LLM and Model Providers

mibyan setup --portal     # fresh install — OAuth + provider + gateway in one command
mibyan model              # existing install — pick "Nous Portal" from the list
mibyan portal info        # inspect login + routing at any time

# With an API key (pay-per-token)
export ANTHROPIC_API_KEY=***
mibyan chat --provider anthropic --model claude-sonnet-4-6

# Preferred: authenticate through `mibyan model`
# Mibyan will use Claude Code's credential store directly when available
mibyan model

# Manual override with a setup-token (fallback / legacy)
export ANTHROPIC_TOKEN=***  # setup-token or manual OAuth token
mibyan chat --provider anthropic

# Auto-detect Claude Code credentials (if you already use Claude Code)
mibyan chat --provider anthropic  # reads Claude Code credential files automatically

model:
  provider: "anthropic"
  default: "claude-sonnet-4-6"

mibyan chat --provider copilot --model gpt-5.4

mibyan chat --provider copilot-acp --model copilot-acp
# Requires the GitHub Copilot CLI in PATH and an existing `copilot login` session

model:
  provider: "copilot"
  default: "gpt-5.4"

# Fireworks AI
mibyan chat --provider fireworks --model accounts/fireworks/models/kimi-k2p6
# Requires: FIREWORKS_API_KEY in ~/.mibyan/.env

# NovitaAI Model API
mibyan chat --provider novita --model moonshotai/kimi-k2.5
# Requires: NOVITA_API_KEY in ~/.mibyan/.env

# Ramp Router (model IDs come from your account's live catalog)
mibyan chat --provider router --model gpt-5.4-mini
# Requires: RAMP_ROUTER_API_KEY in ~/.mibyan/.env

# z.ai / ZhipuAI GLM
mibyan chat --provider zai --model glm-5
# Requires: GLM_API_KEY in ~/.mibyan/.env

# Kimi / Moonshot AI (international: api.moonshot.ai)
mibyan chat --provider kimi-coding --model kimi-for-coding
# Requires: KIMI_API_KEY in ~/.mibyan/.env

# Kimi / Moonshot AI (China: api.moonshot.cn)
mibyan chat --provider kimi-coding-cn --model kimi-k2.5
# Requires: KIMI_CN_API_KEY in ~/.mibyan/.env

# MiniMax (global endpoint)
mibyan chat --provider minimax --model MiniMax-M2.7
# Requires: MINIMAX_API_KEY in ~/.mibyan/.env

# MiniMax (China endpoint)
mibyan chat --provider minimax-cn --model MiniMax-M2.7
# Requires: MINIMAX_CN_API_KEY in ~/.mibyan/.env

# Qwen Cloud / DashScope (Qwen models)
mibyan chat --provider alibaba --model qwen3.5-plus
# Requires: DASHSCOPE_API_KEY in ~/.mibyan/.env

# Xiaomi MiMo
mibyan chat --provider xiaomi --model mimo-v2-pro
# Requires: XIAOMI_API_KEY in ~/.mibyan/.env

# Tencent TokenHub (Hy4 preview)
mibyan chat --provider tencent-tokenhub --model hy4-preview
# Requires: TOKENHUB_API_KEY in ~/.mibyan/.env

# Tencent TokenPlan (Hy4 preview via Anthropic Messages endpoint)
mibyan chat --provider tencent-tokenplan --model hy4-preview
# Requires: TOKENPLAN_API_KEY in ~/.mibyan/.env

# Arcee AI (Trinity models)
mibyan chat --provider arcee --model trinity-large-thinking
# Requires: ARCEEAI_API_KEY in ~/.mibyan/.env

# Meta Model API (Muse Spark family)
mibyan chat --provider meta-ai --model muse-spark-1.2
# Requires: MODEL_API_KEY in ~/.mibyan/.env

# GMI Cloud
# Use the exact model ID returned by GMI's /v1/models endpoint.
mibyan chat --provider gmi --model zai-org/GLM-5.1-FP8
# Requires: GMI_API_KEY in ~/.mibyan/.env

# Nebius Token Factory
mibyan chat --provider nebius --model deepseek-ai/DeepSeek-V4-Pro
# Requires: NEBIUS_API_KEY in ~/.mibyan/.env

model:
  provider: "gmi"
  default: "zai-org/GLM-5.1-FP8"

mibyan migrate xai          # preview replacements
mibyan migrate xai --apply  # rewrite ~/.mibyan/config.yaml in place

# Use any available model
mibyan chat --provider novita --model moonshotai/kimi-k2.5
# Requires: NOVITA_API_KEY in ~/.mibyan/.env

