GLM 4.7
The cheapest provider for GLM 4.7 is DeepInfra at $0.738 per 1M tokens (blended), charging $0.40 per 1M input and $1.75 per 1M output tokens. 7 providers serve it; the most expensive charges 1.56× as much. Context window: 200K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.738
at DeepInfra
Input / output
$0.40 / $1.75
per 1M tokens
Providers
7
1.56× spread
7 days
—
best price
30 days
—
best price
Context
200K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DeepInfraCheapest fp4 | $0.40 | $1.75 | $0.738 | best | |||
| fp4·−27% discount | $0.40 | $1.93 | $0.783 | +6% | |||
| fp8 | $0.52 | $1.85 | $0.853 | +16% | |||
| fp8·−10% discount | $0.54 | $1.98 | $0.90 | +22% | |||
| $0.60 | $2.20 | $1.00 | +36% | ||||
| fp4 | $0.60 | $2.20 | $1.00 | +36% | |||
| fp4 | $0.70 | $2.50 | $1.15 | +56% |
- DeepInfraCheapest$0.738$0.40 in · $1.75 outbest198K ctx98.1% uptimefp4
- $0.783$0.40 in · $1.93 out+6%198K ctx94.1% uptimefp4·−27% discount
- $0.853$0.52 in · $1.85 out+16%198K ctx84.0% uptimefp8
- $0.90$0.54 in · $1.98 out+22%200K ctx99.8% uptimefp8·−10% discount
- $1.00$0.60 in · $2.20 out+36%200K ctx99.9% uptime
- $1.00$0.60 in · $2.20 out+36%198K ctx99.9% uptimefp4
- $1.15$0.70 in · $2.50 out+56%128K ctx93.1% uptimefp4
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| DeepInfra | $0.08 |
| Venice | $0.0801 |
| AtlasCloud | $0.12 |
| Novita | $0.099 |
| Z.AI | $0.11 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
- Released
- Dec 22, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- z-ai/glm-4.7-20251222
- Weights
- zai-org/GLM-4.7