impulse

MiniMax M2.5

Open weights

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

API id MiniMax-M2.5Released 12 Feb 2026 (Feb 2026)
Input / 1M
$0.30
at MiniMax
Output / 1M
$1.20
at MiniMax
Context window
1M
tokens
Max output
8K
tokens per reply
Hosts
9
23 listings
Released
Feb 2026
12 Feb 2026

Pricing

List prices at MiniMax, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.30$1.20
Cached input
90% off input
$0.03
Cache write, 5 minutes$0.375

What it costs a month

At MiniMax list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$156
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$122
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$205
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Use your own numbers

Where to run it

9 hosts serve MiniMax M2.5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
MiniMaxLab API
MiniMax-M2.5
$0.30 / $1.20
MiniMax-M2.5
$0.30 / $1.20
minimax-m2.5
$0.30 / $1.20
minimax.minimax-m2.5
$0.30 / $1.20
BasetenInference
MiniMax-M2.5
$0.30 / $1.20
GMI CloudInference
MiniMax-M2.5
$0.30 / $1.20
MiniMax-M2.5
$0.30 / $1.20
Novita AIInference
minimax-m2.5
$0.30 / $1.20
minimax-m2.5
$0.419 / $1.68
+40% vs headline
Show 14 more listings: regions, snapshots and variants
Amazon Bedrock
us-east-1
minimax.minimax-m2.5
$0.30 / $1.20
us-east-2
minimax.minimax-m2.5
$0.30 / $1.20
us-west-2
minimax.minimax-m2.5
$0.30 / $1.20
Mantle
minimax.minimax-m2.5
$0.30 / $1.20
ap-southeast-2
minimax.minimax-m2.5
$0.31 / $1.24
+3% vs headline
ap-northeast-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
ap-south-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
ap-southeast-3
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
eu-north-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
eu-central-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
eu-west-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
eu-south-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
sa-east-1
minimax.minimax-m2.5
$0.36 / $1.44
+20% vs headline
eu-west-2
minimax.minimax-m2.5
$0.47 / $1.86
+56% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching
Open weights
License: Apache-2.0
Runs in about 548.9 GB of GPU memory
Runtimes: SGLang, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than MiniMax.

Smaller MiniMax models

No cheaper MiniMax model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    12% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    62% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    62% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    50% less

Open-weight picks

  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    8% less
  • Beam 1.0 501B A23B
    Independent · on W&B Inference
    $0.30 / $1.00
    Has every key capability
    10% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    17% less
  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    25% less

Model line

Newer and older versions, at each lab's own price.

  1. May 2026MiniMax M3Latest$0.30 / $1.20
  2. Mar 2026MiniMax M2.7$0.21 / $0.84
  3. Feb 2026MiniMax M2.5This page$0.30 / $1.20
  4. UndatedMiniMax M2.1$0.30 / $1.20
  5. UndatedMiniMax M2$0.30 / $1.20

Call it

Using MiniMax's API.

Python
from litellm import completion

response = completion(
    model="minimax/MiniMax-M2.5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does MiniMax M2.5 cost?

On MiniMax, MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input costs $0.03 per million tokens.

Which APIs offer MiniMax M2.5?

MiniMax M2.5 runs on 9 APIs: MiniMax, Tensormesh, StreamLake, Amazon Bedrock, Baseten, GMI Cloud, Nebius AI Studio, Novita AI and Kyma API.

What is MiniMax M2.5's context window?

1M tokens, with up to 8K tokens in one reply.

Is MiniMax M2.5 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of MiniMax M2.5?

Yes. MiniMax M3 is the newest model in this line, released on 31 May 2026.

What are cheaper alternatives to MiniMax M2.5?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (12% less), Claude Haiku 5.5 on Anthropic (62% less) and Qwen3.7 Plus on Replicate (8% less). Savings are on a mix of 3 input tokens to 1 output token.

When was MiniMax M2.5 released?

MiniMax released it on 12 Feb 2026.

What is MiniMax M2.5's API model id?

Use MiniMax-M2.5 with MiniMax. Other hosts use their own ids: minimax-m2.5 on StreamLake, minimax.minimax-m2.5 on Amazon Bedrock, minimax-m2.5 on Novita AI, minimax-m2.5 on Kyma API.

Sources

Raw catalog entry for MiniMax-M2.5 on MiniMax
{
  "input_cost_per_token": 3e-7,
  "output_cost_per_token": 0.0000012,
  "cache_read_input_token_cost": 3e-8,
  "cache_creation_input_token_cost": 3.75e-7,
  "litellm_provider": "minimax",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_system_messages": true,
  "max_input_tokens": 1000000,
  "max_output_tokens": 8192
}