Choose a model to open its comparison page.
MiniMax M2.5 benchmark, API pricing, and provider data cover 190 API providers, with prices starting at $0.0041/M. MiniMax M2.5 free API options are available from 6 providers. The page also shows measured API speed and first-token latency.
MiniMax M2.5 is MiniMax's flagship text model for coding and agents, with SOTA-level programming and agentic performance, improved token efficiency, and fast high-TPS API deployment.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
2 metrics
2 metrics
0 metrics · No data
2 metrics · Estimated
2 metrics · Provisional
0 metrics · No data
0 metrics · No data
0 metrics · No data
0 metrics · No data
0 metrics · No data
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Parasail parasail/fp8 | $0.300/M | $1.20/M | 100.0% | — | — | 196.6K tokens / 196.6K tokens |
DeepInfra deepinfra/fp8 | $0.150/M | $1.15/M | 100.0% | — | — | 196.6K tokens / 32.8K tokens |
SiliconFlow siliconflow/fp8 | $0.300/M | $1.20/M | 100.0% | — | — | 196.6K tokens / 131.1K tokens |
Friendli friendli | $0.300/M | $1.20/M | 99.9% | — | — | 196.6K tokens / 196.6K tokens |
Inceptron inceptron/fp8 | $0.150/M | $0.900/M | 99.9% | — | — | 196.6K tokens / 196.6K tokens |
Chutes chutes/fp8 | $0.150/M | $1.20/M | 99.8% | — | — | 196.6K tokens / 65.5K tokens |
Novita novita/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | 204.8K tokens / 131.1K tokens |
StreamLake streamlake | $0.270/M | $1.08/M | 99.8% | — | — | 200K tokens / 128K tokens |
DigitalOcean digitalocean | $0.225/M | $0.900/M | 99.7% | — | — | 65.5K tokens / — |
AtlasCloud atlas-cloud/fp8 | $0.295/M | $1.20/M | 99.7% | — | — | 196.6K tokens / 196.6K tokens |
Nebius nebius/fp4 | $0.300/M | $1.20/M | 99.7% | — | — | 8K tokens / — |
Phala phala | $0.200/M | $1.38/M | 99.6% | — | — | 196.6K tokens / 196.6K tokens |
Minimax minimax/highspeed | $0.600/M | $2.40/M | 99.4% | — | — | 204.8K tokens / 131.1K tokens |
Venice venice | $0.270/M | $0.950/M | 99.3% | — | — | 198K tokens / 32.8K tokens |
Minimax minimax/fp8 | $0.300/M | $1.20/M | 98.5% | — | — | 204.8K tokens / 131.1K tokens |
Mara mara | $0.240/M | $0.960/M | 95.4% | — | — | 196.6K tokens / 196.6K tokens |
WandB wandb/fp8 | $0.300/M | $1.20/M | 90.1% | — | — | 196.6K tokens / 196.6K tokens |
Compare MiniMax M2.5 API pricing across 184 providers. Prices range from $0.0041/M to $2997.00/M. 6345ywz API offers the lowest rate at $0.0041/M. 6 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | MiniMax-M2.5 | default | -4%$0.288/M | -4%$1.15/M | 40.0 t/s | 11.01 s | — | |
L1 100% | minimax-m2.5 | default | -4%$0.288/M | -4%$1.15/M | — | — | — | |
L1 100% | Minimax-M2.5 | default | $10.27/M | $10.27/M | — | — | — | |
L1 96% | minimax-m2.5 | default | $0.010/request | - | 18.6 t/s | 19.89 s | — | |
L1 96% | minimax-m2.5-free | default | $0.010/request | - | — | — | — | |
L1 96% | minimaxai/minimax-m2.5 | default | $0.010/request | - | — | — | — | |
L1 100% | MiniMax-M2.5 | default | $60.00/M | $60.00/M | — | — | — | |
L1 100% | minimax-m2.5 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 100% | MiniMax-M2.5 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 100% | Minimax-M2.5 | default | $5.14/M | $5.14/M | — | — | — | |
L1 100% | minimax-m2.5 | bailian | -50%$0.150/M Cache read$0.015/M | -50%$0.600/M | — | — | — | |
L1 99% L2 57% | minimax/minimax-m2.5 | default | -53%$0.140/M | -32%$0.810/M | — | — | — | |
L1 100% | minimax-m2.5 | default | -93%$0.021/M Cache read$0.0041/M | -93%$0.082/M | — | — | — | |
L1 100% | MiniMaxAI/MiniMax-M2.5 | 临时渠道 | -99%$0.0041/M Cache read$0.0008/M | -99%$0.016/M | — | — | — | |
L1 100% | Pro/MiniMaxAI/MiniMax-M2.5 | 临时渠道 | -99%$0.0041/M | -99%$0.017/M | — | — | — | |
L1 100% | MiniMax-M2.5 | default | -11%$0.268/M | -11%$1.07/M | — | — | — | |
L1 100% | Minimax-M2.5 | default | $9.55/M | $9.55/M | — | — | — | |
L1 100% | minimax-m2.5 | default | $0.010/request | - | — | — | — | |
L1 100% | MiniMax-M2.5 | other | -58%$0.125/M Cache read$0.012/M | -58%$0.500/M | — | — | — | |
L1 100% | minimax-m2.5 | default | -32%$0.205/M | $1.23/M | — | — | — |
