MiniMax M2.5 with Jev
MiniMax M2.5 is a model from MiniMax, released 2026-02-12. It costs $0.270 per million input tokens and $1.08 per million output tokens, reads up to 205K tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to minimax/minimax-m2.5.
- Input price
- $0.270 / 1M
- Output price
- $1.08 / 1M
- Context window
- 205K tokens
- Max output
- 128K tokens
- Cached input
- $0.027 / 1M
- Released
- 2026-02-12
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 62% of the 332 priced models we can call cost more.
Using MiniMax M2.5 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 M2.5 does the answering when Jev sends it work, or when you name it yourself. At list price MiniMax M2.5 falls in the llm11-fast 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-m2.5 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for MiniMax M2.5 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.
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.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00035 | $0.351 |
| Question over retrieved documents | 4,000 / 500 | $0.00162 | $1.62 |
| Long document summary | 30,000 / 1,000 | $0.00918 | $9.18 |
Cheaper models to try
The catalogue has no benchmark score for MiniMax M2.5, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| OpenAI GPT-5.4 Nano | $0.200 | $1.25 | 400K | |
| DeepSeek DeepSeek V3 | $0.257 | $1.03 | 164K | |
| OpenAI GPT-5.6 Luna | $0.200 | $1.20 | 1.05M | |
| OpenAI GPT-5.6 Luna Pro | $0.200 | $1.20 | 1.05M |
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-m2.5",
messages=[{"role": "user", "content": "Hello"}],
)More from MiniMax
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| MiniMax M3 | $0.300 | $1.20 | 1.05M | |
| MiniMax M2.7 | $0.210 | $0.840 | 205K | |
| MiniMax M2-her | $0.300 | $1.20 | 66K | |
| MiniMax M2.1Retires 2026-10-08 | $0.300 | $1.20 | 205K | |
| MiniMax M2 | $0.300 | $1.20 | 205K | |
| MiniMax M1 | $0.400 | $2.20 | 1M |
Questions
- What is MiniMax M2.5 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 M2.5 does the answering when Jev sends it work, or when you name it yourself. At list price MiniMax M2.5 falls in the llm11-fast 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-m2.5 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is MiniMax M2.5 a System One model?
- No. MiniMax M2.5 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 M2.5 cost?
- $0.270 per million input tokens and $1.08 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00162, so a thousand of them is about $1.62. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the MiniMax M2.5 context window?
- 204,800 tokens, with up to 128,000 tokens in a single reply.
- Does MiniMax M2.5 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use MiniMax M2.5 through llm11?
- Yes. Set model to minimax/minimax-m2.5 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to MiniMax M2.5?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price MiniMax M2.5 falls in the llm11-fast 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-m2.5 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to MiniMax M2.5?
- Nearest in price and below it: OpenAI GPT-5.4 Nano at $0.200 in and $1.25 out, DeepSeek DeepSeek V3 at $0.257 in and $1.03 out and OpenAI GPT-5.6 Luna at $0.200 in and $1.20 out. The catalogue has no benchmark score for MiniMax M2.5, so this is a price ordering. It does not claim these answer as well.