Migrating from glm-4.7-flash to glm-5.3-flash
What changes when you move from glm-4.7-flash to glm-5.3-flash: prices, limits, features and parameters, read from each company's own pages.
- From
- glm-4.7-flash
- Status
- Active
- Shutdown
- none announced
- Time left
- —
- Status
- Active
- Shutdown
- none announced
- Time left
- —
Prices
USD per 1M tokens, standard tier| Type | glm-4.7-flash | glm-5.3-flash | Change |
|---|---|---|---|
| Input | $0.00first seen October 5, 2026 · source | $0.15first seen October 5, 2026 · source | — |
| Cached input | $0.00first seen October 5, 2026 · source | $0.03first seen October 5, 2026 · source | — |
| Output | $0.00first seen October 5, 2026 · source | $0.50first seen October 5, 2026 · source | — |
At 1M input and 250K output tokens a month: $0.00 on glm-4.7-flash, $0.275 on glm-5.3-flash (—).
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
TokensNeither company publishes a context window or output limit for these models.
Benchmarks
Same benchmark and source on both sides; settings named where they differ| Benchmark | glm-4.7-flash | glm-5.3-flash | Change |
|---|---|---|---|
| Arena TextArena. Ranges don't overlap. | 1365 ±6 | 1474 ±5 | +109 |
| Arena Text: CodingArena. Ranges don't overlap. | 1423 ±11 | 1525 ±8 | +102 |
| GPQA DiamondEpoch AI, max effort (vs no setting). | 60.5% | 90.2% | +29.7 pts |
| OTIS Mock AIME 2024-2025Epoch AI, max effort (vs no setting). | 58.3% | 93.9% | +35.6 pts |
A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
Features and parameters
Compare modelsNeither company publishes feature facts for these models.
Free tier
glm-4.7-flash: Free model, in place when tracking began (October 7, 2026) (source) · All free models
glm-5.3-flash: no free tier listed
Free access is lost: glm-5.3-flash has no free tier listed.
Aliases
All aliasesNo aliases point at either model.
On cloud platforms
All platform dates| Model | Platform | Platform ID | Shutdown | Time left |
|---|---|---|---|---|
| glm-4.7-flash | Amazon Bedrock | zai.glm-4.7-flash | Mar 30, 2027Legacy | 166 days |
Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.
Checklist
- Change the model string from
glm-4.7-flashtoglm-5.3-flash. - Re-check costs: glm-5.3-flash costs more than glm-4.7-flash (input $0.00 → $0.15, output $0.00 → $0.50).
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: glm-4.7-flash, glm-5.3-flash.