MiniMax M2.5 pricing across providers
Across tracked provider offerings, input runs $0.143–$0.300 per million tokens and output $0.855–$1.20 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is StreamLake at $0.038 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 9 of 9 offerings publish a cache-read rate; 7 of 9 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to MiniMax M2.5
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 MiniMax M2.5
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) |
|---|---|---|---|---|---|---|
| Streamlake promo | unknown | $0.270 | $1.08 | $0.027 | $0.038 | 100.00% |
| Venice | unknown | $0.270 | $0.950 | $0.030 | $0.041 | 100.00% |
| GMI Cloud | fp8 | $0.300 | $1.20 | $0.030 | $0.043 | 50.00% |
| Novita | fp8 | $0.300 | $1.20 | $0.030 | $0.043 | 100.00% |
| Minimax | unknown | $0.300 | $1.20 | $0.030 | $0.043 | 100.00% |
| Ember | — | $0.143 | $0.855 | $0.040 | $0.047 | — |
| Atlascloud | fp8 | $0.295 | $1.20 | $0.060 | $0.072 | 100.00% |
| Digitalocean | unknown | $0.300 | $1.20 | $0.060 | $0.072 | 100.00% |
| Avian | — | $0.270 | $1.08 | $0.150 | $0.158 | — |
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.