/M
- Context
- 205K
- vs GPT-4o
- ~76% cheaper
Price in context
Where the price sits among 60 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 200,000 |
|---|---|
| Max output (vendor spec) | 131,072 |
Prompt caching
| How it caches | automatic |
|---|
Thinking
| Vendor control | thinking.type |
|---|---|
| Accepted values | enabled · disabled |
| Default | enabled, and the model automatically determines whether to think applied when the request sets nothing |
| Can be turned off | Yes |
| Thinking behaviour | Trace returns in reasoning_content; prior turns' traces are cleared by default (clear_thinking true), and interleaved thinking blocks should be preserved and returned together with tool results. |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text → text |
|---|
- API-only speed-optimized GLM-5 variant tuned for the OpenClaw agent scenario: more reliable tool invocation and long-running task stability
- 200K context / 128K max output
Use GLM-5-Turbo in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="glm-5-turbo",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "glm-5-turbo",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-turbo",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "glm-5-turbo",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("glm-5-turbo")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About GLM-5-Turbo
- Compared with the base GLM-5, the official docs highlight four targeted upgrades: more precise tool invocation, stronger decomposition of complex instructions, time-aware handling of scheduled and persistent tasks, and higher throughput on long logical chains.
- It provides a 200K context window and up to 128K output tokens, with thinking modes, streaming, function calling, context caching, structured JSON output, and MCP tool integration.
- Z.AI frames the release as improving stability and efficiency in long-chain agent tasks rather than raw intelligence, and lists the domains it was tuned against: installation and configuration, code development, information gathering, data analysis, content creation, office productivity, financial analysis, operations engineering, and research.
- That list is the honest way to read it: an agent-harness specialist rather than a general-purpose sibling.
- Thinking follows the same GLM-5 convention, enabled by default with the model deciding whether to reason, and the trace returned separately from the answer.
- External skills can be invoked alongside tools, and tool-call arguments can be streamed incrementally.
- Two things distinguish it from the rest of the line: Z.AI does not publish its parameter count, and unlike GLM-5, 5.1 and 5.2 it has no open-weights release.
- It is API-only.
- On Synthorai, GLM-5-Turbo is callable via the standard OpenAI-compatible API.
FAQ
Is the GLM-5-Turbo API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $1.2/M input tokens, that credit alone covers roughly 104 requests of ~8K tokens against GLM-5-Turbo.
What is GLM-5-Turbo best at?
Deeply optimized for the OpenClaw agent scenario; more precise tool invocation and instruction decomposition; time-aware handling of scheduled, persistent tasks. See the About section for the full picture from the vendor's own release notes.
How much does GLM-5-Turbo cost?
GLM-5-Turbo costs $1.2 per million input tokens and $4 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.24/M.
Does GLM-5-Turbo support prompt caching?
Yes, automatically: Z.ai-served prompts cache with no code changes. Cached input tokens bill at $0.24/M vs $1.2/M uncached. Prompt caching guide →
How do I get access to GLM-5-Turbo?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="glm-5-turbo", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.