MiniMax M3
by MiniMax · minimax/minimax-m3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
- Input / 1M tokens
- $0.30
- Output / 1M tokens
- $1.20
- Context
- 1.05M
Specs
| Input price | $0.30 / 1M tokens |
|---|---|
| Output price | $1.20 / 1M tokens |
| Cached input | $0.06 / 1M tokens |
| Context window | 1.05M tokens |
| Max output | 512K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | May 31, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
13 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 524K | 131K | $0.224 | $0.88 | $0.0448 | 100% | — | — | Normal | |
| CoreWeave | fp4 | 262K | 236K | $0.23 | $0.96 | $0.05 | 100% | 465 ms | 118 tok/s | Normal | |
| GMICloud | fp8 | 1.05M | 524K | $0.24 | $0.96 | $0.048 | — | 2.29 s | 72 tok/s | Code -2 | |
| DeepInfra | fp8 | 524K | 131K | $0.28 | $1.10 | $0.056 | 100% | 862 ms | 41 tok/s | Normal | |
| AtlasCloud | fp8 | 524K | 524K | $0.30 | $1.20 | $0.06 | 100% | 1.60 s | 138 tok/s | Normal | |
| Minimax | — | 524K | 512K | $0.30 | $1.20 | $0.06 | 100% | 1.29 s | 105 tok/s | Normal | |
| Novita | fp8 | 1M | 131K | $0.30 | $1.20 | $0.06 | 100% | 1.93 s | 109 tok/s | Normal | |
| Parasail | fp8 | 1.05M | 524K | $0.30 | $1.20 | $0.06 | 100% | 1.20 s | 107 tok/s | Normal | |
| StreamLake | fp8 | 1M | 512K | $0.30 | $1.20 | $0.06 | 100% | 2.88 s | 90 tok/s | Normal | |
| Together | — | 524K | 472K | $0.30 | $1.20 | $0.06 | 100% | 490 ms | 94 tok/s | Normal | |
| Venice | fp8 | 524K | 65.5K | $0.30 | $1.20 | $0.06 | 100% | 684 ms | 167 tok/s | Normal | |
| ModelRun | fp8 | 1.05M | 944K | $0.30 | $1.30 | $0.05 | 100% | 860 ms | 104 tok/s | Normal | |
| Mara | — | 1.05M | 944K | $0.60 | $2.40 | — | — | 2.02 s | 85 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#48
by tokens, Oct 29, 2026
56.8B
tokens that day · 7 days −22%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- MiniMax
MiniMax M3.1 Flash
- Input
- $0.075
- Output
- $0.30
- Context
- 1.05M
- MiniMax
MiniMax M2.7
- Input
- $0.30
- Output
- $1.20
- Context
- 205K
- MiniMax
MiniMax M2.5
- Input
- $0.30
- Output
- $1.20
- Context
- 205K
- MiniMax
MiniMax M2-her
- Input
- $0.30
- Output
- $1.20
- Context
- 65.5K
- MiniMax
MiniMax M2.1
- Input
- $0.30
- Output
- $1.20
- Context
- 205K
- MiniMax
MiniMax M2
- Input
- $0.255
- Output
- $1.02
- Context
- 205K