GLM 5.1 pricing across providers
Across tracked provider offerings, input runs $0.743–$1.40 per million tokens and output $2.90–$4.40 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Chutes at $0.124 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 15 of 15 offerings publish a cache-read rate; 8 of 15 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to GLM 5.1
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 5.1
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) |
|---|---|---|---|---|---|---|
| Chutes | fp8 | $0.900 | $2.90 | $0.090 | $0.124 | 100.00% |
| Ember | — | $0.931 | $2.93 | $0.173 | $0.206 | — |
| Streamlake promo | fp8 | $0.966 | $3.04 | $0.179 | $0.213 | 100.00% |
| Avian | — | $0.743 | $2.97 | $0.186 | $0.214 | — |
| Atlascloud | fp8 | $1.26 | $3.96 | $0.234 | $0.278 | — |
| Alibaba | fp8 | $1.33 | $4.18 | $0.247 | $0.294 | — |
| Novita | fp8 | $1.38 | $4.40 | $0.260 | $0.309 | — |
| Nebius | fp8 | $1.40 | $4.40 | $0.260 | $0.309 | 100.00% |
| Baidu | fp8 | $1.40 | $4.40 | $0.260 | $0.309 | 100.00% |
| GMI Cloud | fp8 | $1.40 | $4.40 | $0.260 | $0.309 | — |
| Friendli | unknown | $1.40 | $4.40 | $0.260 | $0.309 | 100.00% |
| Z.ai | fp8 | $1.40 | $4.40 | $0.260 | $0.309 | 100.00% |
| Venice promo | fp8 | $1.40 | $4.40 | $0.260 | $0.310 | 100.00% |
| SiliconFlow | fp8 | $1.19 | $3.74 | $0.600 | $0.630 | 100.00% |
| Phala | unknown | $1.21 | $4.20 | $0.600 | $0.633 | — |
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.