MiniMax M3 pricing & price history
MiniMax M3 by MiniMax costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.23 input / $0.96 output.
Price history
No price changes since tracking began on 2026-09-24. We check hourly.
Providers serving MiniMax M3 (13)
| Provider | Input | Output | Context | Uptime 30m | Uptime 24h |
|---|---|---|---|---|---|
| CoreWeave fp4 | $0.23 | $0.96 | 262K | 99.9% | 99.8% |
| GMICloud fp8 | $0.24 | $0.96 | 1M | 98.9% | 99.7% |
| DeepInfra fp8 | $0.28 | $1.10 | 524K | 99.2% | 99.5% |
| StreamLake fp8 | $0.30 | $1.20 | 1M | 99.0% | 99.5% |
| Venice fp8 | $0.30 | $1.20 | 524K | 76.2% | 93.6% |
| Together | $0.30 | $1.20 | 524K | 100.0% | 99.9% |
| Parasail fp8 | $0.30 | $1.20 | 1M | 100.0% | 97.8% |
| AtlasCloud fp8 | $0.30 | $1.20 | 524K | 84.8% | 97.7% |
| Novita fp8 | $0.30 | $1.20 | 1M | 99.5% | 99.5% |
| Minimax fp8 | $0.30 | $1.20 | 524K | 98.5% | 99.0% |
| Mara | $0.60 | $2.40 | 1M | 81.2% | 79.3% |
| SambaNova | $0.60 | $2.40 | 1M | 99.6% | 99.0% |
| ModelRun fp4 | $0.75 | $3.00 | 1M | 99.8% | 99.5% |
Provider availability updated 54m ago.
Cost calculator
Cheaper alternatives to MiniMax M3
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
I Ling 3.0 Flash VL inclusionAI | $0.06 | $0.18 | 262K | 24.6 | compare |
O GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.1M | 37.3 | compare |
D DeepSeek V4.1 Flash DeepSeek | $0.14 | $0.42 | 1M | 39.5 | compare |
Z GLM 5.3 Flash Z.ai (Zhipu) | $0.15 | $0.50 | 1.3M | 41.8 | compare |
O GPT-5.6 Luna OpenAI | $0.20 | $1.20 | 1.1M | 37.3 | compare |
O GPT-5.4 Nano OpenAI | $0.20 | $1.25 | 400K | 20.7 | compare |
About 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,...
FAQ
How much does MiniMax M3 cost?
MiniMax M3 by MiniMax costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.23 input / $0.96 output. A typical request with 2,000 input and 500 output tokens costs about $0.0012.
What is the context window of MiniMax M3?
MiniMax M3 supports up to 1,048,576 tokens of context and up to 512,000 output tokens per request.
Has MiniMax M3’s price changed?
No price changes recorded since ModelBank started tracking it on 2026-09-24.
Is MiniMax M3 being deprecated?
No retirement date has been announced for MiniMax M3 as of 2026-09-24.
What are cheaper alternatives to MiniMax M3?
Cheaper options include Ling 3.0 Flash VL ($0.06/$0.18), GPT-6 Luna ($0.10/$0.50), DeepSeek V4.1 Flash ($0.14/$0.42), GLM 5.3 Flash ($0.15/$0.50).