Skip to content
OhMyGPT

MiniMax M2.5

MiniMax's flagship M2.5 model (230B MoE, 10B active). Production-level agent model with function calling, structured output, and reasoning.

Try in ChatCompare
Input price
$0.33
Output price
$1.32
Context
205K
Max output
66K
Modalities
InputTextOutputText
147 (#57 of 75)
1359
—
Released
2026-02-12
Knowledge cutoff
2025-06

Providers

Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.

Pricing

All prices for this model, by service tier.

ItemStandardPriorityFlex
Inputper 1M tokens$0.33$0.5775$0.165
Outputper 1M tokens$1.32$2.31$0.66

Make a request

Set your provider preferences, then copy the request. It reads your API key from OHMYGPT_API_KEY.

Later turns reuse the provider’s prompt cache, which can lower cost and latency.

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Similar models

Other models with the same output types at a similar price.

  • Better value: more capable, lower price
  • Pareto frontier
  • This model

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

MiniMax M2.5This model
147
Input
$0.33
Output
$1.32
MiniMax M2
—
Input
$0.33
Output
$1.32
Codestral
—
Input
$0.33
Output
$0.99
GLM-5.3-FlashX
—
Input
$0.3212
Output
$1.1242
Tencent Hunyuan Role Latest
—
Input
$0.3504
Output
$1.4016

Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-10-28): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text