# Short alias
mibyan chat --provider novita-ai --model deepseek/deepseek-v3-0324

model:
  provider: "novita"
  default: "moonshotai/kimi-k2.5"
  base_url: "https://api.novita.ai/openai/v1"

mibyan model
# → pick "Ollama Cloud"
# → paste your OLLAMA_API_KEY
# → select from discovered models (gpt-oss:120b, glm-4.6:cloud, qwen3-coder:480b-cloud, etc.)

model:
  provider: "ollama-cloud"
  default: "gpt-oss:120b"

# Simplest — named profile in ~/.aws/credentials
mibyan chat --provider bedrock --model us.anthropic.claude-sonnet-4-6

# Or with explicit env vars
AWS_PROFILE=myprofile AWS_REGION=us-east-1 mibyan chat --provider bedrock --model us.anthropic.claude-sonnet-4-6

model:
  provider: "bedrock"
  default: "us.anthropic.claude-sonnet-4-6"
bedrock:
  region: "us-east-1"          # or set AWS_REGION
  # profile: "myprofile"       # or set AWS_PROFILE
  # discovery: true            # auto-discover region from IAM
  # guardrail:                 # optional Bedrock Guardrails
  #   guardrail_identifier: "your-guardrail-id"
  #   guardrail_version: "DRAFT"

# Service account JSON (recommended for servers / gateways)
echo "VERTEX_CREDENTIALS_PATH=/path/to/service-account.json" >> ~/.mibyan/.env
# or Application Default Credentials
gcloud auth application-default login

mibyan model   # → "Google Vertex AI" → project → region → model

model:
  provider: "vertex"
  default: "google/gemini-3-flash-preview"   # Vertex requires the google/ prefix
vertex:
  project_id: "my-gcp-project"   # blank → use the project embedded in the credentials
  region: "global"               # required for the Gemini 3.x previews

mibyan model
# → pick "Qwen OAuth (Portal)"
# → browser opens; sign in with your Alibaba account
# → confirm — credentials are saved to ~/.mibyan/auth.json

mibyan chat   # uses portal.qwen.ai/v1 endpoint

model:
  provider: "qwen-oauth"
  default: "qwen3-coder-plus"

model:
  provider: alibaba_coding     # alias for alibaba-coding-plan
  model: qwen3-coder-plus

mibyan chat --provider alibaba_coding --model qwen3-coder-plus

mibyan model
# → pick "MiniMax (OAuth)"
# → browser opens; sign in with your MiniMax account (global or CN region)
# → confirm — credentials are saved to ~/.mibyan/auth.json

mibyan chat   # uses api.minimax.io/anthropic endpoint

model:
  provider: "minimax-oauth"
  default: "MiniMax-M2.7"

# Cloud (build.nvidia.com)
mibyan chat --provider nvidia --model nvidia/nemotron-3-super-120b-a12b
# Requires: NVIDIA_API_KEY in ~/.mibyan/.env

# Local NIM endpoint — override base URL
NVIDIA_BASE_URL=http://localhost:8000/v1 mibyan chat --provider nvidia --model nvidia/nemotron-3-super-120b-a12b

model:
  provider: "nvidia"
  default: "nvidia/nemotron-3-super-120b-a12b"

# GMI Cloud
mibyan chat --provider gmi --model deepseek-ai/DeepSeek-V3.2
# Requires: GMI_API_KEY in ~/.mibyan/.env

model:
  provider: "gmi"
  default: "deepseek-ai/DeepSeek-V3.2"

# Hosted relay (ACTUAL_API_KEY in ~/.mibyan/.env)
mibyan chat --provider actual --model <model-id-from-your-cluster>

# Local daemon (model.base_url in ~/.mibyan/config.yaml, no key)
mibyan chat --provider actual --model <installed-model-name>

model:
  provider: "actual"
  default: "<model-id>"
  base_url: "http://127.0.0.1:8080/v1" # Omit for the hosted relay.

# StepFun
mibyan chat --provider stepfun --model step-3.5-flash
# Requires: STEPFUN_API_KEY in ~/.mibyan/.env

model:
  provider: "stepfun"
  default: "step-3.5-flash"

# Use any available model
mibyan chat --provider huggingface --model Qwen/Qwen3.5-397B-A17B
# Requires: HF_TOKEN in ~/.mibyan/.env

# Short alias
mibyan chat --provider hf --model deepseek-ai/DeepSeek-V3.2

model:
  provider: "huggingface"
  default: "Qwen/Qwen3.5-397B-A17B"

mibyan model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter: API base URL, API key, Model name

# In ~/.mibyan/config.yaml
model:
  default: your-model-name
  provider: custom
  base_url: http://localhost:8000/v1
  api_key: your-key-or-leave-empty-for-local
  # key_env: MY_PROVIDER_API_KEY  # env var holding the key (alternative to api_key)

