Models

GPT-oss-120b vs MiMo-V2.5

API price, context window, capabilities and live speed, side by side.

MiMo-V2.5 is about 1.5× cheaper than GPT-oss-120b at a typical 3:1 input-to-output token mix. MiMo-V2.5 has the larger context window (1.1M vs 131K tokens). Only MiMo-V2.5 supports image input; GPT-oss-120b does not. Only MiMo-V2.5 supports tool calling; GPT-oss-120b does not. Both run on the same UltraGPT API key, so you can switch between them by changing the model field - or list both in models: [...] for automatic fallback.

GPT-oss-120bMiMo-V2.5
LabOpenAIXiaomi (MiMo)
Model idgpt-oss-120bmimo-v2.5
Input / 1M tokens$0.15$0.14
Cached input / 1M$0.075$0.0048
Output / 1M tokens$0.6$0.28
Context window131K1.1M
Inputtexttext, audio, image, video
Outputtexttext
Tool calling—✓
Vision (image input)—✓
Reasoning——

Cost of 1,000 requests

Estimated from the list prices above; your real cost is reported per request in usage.cost.

Chatbot1.5K tokens in, 400 outGPT-oss-120b $0.47MiMo-V2.5 $0.32
RAG over documents20K in, 800 outGPT-oss-120b $3.48MiMo-V2.5 $3.02
Coding agent step40K in (80% cached), 1.5K outGPT-oss-120b $4.50MiMo-V2.5 $1.69

Use both, with automatic fallback

Same key, same endpoint: change the model id between "gpt-oss-120b" and "mimo-v2.5".

curl https://api.ultragpt.pro/v1/chat/completions \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "models": ["mimo-v2.5"],
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

FAQ

Which is cheaper, GPT-oss-120b or MiMo-V2.5?

GPT-oss-120b: $0.15 in / $0.6 out per 1M. MiMo-V2.5: $0.14 in / $0.28 out per 1M. Prices are in USD and billed per use from your UltraGPT balance.

Can I use GPT-oss-120b and MiMo-V2.5 with the same API key?

Yes. Both are available through the OpenAI-compatible UltraGPT API at https://api.ultragpt.pro/v1: set model to "gpt-oss-120b" or "mimo-v2.5".

Which has a bigger context window, GPT-oss-120b or MiMo-V2.5?

GPT-oss-120b: 131,072 tokens. MiMo-V2.5: 1,050,000 tokens.

More comparisons