GLM 4.7 Flash pricing & benchmarks
Released Jan 19, 2026 · served by 4 providers
What GLM 4.7 Flash is
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,...
- Model ID:
z-ai/glm-4.7-flash - Modality: text->text
- Tool calling: supported · Structured output: supported
- Weights:
zai-org/GLM-4.7-Flashon Hugging Face
Providers and prices for GLM 4.7 Flash
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| DeepInfracheapest | $0.060 | $0.400 | 203K | bf16 | 99.6% | — |
| Cloudflare | $0.060 | $0.400 | 131K | — | 99.6% | — |
| Novita | $0.070 | $0.400 | 200K | bf16 | 86.4% | — |
| Venice | $0.125 | $0.500 | 128K | fp8 | 98.6% | — |
GLM 4.7 Flash benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| uicomponent | models | #35 | 1244 | 57.6% |
| website | models | #42 | 1219 | 54% |
| codecategories | models | #44 | 1208 | 53.1% |
| 3d | models | #54 | 1178 | 51.2% |
| gamedev | models | #54 | 1191 | 49.7% |
| svg | models | #55 | 1088 | 44.2% |
| dataviz | models | #70 | 1152 | 45.3% |
FAQ
How much does the GLM 4.7 Flash API cost?
$0.060 per 1M input tokens and $0.400 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.18.
Is GLM 4.7 Flash free?
No. It is a paid model starting at $0.060 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GLM 4.7 Flash?
DeepInfra at $0.060 input / $0.400 output per 1M tokens (bf16 quantization).
Can I self-host GLM 4.7 Flash?
Yes — weights are published as zai-org/GLM-4.7-Flash on Hugging Face, so you can run it on your own hardware.