About
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
Related Models
Pricing
Input
$0.06
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.14
per 1M tokens
Cheaper than 77% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.14
Monthly
$4.35
vs. Similar Models
Z.ai: GLM 4.6Q:+0.1
$0.76+422%
Grok 3 mini Reasoning (high)Q:-0.4
$0.35+141%
Grok 4.20 0309 (Non-reasoning)Q:-0.4
$3.00+1969%
OpenAI: o1Q:+0.5
$26.25+18003%
Performance
105
tokens/sec
Faster than 56% of models
0.92
seconds
Faster than 60% of models
20.05
seconds
Faster than 25% of models
Market Median
94 tok/s
11% faster
Median TTFT
1.11s
17% faster
Throughput/Dollar
721
tok/s per $/1M
Speed Comparison
Qwen3 4B (Non-reasoning)
104 tok/s-0%
Qwen3 4B (Reasoning)
104 tok/s-0%
Qwen3 Omni 30B A3B Instruct
105 tok/s+1%
Context Window
203K
tokens
Larger than 55% of models
Max Output
16K
tokens
8% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
58.1%
HLE
7.1%
LiveCodeBenchNot evaluated
SciCode
33.7%
TerminalBench Hard
22.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
60.8%
Long Context Recall
35.0%
Tau2
98.8%
Market AverageTop Score