Devstral Small vs GLM 4.7 Flashx: cost comparison
Prices updated 2026-11-05 · computed from live provider data
Short answer: Devstral Small is cheaper on a
3:1 input/output blend — $0.122 per million tokens versus
$0.152, a 20% difference.
GLM 4.7 Flashx offers the larger context window at 202,752 tokens, against 128,000 for Devstral Small.
Head to head
| Devstral Small | GLM 4.7 Flashx | |
|---|---|---|
| Input, per 1M tokens | $0.070 | $0.070 |
| Output, per 1M tokens | $0.280 | $0.400 |
| Blended 3:1, per 1M | $0.122 | $0.152 |
| Context window | 128,000 | 202,752 |
| Vendor | vercel_ai_gateway | empiriolabs |
Monthly cost at real volumes
| Workload (input / output) | Devstral Small | GLM 4.7 Flashx |
|---|---|---|
| 1M in / 250K out | $0.140 | $0.170 |
| 10M in / 2.5M out | $1.40 | $1.70 |
| 100M in / 25M out | $14.00 | $17.00 |
Which should you pick?
Pick GLM 4.7 Flashx when you need the longer context window (202,752 vs 128,000 tokens). Pick Devstral Small when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.