/model custom:qwen-2.5          # Switch to a model on your custom endpoint
/model custom                    # Auto-detect the model from the endpoint
/model openrouter:claude-sonnet-4 # Switch back to a cloud provider

/model custom:local:qwen-2.5    # Use the "local" custom provider with model qwen-2.5
/model custom:work:llama3       # Use the "work" custom provider with llama3

# Install and run a model
ollama pull qwen2.5-coder:32b
ollama serve   # Starts on port 11434

mibyan model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter URL: http://localhost:11434/v1
# Skip API key (Ollama doesn't need one)
# Enter model name (e.g. qwen2.5-coder:32b)

model:
  default: qwen2.5-coder:32b
  provider: custom
  base_url: http://localhost:11434/v1
  context_length: 64000   # See warning below

ollama ps
# Look at the CONTEXT column — it should show your configured value

pip install vllm
vllm serve meta-llama/Llama-3.1-70B-Instruct \
  --port 8000 \
  --max-model-len 65536 \
  --tensor-parallel-size 2 \
  --enable-auto-tool-choice \
  --tool-call-parser mibyan

mibyan model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter URL: http://localhost:8000/v1
# Skip API key (or enter one if you configured vLLM with --api-key)
# Enter model name: meta-llama/Llama-3.1-70B-Instruct

pip install "sglang[all]"
python -m sglang.launch_server \
  --model meta-llama/Llama-3.1-70B-Instruct \
  --port 30000 \
  --context-length 65536 \
  --tp 2 \
  --tool-call-parser qwen

mibyan model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter URL: http://localhost:30000/v1
# Enter model name: meta-llama/Llama-3.1-70B-Instruct

# Build and start llama-server
cmake -B build && cmake --build build --config Release
./build/bin/llama-server \
  --jinja -fa \
  -c 64000 \
  -ngl 99 \
  -m models/qwen2.5-coder-32b-instruct-Q4_K_M.gguf \
  --port 8080 --host 0.0.0.0

mibyan model
# Select "Custom endpoint (self-hosted / VLLM / etc.)"
# Enter URL: http://localhost:8080/v1
# Skip API key (local servers don't need one)
# Enter model name — or leave blank to auto-detect if only one model is loaded

lms server start                        # Starts on port 1234
lms load qwen2.5-coder --context-length 64000

mibyan model
# Select "LM Studio"
# Press Enter to use http://localhost:1234/v1
# Pick one of the discovered models
# If LM Studio server auth is enabled, enter LM_API_KEY when prompted

mibyan config set model.lmstudio_load_mode jit

mibyan config set model.lmstudio_load_mode explicit

# Get the Windows host IP (the default gateway of WSL2's virtual network)
ip route show | grep -i default | awk '{ print $3 }'
# Example output: 172.29.192.1

model:
  default: qwen2.5-coder:32b
  provider: custom
  base_url: http://172.29.192.1:11434/v1   # Windows host IP, not localhost

# Run in Admin PowerShell — replace PORT with your server's port
New-NetFirewallRule -DisplayName "Allow WSL2 to Model Server" -Direction Inbound -Action Allow -Protocol TCP -LocalPort 11434

# Replace URL with your server's address and port
curl http://localhost:11434/v1/models          # Mirrored mode
curl http://172.29.192.1:11434/v1/models       # NAT mode (use your actual host IP)

# Check what Mibyan thinks the context is
# Look at startup line: "Context limit: X tokens"

# Check your server's actual context
# Ollama: ollama ps (CONTEXT column)
# llama.cpp: curl http://localhost:8080/props | jq '.default_generation_settings.n_ctx'
# vLLM: check --max-model-len in startup args

model:
  default: your-model
  provider: custom
  base_url: http://localhost:11434/v1
  context_length: 64000

# Install and start
pip install "litellm[proxy]"
litellm --model anthropic/claude-sonnet-4 --port 4000

# Or with a config file for multiple models:
litellm --config litellm_config.yaml --port 4000

model_list:
  - model_name: "best"
    litellm_params:
      model: anthropic/claude-sonnet-4
      api_key: sk-ant-...
  - model_name: "best"
    litellm_params:
      model: openai/gpt-4o
      api_key: sk-...
router_settings:
  routing_strategy: "latency-based-routing"

