GLM 4.7 pricing across providers
Across tracked provider offerings, input runs $0.380–$0.700 per million tokens and output $1.66–$2.50 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Ember at $0.092 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 7 of 8 offerings publish a cache-read rate; 3 of 8 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to GLM 4.7
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for GLM 4.7
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Ember | — | $0.380 | $1.66 | $0.076 | $0.092 | — |
| DeepInfra | — | $0.400 | $1.75 | $0.080 | $0.096 | — |
| Venice promo | fp4 | $0.400 | $1.93 | $0.080 | $0.097 | — |
| Avian | — | $0.388 | $1.81 | $0.097 | $0.113 | — |
| Novita promo | fp8 | $0.540 | $1.98 | $0.099 | $0.119 | 100.00% |
| Bytedance | — | $0.600 | $2.20 | $0.110 | $0.133 | — |
| Z.ai | fp4 | $0.600 | $2.20 | $0.110 | $0.133 | 100.00% |
| Mancer 2 | fp4 | $0.700 | $2.50 | — | $0.709 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.