Choose a model to open its comparison page.
MiniMax M3 benchmark, API pricing, and provider data cover 146 API providers, with prices starting at $0.0020/request. MiniMax M3 free API options are available from 4 providers. The page also shows measured API speed and first-token latency.
MiniMax M3 is MiniMax next-generation large language model, designed for advanced reasoning, long-context understanding, and high-quality multilingual dialogue.
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.
1 metric
2 metrics
2 metrics
17 metrics · Rated
13 metrics · Rated
4 metrics · Estimated
8 metrics · Provisional
1 metric · No data
0 metrics · No data
8 metrics · Estimated
2 metrics · Provisional
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 |
|---|---|---|---|---|---|---|
AtlasCloud atlas-cloud/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | 524.3K tokens / 524.3K tokens |
DeepInfra deepinfra/bf16 | $0.300/M | $1.20/M | 99.8% | — | — | 524.3K tokens / 512K tokens |
Novita novita/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | 1M tokens / 131.1K tokens |
Together together | $0.300/M | $1.20/M | 99.8% | — | — | 524.3K tokens / — |
GMICloud gmicloud/fp8 | $0.600/M | $2.40/M | 99.6% | — | — | 1.0M tokens / — |
Minimax minimax/fp8 | $0.300/M | $1.20/M | 99.5% | — | — | 524.3K tokens / 512K tokens |
Morph morph | $0.600/M | $2.40/M | 99.1% | — | — | 256K tokens / 256K tokens |
Venice venice/fp8 | $0.300/M | $1.20/M | 98.1% | — | — | 524.3K tokens / 65.5K tokens |
Parasail parasail/fp8 | $0.300/M | $1.20/M | 95.7% | — | — | 1.0M tokens / 1.0M tokens |
Compare MiniMax M3 API pricing across 142 providers. Prices range from $0.0020/request to $2997.00/M. 3173721 API offers the lowest rate at $0.0020/request. 4 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | MiniMax-M3 | minimax-officially | $0.300/M Cache read$0.060/M | $1.20/M | — | — | — | |
L1 100% | MiniMax-M3 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 100% | minimax-m3 | default | -40%$0.180/M Cache read$0.036/M | -40%$0.720/M | — | — | ||
L1 100% | minimax-m3 | default | -93%$0.021/M | -93%$0.082/M | — | — | — | |
L1 100% | minimaxai/minimax-m3 | 0倍倍率分组 | -86%$0.041/M | -90%$0.123/M | — | — | — | |
L1 100% | MiniMax-M3 | 5倍倍率分组 | $0.685/M | $2.05/M | — | — | — | |
L1 100% | MiniMax-M3 | default | -11%$0.268/M | -11%$1.07/M | — | — | — | |
L1 100% | MiniMax-M3 | default | $4.20/M Cache read$0.840/M | $16.80/M | — | — | — | |
L1 100% | minimax-m3 | default | $0.030/request | - | — | — | — | |
L1 100% | minimax-m3 | default | -54%$0.137/M | $1.23/M | — | — | — | |
L1 100% | MiniMax-M3 | other | -17%$0.250/M Cache read$0.050/M | -17%$1.000/M | — | — | — | |
L1 100% | minimax-m3 | free | $7.50/M | $7.50/M | — | — | — | |
L1 100% | MiniMax-M3 | default | -52%$0.144/M | -52%$0.575/M | — | — | — | |
L1 100% | MiniMax-M3 | default | -23%$0.230/M | -23%$0.921/M | — | — | — | |
L1 100% | MiniMax-M3 | nvidia | $0.600/M Cache read$0.120/M | $2.40/M | — | — | — | |
L1 100% | MiniMax-M3 | default | $36.71/M | $36.71/M | — | — | — | |
L1 100% | [按量]minimax-m3 | default | $69.00/M | $69.00/M | — | — | — | |
Dext API Free | L1 100% | MiniMax-M3 | 公益 | Free | Free | — | — | — |
L1 100% | minimax-m3-free | 公益 | Free | Free | — | — | — | |
L1 100% | MiniMax-M3 | 国产模型 | $0.010/request | - | — | — | — |
