MiniMax M2.1 · MiniMax

What does MiniMax M2.1 cost to run in a coding agent?

MiniMax M2.1 costs about $0.0065 per average coding-agent request on our measured traffic, at OpenRouter's listed prices of $0.30 per million input and $1.20 per million output tokens. It scores 21 on the Artificial Analysis Intelligence Index (an estimate), 40th of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenRouter listed price, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run current Claude, GPT, Gemini and open models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What MiniMax M2.1 costs per coding-agent request

Cost at list price	MiniMax M2.1
Prompt under 100K tokens50% of requests, 87% of input cached	$0.0045
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.0099
Prompt over 272K tokens11% of requests, 86% of input cached	n/a
Average request	$0.0065
100 requests	$0.65
Median session16 requests; a session ends after 10 idle minutes	$0.076
A month of regular usemedian of 20 users active on 5+ days	$7.18

Each logged request priced at the listed rates above for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request. 20% of requests were larger than MiniMax M2.1's 205K context window and are left out of its figures.

MiniMax M2.1 benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	21 (estimate)	40 of 48
Output speedmedian	67 tokens/s	32 of 44
Time to first answer tokenincludes thinking time	31 s	17 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: MiniMax-M2.1, speed on MiniMax. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

What to watch for

Its 205K-token window is smaller than 20% of our coding-agent requests, which are left out of the figures above, so long agent sessions will hit the limit. The price is OpenRouter's listed rate on October 13, 2026, which can be a third-party host's; MiniMax's own API may charge differently.

About MiniMax M2.1

MiniMax M2.1 is MiniMax's December 23, 2025 open-weight model for agent workloads, with a 204K context. It is the second-cheapest model on this hub per request in our measurements ($0.0065 at OpenRouter's listed price), but Artificial Analysis estimates 21 on its Intelligence Index and lists it as superseded, and its 204K context is smaller than 19.7% of the coding-agent requests we measured.

Sources: Artificial Analysis

MiniMax M2.1 FAQ

How much does MiniMax M2.1 cost per coding-agent request?

$0.0065 on average at OpenRouter's listed price, $0.65 per 100 requests, and $0.076 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenRouter's listed rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.

Does MiniMax M2.1 charge more for long prompts?

No. MiniMax M2.1 bills the same rate per token up to its 205K-token context window, which is smaller than 20% of the coding-agent requests we measured.

How fast is MiniMax M2.1?

Artificial Analysis measures MiniMax-M2.1 at 67 output tokens per second, with 31 seconds to the first answer token, thinking time included, on MiniMax's API. Source: Artificial Analysis (artificialanalysis.ai).

Is MiniMax M2.1 good for AI agents?

Short, tool-heavy agent steps on a tight budget. On our scoring, which is calibrated to public benchmarks, it rates 4.7/10 for agentic ability and 5.1/10 for output quality. Low cost per request ($0.0065).

What is MiniMax M2.1's context window?

MiniMax M2.1 has a 205K-token context window. MiniMax is the maker.

Is MiniMax M2.1 open source?

Yes. MiniMax M2.1 ships with open weights, so you can self-host it or run it through a hosted provider such as OpenRouter. Check the license before commercial use.

What are the downsides of MiniMax M2.1?

The main trade-offs: 204K context, smaller than 19.7% of the coding-agent requests we measured; Superseded by MiniMax M3. It's strongest for short, tool-heavy agent steps on a tight budget.