Skip to main content

Default Model: MiMo-V2-Pro

MiMo-V2-Pro is Xiaomi’s flagship foundation model and the default model for all Agentbot deployments.
  • 1T+ parameters — Exceptional reasoning and generation quality
  • 1M context length — Entire codebases in context, no chunking needed
  • #1 in Programming — Top-ranked in standard benchmarks
  • Built for Agents — Deeply optimized for agentic workflows
  • 100% uptime — Reliable Xiaomi infrastructure

MiMo-V2-Pro Pricing

TierInputOutputCache Read
≤256K tokens$1/M$3/M$0.20/M
>256K tokens$2/M$6/M$0.40/M

Specs

SpecValue
Total Context1.05M tokens
Max Output131.1K tokens
Parameters1T+ total
Latency2.8s
Throughput34 tps
ProviderXiaomi (via OpenRouter)
ReleasedMarch 18, 2026

Benchmark Rankings

BenchmarkRank
Programming#1
Academia#18
Legal#21
SEO#32
Roleplay#43

Supported Models

Agentbot supports 300+ models via OpenRouter. BYOK (Bring Your Own Key) — you pay providers directly with zero markup.
ModelInputOutputBest For
MiMo-V2-Pro$1/M$3/MDefault — agents, coding, long context
Claude Sonnet 4$3/M$15/MComplex reasoning, analysis
GPT-4o$2.5/M$10/MGeneral purpose, vision
Gemini 2.5 Flash$0.15/M$0.60/MFast, cost-effective
DeepSeek R1$0.55/M$2.19/MReasoning, math

Free Models

ModelCostNotes
Gemini 2.0 FlashFree150 RPM limit
Gemma 3NFreeGood for testing

Full Pricing Table

ModelInput (per 1K tokens)Output (per 1K tokens)
Gemini 2.0 FlashFreeFree
Groq Llama 3£0.0002£0.0002
Gemini 1.5 Flash£0.0001£0.0005
MiMo-V2-Pro$1/M$3/M
GPT-4o Mini£0.0003£0.0012
Claude 3 Haiku£0.0002£0.0010
GPT-4o£0.0022£0.0088
Claude Sonnet 4$3/M$15/M
DeepSeek R1$0.55/M$2.19/M

Plan Model Access

Different plans unlock different model sets:
PlanModels Available
Solo (£29)MiMo-V2-Pro, GPT-4o Mini, Gemini Flash, Claude 3.5 Sonnet
Collective (£69)+ GPT-4o, GPT-4 Turbo, Claude 3 Opus
Label (£149)+ DeepSeek R1, extended models
Network (£499)All models (wildcard access)

BYOK (Bring Your Own Key)

Agentbot is BYOK — you connect your own API keys from AI providers. We charge zero markup on model usage.

Supported Providers

  • OpenRouter — 300+ models, one key
  • Anthropic — Direct Claude access
  • OpenAI — Direct GPT access
  • Google — Direct Gemini access
  • Ollama — Local models, free

Getting an OpenRouter Key

  1. Go to openrouter.ai
  2. Create an account
  3. Go to Keys → Create Key
  4. Add credits (minimum $5)
  5. Copy key to Agentbot dashboard

Key Security

  • API keys are encrypted at rest
  • Never shared with third parties
  • Can be rotated at any time
  • Deleted on account removal

Model Selection

From Dashboard

  1. Go to Settings → Models
  2. Select your preferred model
  3. Your agent uses it for all new conversations

From Config

{
  "models": {
    "default": "openrouter/xiaomi/mimo-v2-pro",
    "fallbacks": ["openrouter/anthropic/claude-sonnet-4"]
  }
}

Per-Conversation

Override the default model for specific conversations via the chat interface.

FAQ

Q: Why MiMo-V2-Pro as default? A: Best balance of quality, context length (1M), and cost. #1 in programming benchmarks, purpose-built for agents. Q: Can I use a different default? A: Yes — change it in Settings → Models anytime. Q: Do you mark up model prices? A: No. Zero markup. You pay providers directly at their rates. Q: What if my model goes down? A: Fallback models automatically kick in. Configure fallbacks in your agent settings.