llm11

MiniMax M2.1 with Jev

MiniMax M2.1 is a model from MiniMax, released 2025-12-23. It costs $0.300 per million input tokens and $1.20 per million output tokens, reads up to 205K tokens of context, and writes up to 131,072 tokens in one reply. Through llm11, set model to minimax/minimax-m2.1.

The catalogue lists 2026-10-08 as the date MiniMax M2.1 stops being served.

Input price
$0.300 / 1M
Output price
$1.20 / 1M
Context window
205K tokens
Max output
131K tokens
Cached input
$0.030 / 1M

Read from the provider's prompt cache

Released
2025-12-23
Accepts
text

Read from the live catalogue and refreshed daily. At blended list price, 58% of the 332 priced models we can call cost more.

Using MiniMax M2.1 with Jev

Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. MiniMax M2.1 does the answering when Jev sends it work, or when you name it yourself. At list price MiniMax M2.1 falls in the llm11-balanced band, but no pack routes to it because MiniMax is not one of the labs the packs draw from. You can still pin it: pass minimax/minimax-m2.1 as model and routing steps aside while verification still runs.

Jev is new, so we have not published results for MiniMax M2.1 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.

About JevThe System One router

What a request costs

List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.

RequestTokens in / outOneA thousand
Short chat turn500 / 200$0.00039$0.390
Question over retrieved documents4,000 / 500$0.00180$1.80
Long document summary30,000 / 1,000$0.010$10.20

Cheaper models to try

The catalogue has no benchmark score for MiniMax M2.1, so this is a price ordering. It does not claim these answer as well.

Cheaper alternatives to MiniMax M2.1
ModelInput / 1MOutput / 1MContext
DeepSeek DeepSeek V3 0324$0.290$1.14164K
DeepSeek DeepSeek V3.1 Terminus$0.300$1.00164K
Qwen Qwen3 Coder 480B A35B$0.300$1.00262K
OpenAI GPT-5.4 Nano$0.200$1.25400K

Call it

Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.

python

from openai import OpenAI

client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")

res = client.chat.completions.create(
    model="minimax/minimax-m2.1",
    messages=[{"role": "user", "content": "Hello"}],
)

More from MiniMax

Other MiniMax models
ModelInput / 1MOutput / 1MContext
MiniMax M3$0.300$1.201.05M
MiniMax M2.7$0.210$0.840205K
MiniMax M2.5$0.270$1.08205K
MiniMax M2-her$0.300$1.2066K
MiniMax M2$0.300$1.20205K
MiniMax M1$0.400$2.201M

All 8 MiniMax models

Questions

What is MiniMax M2.1 with Jev?
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. MiniMax M2.1 does the answering when Jev sends it work, or when you name it yourself. At list price MiniMax M2.1 falls in the llm11-balanced band, but no pack routes to it because MiniMax is not one of the labs the packs draw from. You can still pin it: pass minimax/minimax-m2.1 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
Is MiniMax M2.1 a System One model?
No. MiniMax M2.1 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
How much does MiniMax M2.1 cost?
$0.300 per million input tokens and $1.20 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00180, so a thousand of them is about $1.80. llm11 passes provider list price through and charges 5% when you buy credits.
What is the MiniMax M2.1 context window?
204,800 tokens, with up to 131,072 tokens in a single reply.
Does MiniMax M2.1 support tool calling and structured output?
The catalogue lists tool calling, structured output and reasoning controls.
Can I use MiniMax M2.1 through llm11?
Yes. Set model to minimax/minimax-m2.1 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
Does Jev route to MiniMax M2.1?
Routing decisions are made by Jev, TypeSafe AI's System One model. At list price MiniMax M2.1 falls in the llm11-balanced band, but no pack routes to it because MiniMax is not one of the labs the packs draw from. You can still pin it: pass minimax/minimax-m2.1 as model and routing steps aside while verification still runs.
What is a cheaper alternative to MiniMax M2.1?
Nearest in price and below it: DeepSeek DeepSeek V3 0324 at $0.290 in and $1.14 out, DeepSeek DeepSeek V3.1 Terminus at $0.300 in and $1.00 out and Qwen Qwen3 Coder 480B A35B at $0.300 in and $1.00 out. The catalogue has no benchmark score for MiniMax M2.1, so this is a price ordering. It does not claim these answer as well.
Is MiniMax M2.1 being retired?
The catalogue lists 2026-10-08 as the date it stops being served. Move traffic before then.