MiniMax M3
$0.90
estimated usage cost
1,000 requests × (1,000 uncached input × $0.30 + 500 output × $1.20) / 1,000,000 = $0.90
base rates: up to 512,000 input tokens per request, inclusive.
the model directory
MiniMax M3 vs GPT-5.6 Terra
compare api pricing, context windows, and capabilities side by side.
use the same workload to understand the cost before choosing a model.
prices are published impossibl api usage rates in usd. compare the billing units and context tiers alongside each price. unpublished capabilities are marked explicitly.
| specification | MiniMax M3 minimaxai/minimax-m3 | GPT-5.6 Terra openai/gpt-5.6-terra |
|---|---|---|
| creator | MiniMax | OpenAI |
| model type | Text generation | Text generation |
| input modalities | text, image | text, image |
| output modalities | text | text |
| base input price | $0.30 / 1m tokens | $2.00 / 1m tokens |
| base output price | $1.20 / 1m tokens | $12.00 / 1m tokens |
| cached input price | $0.06 / 1m tokens | $0.20 / 1m tokens |
| cache creation price | not published | $2.50 / 1m tokens |
| context window | 524.3k tokens | 1.05m tokens |
| tool calling | not published | not published |
| context pricing tiers |
|
|
| endpoints |
|
|
| retirement | not announced | not announced |
estimate your api cost
estimate text token usage across the same workload. all amounts are in usd.
GPT-5.6 Terra
$8.00
estimated usage cost
1,000 requests × (1,000 uncached input × $2.00 + 500 output × $12.00) / 1,000,000 = $8.00
base rates: up to 272,000 input tokens per request, inclusive.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
MiniMax M3 vs GPT-5.6 Terra: side-by-side summary
MiniMax M3 and GPT-5.6 Terra are available through the Impossibl API. They share the /v1/chat/completions endpoint. Set the model identifier to select the model for a supported request.
MiniMax M3 is created by MiniMax. It has a 524,300-token context window. Base API pricing (USD): $0.30 per million input tokens; $1.20 per million output tokens. Above 512,000 input tokens per request, context-tier rates apply to the whole request.
GPT-5.6 Terra is created by OpenAI. It has a 1,050,000-token context window. Base API pricing (USD): $2.00 per million input tokens; $12.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
context window
- MiniMax M3: 524,300 tokens
- GPT-5.6 Terra: 1,050,000 tokens
price
- MiniMax M3: Base API pricing (USD): $0.30 per million input tokens; $1.20 per million output tokens. Above 512,000 input tokens per request, context-tier rates apply to the whole request.
- GPT-5.6 Terra: Base API pricing (USD): $2.00 per million input tokens; $12.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
created by
- MiniMax M3: MiniMax
- GPT-5.6 Terra: OpenAI