# Install and start
npx @blockrun/clawrouter    # Starts on port 8402

model:
  default: meta-llama/Llama-3.1-70B-Instruct-Turbo
  provider: custom
  base_url: https://api.together.xyz/v1
  api_key: your-together-key

model:
  default: "qwen3.5:9b"
  base_url: "http://localhost:8080/v1"
  context_length: 131072  # tokens

providers:
  my-local-llm:
    api: "http://localhost:11434/v1"
    models:
      qwen3.5:27b:
        context_length: 64000
      deepseek-r1:70b:
        context_length: 65536

providers:
  local:
    api: http://localhost:8080/v1
    # api_key omitted — Mibyan uses "no-key-required" for keyless local servers
  work:
    api: https://gpu-server.internal.corp/v1
    key_env: CORP_API_KEY
    transport: chat_completions   # set explicitly by `mibyan model` → Custom Endpoint wizard; auto-detection still happens as a fallback
  anthropic-proxy:
    api: https://proxy.example.com/anthropic
    key_env: ANTHROPIC_PROXY_KEY
    transport: anthropic_messages  # for Anthropic-compatible proxies

providers:
  my-gateway:
    base_url: "https://gateway.internal.example.com/v1"
    api_mode: chat_completions
    key_cmd: "my-auth-cli print-token --profile prod"

providers:
  gemma-local:
    api: http://localhost:8080/v1
    default_model: google/gemma-4-31b-it
    extra_body:
      enable_thinking: true
      reasoning_effort: high

extra_body:
  chat_template_kwargs:
    enable_thinking: true

extra_body:
  chat_template_kwargs:
    enable_thinking: false

model:
  provider: custom
  base_url: http://localhost:8080/v1
  default: qwen3.6-35b-a3b
  supports_vision: true   # send images natively; otherwise vision_analyze pre-describes them

providers:
  my-gateway:
    api: https://gateway.example.com/v1
    key_env: GATEWAY_API_KEY
    catalog_provider: deepseek   # metadata lookups use DeepSeek's catalog entries

/model custom:local:qwen-2.5       # Use the "local" endpoint with qwen-2.5
/model custom:work:llama3-70b      # Use the "work" endpoint with llama3-70b
/model custom:anthropic-proxy:claude-sonnet-4  # Use the proxy

# ~/.mibyan/config.yaml
providers:
  together:
    api: https://api.together.xyz/v1
    key_env: TOGETHER_API_KEY
    # transport: chat_completions  # default — no need to set

model:
  default: MiniMaxAI/MiniMax-M2.7   # or any model from together.ai/models
  provider: custom:together

# ~/.mibyan/.env
TOGETHER_API_KEY=your-together-key

/model custom:together:meta-llama/Llama-3.3-70B-Instruct-Turbo
/model custom:together:google/gemma-4-31b-it
/model custom:together:deepseek-ai/DeepSeek-V3

# ~/.mibyan/config.yaml
providers:
  groq:
    api: https://api.groq.com/openai/v1
    key_env: GROQ_API_KEY

model:
  default: llama-3.3-70b-versatile
  provider: custom:groq

# ~/.mibyan/.env
GROQ_API_KEY=your-groq-key

# ~/.mibyan/config.yaml
providers:
  perplexity:
    api: https://api.perplexity.ai
    key_env: PERPLEXITY_API_KEY

model:
  default: sonar
  provider: custom:perplexity

# ~/.mibyan/.env
PERPLEXITY_API_KEY=your-perplexity-key

providers:
  together:
    api: https://api.together.xyz/v1
    key_env: TOGETHER_API_KEY
  groq:
    api: https://api.groq.com/openai/v1
    key_env: GROQ_API_KEY
  perplexity:
    api: https://api.perplexity.ai
    key_env: PERPLEXITY_API_KEY

model:
  default: MiniMaxAI/MiniMax-M2.7
  provider: custom:together      # boot to Together; switch freely after

provider_routing:
  sort: "throughput"          # "price" (default), "throughput", or "latency"
  # only: ["anthropic"]      # Only use these providers
  # ignore: ["deepinfra"]    # Skip these providers
  # order: ["anthropic", "google"]  # Try providers in this order
  # require_parameters: true  # Only use providers that support all request params
  # data_collection: "deny"   # Exclude providers that may store/train on data
  # models:                   # Per-model pins (same keys; unset keys fall through)
  #   "openai/gpt-6-astra": {only: ["openai"]}
  #   "anthropic/claude-fable-5.1": {only: ["anthropic"]}

model:
  provider: openrouter
  model: openrouter/pareto-code

openrouter:
  min_coding_score: 0.65   # 0.0–1.0; higher = stronger (more expensive) coders. Default 0.65.

fallback_providers:
  - provider: openrouter
    model: anthropic/claude-sonnet-4
  - provider: anthropic
    model: claude-sonnet-4
    # base_url: http://localhost:8000/v1    # optional, for custom endpoints
    # api_mode: chat_completions           # optional override (`transport:` is an accepted alias)

fallback_model:
  provider: openrouter
  model: anthropic/claude-sonnet-4