GLM 4.6 pricing across providers
Across tracked provider offerings, input runs $0.380–$0.600 per million tokens and output $1.55–$2.20 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 $0.085 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 5 of 5 offerings publish a cache-read rate; 3 of 5 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to GLM 4.6
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 4.6
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 | $1.55 | $0.070 | $0.085 | — |
| Venice | fp4 | $0.430 | $1.75 | $0.080 | $0.097 | 100.00% |
| DeepInfra | — | $0.500 | $2.00 | $0.100 | $0.120 | — |
| Novita | bf16 | $0.550 | $2.20 | $0.110 | $0.131 | 100.00% |
| Z.ai | fp4 | $0.600 | $2.20 | $0.110 | $0.133 | 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.