GLM-4.7-Flash

Zhipu AIMCP Tool CallReasoning
zhipuai/glm-4.7-flashOpen Weights

Budget GLM lane for fast coding help, routing, and everyday automation

Benchmark Pricing$0.08 / 1M in$0.48 / 1M out
Context: 200,000 tokens•Max Output: 131,072 tokens•Knowledge: 2025-04•Released: 2026-01-19

TECHNICAL SPECIFICATIONS

Context Window200,000200K tokens
Max Output131,072131.1K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ GLM-4.7-Flash natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 200,000 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedresolved
59.2

API CALL INVOCATION EXAMPLE

// Example: Calling GLM-4.7-Flash via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ZHIPUAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "zhipuai/glm-4.7-flash",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

15 providers
Zhipu AIglm-4.7-flash
$0.00 / $0.00$0.00 cache
Cortecsglm-4.7-flash
$0.08 / $0.48
NanoGPTz-ai/glm-4.7-flash:thinking
$0.07 / $0.40$0.01 cache
Novita AIzai-org/glm-4.7-flash
$0.07 / $0.40$0.01 cache
Synthetichf:zai-org/GLM-4.7-Flash
$0.10 / $0.50$0.02 cache
LLM Gatewayembercloud/glm-4.7-flash
$0.06 / $0.40$0.01 cache
Poenovita/glm-4.7-flash
$0.07 / $0.40
Tempr Gatewayzai/glm-4.7-flashx
$0.07 / $0.40$0.01 cache
AI/ML APIz-ai/glm-4.7-flash
$0.17 / $0.69$0.01 cache
Venice AIolafangensan-glm-4.7-flash-heretic
$0.07 / $0.40$0.04 cache
AIHubMixglm-4.7-flash-free
$0.00 / $0.00
Vercel AI Gatewayzai/glm-4.7-flashx
$0.06 / $0.40$0.01 cache
Eden AIcloudflare/@cf/zai-org/glm-4.7-flash
$0.06 / $0.40
Ofoxz-ai/glm-4.7-flashx
$0.07 / $0.40$0.01 cache
Merge Gatewayzai/glm-4.7-flashx
$0.07 / $0.40$0.01 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

MODEL RESOURCES

View Zhipu AI HubHugging Face Weights

More Models by Zhipu AI

Alternative and family models from the same lab

View all Zhipu AI models →
GLM-5.3
zhipuai/glm-5.3•Zhipu AI
1M ctx

Flagship GLM model for long-horizon coding, agents, and complex project delivery

131.1K out maxTerminal-Bench: 88.2 pass@1
In: $1.20 • Out: $4.18
Zhipu AI
GLM-5.3-Flash
zhipuai/glm-5.3-flash•Zhipu AI
1M ctx

Native multimodal GLM model for efficient coding and long-horizon agent tasks

131.1K out maxVisionPDFTerminal-Bench: 84.3 pass@1
In: $0.12 • Out: $0.42
Zhipu AI
GLM-5.2
zhipuai/glm-5.2•Zhipu AI
1M ctx

Open flagship GLM for long-horizon coding agents and million-token context work

131.1K out maxSWE-Bench Pro: 62.1 resolve rate
In: $1.20 • Out: $4.18
Zhipu AI