mimo-v2.5 API
Call mimo-v2.5 through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.
Xiaomi MiMoChatReasoningCodingVision26.0
Intelligence index
60.2
Coding index
21.3
Agentic index
Pricing
Input$0.12 / 1M tokens (¥0.77)
Output$0.24 / 1M tokens (¥1.55)
Output multiplier×2.00
Context window1M tokens
Max output131K tokens
Prices are per 1M tokens in USD · ¥6.5 = $1 · Billed in CNY
Xiaomi MiMo
MiMo models are compact by design and their capability comes from training efficiency rather than raw scale, which shows up as a very low price per million tokens.
When to use it
At $0.12 per 1M input tokens it sits far below the catalogue median of $0.69 — a cost-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.
Code
from openai import OpenAI
client = OpenAI(
base_url="https://starseaapi.com/v1",
api_key="sk-your-key"
)
r = client.chat.completions.create(
model="mimo-v2.5",
messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)Other models from this provider
| Models | Input $/M | Output $/M | Intelligence index | Coding index |
|---|---|---|---|---|
| mimo-v2.6-flash | $0.15 | $0.31 | 37.9 | — |
| mimo-v2.6-pro | $0.46 | $0.92 | 46.3 | — |