GLM-4.7 vs Gemini 3.5 Flash Lite
API pricing, benchmark indices and specs — updated 19 October 2026.
google · B · API-only
Input / 1M
$0.30
Output / 1M
$2.50
AA index
22.2
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | GLM-4.7 | Gemini 3.5 Flash Lite |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 358.3 B | n/a — API-only |
| Architecture | Glm4MoeForCausalLM | n/a — API-only |
| Context length | 202,752 | 1,048,576 |
| Licence | mit | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | 2 | n/a — API-only |
| Downloads 30d | 80,924 | n/a — API-only |
| Downloads all time | 910 K | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2025-12-22 | n/a — API-only |
| API input price / 1M tokens | $0.54 | $0.30 |
| API output price / 1M tokens | $1.98 | $2.50 |
| Est. cost per 1M input + 1M output tokens | $2.52 | $2.80 |
| Cached input / 1M tokens | $0.099 | $0.03 |
| AA Intelligence Index | 22.2 | 22.2 |
| AA Coding Index | 45.3 | 49.3 |
| AA Agentic Index | — | 14.3 |
| Max output tokens | 131,072 | 65,536 |
| API providers | 6 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
GLM-4.7
$2.52
Gemini 3.5 Flash Lite
$2.80
GLM-4.7 is 1.1× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
GLM-4.7 · fp16 @ 198K ctx
2,119.2 GB / 24 GB