💰 TokenWatchWyrdWerkGitHubLinkedInX

MiniMax M3 API pricing

18 tracked providers; 18 priced offerings with offering-level rates

MiniMax M3 pricing across providers

Across tracked provider offerings, input runs $0.230–$0.600 per million tokens and output $0.960–$2.40 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is GMICloud at $0.057 per million tokens.

Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 17 of 18 offerings publish a cache-read rate; 10 of 18 publish a 30-minute endpoint uptime figure.

Open the calculator filtered to MiniMax M3

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 M3

Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.

MiniMax M3 provider offerings
ProviderQuantInput $/MOutput $/MCache $/MBlended $/MUptime (30m)
GMI Cloud promofp8$0.240$0.960$0.048$0.057100.00%
Coreweavefp4$0.230$0.960$0.050$0.059100.00%
Avian—$0.255$1.02$0.051$0.061—
Consensusprotocol—$0.280$1.10$0.050$0.061—
Modelrunfp8$0.300$1.30$0.050$0.062100.00%
Ember—$0.270$1.08$0.054$0.065—
DeepInfra—$0.280$1.10$0.056$0.067—
Streamlake promofp8$0.300$1.20$0.060$0.072100.00%
Venicefp8$0.300$1.20$0.060$0.072100.00%
Togetherunknown$0.300$1.20$0.060$0.072100.00%
Parasailfp8$0.300$1.20$0.060$0.072100.00%
Atlascloudfp8$0.300$1.20$0.060$0.072100.00%
Novitafp8$0.300$1.20$0.060$0.072100.00%
Minimaxunknown$0.300$1.20$0.060$0.072100.00%
OpenCode—$0.300$1.20$0.060$0.072—
Hyper—$0.327$1.31$0.064$0.077—
Runanywherebf16$0.330$1.32$0.066$0.079—
Maraunknown$0.600$2.40—$0.609—

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.