MiniMax · Open-weight
MiniMax M2.5 API Member pricing vs list price
minimax/minimax-m2.5
Open-weightMiniMax M2.5 is an open-weight model from MiniMax with a 204K-token context window. It lists at $0.27 input and $0.95 output per 1M tokens, and Members pay $0.2295 and $0.8075 with a Private key.
MiniMax M2.5 prices per 1M tokens
Input / output, by membership tier and data policy. Every price is a percent of the provider's public list price.
| Tier | Private | Research ShareFinancial incentive notice |
|---|---|---|
| List price | $0.27 input, $0.95 output per 1M tokens | |
| Guest | Not on Guest (data sharing required) | $0.2565 input, $0.9025 output per 1M tokens5% off list price |
| Member | $0.2295 input, $0.8075 output per 1M tokens15% off list price | $0.216 input, $0.76 output per 1M tokens20% off list price |
| Executive | $0.2025 input, $0.7125 output per 1M tokens25% off list price | $0.189 input, $0.665 output per 1M tokens30% off list price |
Does Member pay for itself on MiniMax M2.5?
- Member ($199 a year) pays for itself once your MiniMax M2.5 spend at list price passes $111 a month with a Private key (about 251M tokens at a 3:1 input-to-output mix) or $82.92 a month with Research Share.
- Executive ($1,999 a year) costs less than Member above $1,500 a month (Private keys), about 3.4B tokens a month.
- Guests already pay 5% below list here with no fee; against that price, Member Research Share pays for itself above $111 a month.
At this volume Guest saves $2.20 a month against list price.
| Plan | Usage / mo | Fee / mo | Net vs list / mo | Pays off above |
|---|---|---|---|---|
| Guest | $41.80 | Free | $2.20 | No fee |
| Member · Private | $37.40 | $16.58 | −$9.98 | 251M tokens |
| Member · Research Share | $35.20 | $16.58 | −$7.78 | 188M tokens |
| Executive · Private | $33.00 | $167 | −$156 | 1.5B tokens |
| Executive · Research Share | $30.80 | $167 | −$153 | 1.3B tokens |
Usage at each plan's price per token. The fee is the annual membership fee divided by 12 and covers every model, so spend on other models counts toward it too.
Specs
| Provider | MiniMax |
|---|---|
| Model type | Open-weight |
| Context window | 204,800 tokens (204K) |
| Input and output | Text in, text out (chat completions) |
| Model ID | minimax/minimax-m2.5 |
| Endpoint | POST https://api.bearer.club/v1/chat/completions |
| Plans | Guest (Research Share), Member, Executive |
| List price per 1M tokens | $0.27 input, $0.95 output |
List price rank: 31st lowest input price and 25th lowest output price of the 69 models. Its context window is larger than 5 of them.
Where MiniMax M2.5 fits
MiniMax M2.5 is a general chat model, a common choice for chat, drafting, summarization and question answering. By list price at a 3:1 input-to-output mix it is in the middle-priced third of the 69 models on Bearer Club.
Its 204,800-token window fits long documents in one request; inputs beyond that need splitting.
It is open-weight, so Guests can call it at 5% below list with Research Share and no membership fee (usage is paid from prepaid credit), and signed-in users can try it in the free Playground.
Bearer Club does not publish benchmark scores. Test MiniMax M2.5 on your own prompts before you move traffic to it.
What 1,000 requests cost
Example request shapes, priced per 1,000 requests from the per-token prices above.
| Request (input / output tokens) | List price | Guest | Member Private | Executive Private |
|---|---|---|---|---|
| Short chat reply1,000 / 300 | $0.56 | $0.53 | $0.47 | $0.42 |
| Document summary20,000 / 1,000 | $6.35 | $6.03 | $5.40 | $4.76 |
| Long-context read200,000 / 2,000 | $55.90 | $53.11 | $47.52 | $41.93 |
Related models
- MiniMax M2.7
$0.30 input / $1.20 output at list, 19% more than MiniMax M2.5 at a 3:1 mix; 204K-token context; open-weight, on the Guest plan.
- MiniMax M3
$0.30 input / $1.20 output at list, 19% more than MiniMax M2.5 at a 3:1 mix; 1M-token context; open-weight, on the Guest plan.
