GLM 4.7 Flash
z-ai/glm-4.7-flash- Z.ai
- Family · GLM 4 Flash
- Released 19 Jan 2026
- Open weights
- Text → Text
- Tools · JSON
Spec & list price
Context195K
Max output118K
Input / 1M$0.06
Output / 1M$0.406.6× input
Scores · standing
Intelligence14.9#175/489
Usage
Tokens / day1.4B▼ 18% 7d
Usage rank#178
Requests / day494.5K
Tool calls / req0.12
Per request · 30 days
Avg input2.2K0.1× median
Avg output1770.3× median
Cache hit14%0.2× median
Reasoning share57%about median
Tool-call failures0.8%0.4× median
Consumption
Peak 3.8B 26 OctLow 809.1M 1 NovRank today #178
News & trends
News · latest from Z.ai
- Hermes and REA and GLM 5.3 = Reverse engineering TikTok app for less than $20scraping.club · 29 Oct
- GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behaviorlesswrong.com · 27 Oct
- Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)blog.cloudflare.com · 26 Oct
- ReplaySSM: Rethinking State Storage for Faster Hybrid-Model DecodingNVIDIA · 12 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 2 providers, latest day
Output speed#223/33451 tok/s1.3× slower than median
Fastest provider55 tok/sbest of 2 providers
First token#1290.81 s1.3× quicker than median
#4 cheapest of 23 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Technical details
- Tokenizer
- Other
- License
- MIT
- Parameters
- 31.2B
- Moderation
- none
- Downloads · likes
- 968.9K · 1.9K
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Low-cost agents that call tools
- Instruction-following assistants
- Structured JSON extraction
- Retrieval-augmented question answering
- Self-hosted open-weight deployments
Think twice for
- Image understanding
- Hardest reasoning and science tasks
- Hardest terminal-style agent runs
- Frontier-level coding
Research papers
- RAZOR: Pruning Replaceable Experts in LLMs24 Sep
- Opinion Leader Dynamics: How Sparse Attention Shapes Token Clustering21 Sep
- Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain14 Sep
- What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness9 Jul
- CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents6 Jul
- Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents4 Jun
- Post-Trained MoE Can Skip Half Experts via Self-Distillation18 May
- AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards21 Apr
Alternatives
other vendors · similar capability- 12.9
- 11.6
- 18.2
- 10.0
Using GLM 4.7 Flash at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.