- Qwen3 Coder 480B A35B
$0.30 input / $1.00 output at list, 8% more than MiniMax M2.5 at a 3:1 mix; 262K-token context; open-weight, on the Guest plan.
- DeepSeek V3.2
$0.259 input / $0.80 output at list, 10% cheaper than MiniMax M2.5 at a 3:1 mix; 163K-token context; open-weight, on the Guest plan.
Data policy for this model
Private: Your prompts and outputs are never used for training and never shared or licensed. For security, abuse prevention and debugging we store request and response content, encrypted, and delete it after 30 days; error details may be kept longer. We also keep usage details (model, tokens, cost, latency, status and time). The model provider may keep requests briefly for abuse monitoring under its own terms.
Research Share: available. Opt in per key and pay less. Data from that key will be used to accelerate AGI and supplied to top frontier labs for AGI purposes, and only for traffic after you opt in.
Regions
Each model is served only in the regions its provider supports. Per-model region details are not published yet.
Use MiniMax M2.5 with the OpenAI SDK
Change two settings: point the SDK at https://api.bearer.club/v1 and use your Bearer Club key, then pass minimax/minimax-m2.5 as the model.
curl https://api.bearer.club/v1/chat/completions \ -H "Authorization: Bearer $BEARER_CLUB_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax/minimax-m2.5", "messages": [{"role": "user", "content": "Hello from the Club!"}] }'import osfrom openai import OpenAIclient = OpenAI( base_url="https://api.bearer.club/v1", api_key=os.environ["BEARER_CLUB_API_KEY"], # your membership card)resp = client.chat.completions.create( model="minimax/minimax-m2.5", messages=[{"role": "user", "content": "Hello from the Club!"}],)print(resp.choices[0].message.content)import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://api.bearer.club/v1", apiKey: process.env.BEARER_CLUB_API_KEY, // your membership card});const resp = await client.chat.completions.create({ model: "minimax/minimax-m2.5", messages: [{ role: "user", content: "Hello from the Club!" }],});console.log(resp.choices[0].message.content);The official OpenAI SDKs and most OpenAI-compatible tools, such as Cursor, Cline, Continue, Open WebUI and LiteLLM, work the same way; the name of the base URL setting varies by tool.
MiniMax M2.5 FAQ
How much does MiniMax M2.5 cost on Bearer Club?
MiniMax M2.5 lists at $0.27 input and $0.95 output per 1M tokens. Members pay $0.2295 / $0.8075 with a Private key and $0.216 / $0.76 with Research Share; Executives pay $0.2025 / $0.7125 and $0.189 / $0.665. Guests pay $0.2565 / $0.9025 with Research Share.
Can Guests use MiniMax M2.5?
Yes. MiniMax M2.5 is open-weight, so Guests can call it with Research Share at $0.2565 input and $0.9025 output per 1M tokens (5% below list). There is no membership fee, but API calls are paid from a prepaid balance, so add credit first. Signed-in users can also try it free in the Playground.
When does Member pay for itself on MiniMax M2.5?
Member ($199 a year) pays for itself above about $111 a month of MiniMax M2.5 spend at list price with a Private key, or $82.92 a month with Research Share. The fee is shared across every model you call, so spend on other models counts too.
What context window does MiniMax M2.5 support?
204,800 tokens, roughly 150,000 English words. The prompt and the answer together have to fit in it.
What is the model id for MiniMax M2.5 on Bearer Club?
Use minimax/minimax-m2.5 as the model in requests to https://api.bearer.club/v1/chat/completions. The same id appears in the https://api.bearer.club/v1/models list.
Further reading
- Replicate alternatives for developers watching token costs
Replicate alternatives compared: Bearer Club gives you Claude, GPT, Llama and DeepSeek on one OpenAI-compatible key at member prices. Verified prices inside.
- OpenAI-compatible API explained: one key for 69 models
OpenAI-compatible API: change base_url and api_key to reach 69 models including GPT-6, Claude, DeepSeek, and Gemini through Bearer Club at member prices.
Discounts are measured against each provider's public list price and vary by model, membership tier and data policy. See Pricing.