Providers

Maki talks to LLM providers over their HTTP APIs. Models are split into three tiers: weak (cheap and fast), medium (balanced), and strong (highest capability, highest cost).

Open the model picker with /model and press Alt+1, Alt+2, or Alt+3 on any row to reassign it to strong, medium, or weak. Your overrides are saved to ~/.maki/model-tiers and apply across sessions.

Auth Reloading

Maki re-reads auth from storage and environment variables each time a new agent spawns (/new, retry, session load). If you run maki auth login in another terminal or change an env var, the next session picks it up without a restart.

Built-in Providers

Anthropic

Env var: ANTHROPIC_API_KEY
API: https://api.anthropic.com/v1/messages
Features: Prompt caching, thinking mode (adaptive/budgeted), advanced tool use

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	claude-3-haiku, claude-3-5-haiku, claude-haiku-4-5 (default)	$0.25 / $1.25	200K ctx / 4K out
Medium	claude-3-sonnet, claude-3-5-sonnet, claude-3-7-sonnet, claude-sonnet-4, claude-sonnet-4-5, claude-sonnet-4-6-1m, claude-sonnet-4-6 (default)	$3.00 / $15.00	200K ctx / 4K out
Strong	claude-opus-4-5, claude-opus-4-7-1m, claude-opus-4-7 (default), claude-opus-4-6-1m, claude-opus-4-6, claude-3-opus, claude-opus-4-0, claude-opus-4-1	$5.00 / $25.00	200K ctx / 64K out

Defaults: claude-haiku-4-5 (weak), claude-sonnet-4-6 (medium), claude-opus-4-7 (strong)

Amazon Bedrock

If you already use Claude through AWS Bedrock, you can point Maki at it instead of the direct Anthropic API. Set CLAUDE_CODE_USE_BEDROCK=1 and Maki will route all Anthropic requests through Bedrock. The same models, the same features, just a different door.

You will need AWS_REGION and one of the following for auth:

Method	Env vars
IAM credentials	`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` (and optionally `AWS_SESSION_TOKEN`)
Credentials file	`AWS_PROFILE` (defaults to `default`), reads `~/.aws/credentials`
Bearer token	`AWS_BEARER_TOKEN_BEDROCK`
Gateway proxy	`CLAUDE_CODE_SKIP_BEDROCK_AUTH=1` + `ANTHROPIC_BEDROCK_BASE_URL` (skips signing, useful behind a proxy that handles auth)

You can override the model with ANTHROPIC_MODEL and the endpoint with ANTHROPIC_BEDROCK_BASE_URL. These env var names match Claude Code, so if you were already using Bedrock there, the same setup works here.

OpenAI

Env var: OPENAI_API_KEY (also supports OAuth device flow)
API: https://api.openai.com/v1

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	gpt-5.4-nano (default), gpt-5.4-mini, gpt-4.1-nano	$0.20 / $1.25	400K ctx / 128K out
Medium	gpt-4.1-mini, gpt-4.1 (default), o4-mini, gpt-5.1-codex-mini	$0.40 / $1.60	1047K ctx / 32K out
Strong	gpt-5.5 (default), gpt-5.4, o3, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex	$5.00 / $30.00	1050K ctx / 128K out

Defaults: gpt-5.4-nano (weak), gpt-4.1 (medium), gpt-5.5 (strong)

Google

Env var: GEMINI_API_KEY
API: https://generativelanguage.googleapis.com/v1beta
Features: Native Gemini API with thinking support

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	gemini-2.0-flash-lite (default)	$0.07 / $0.30	1048K ctx / 65K out
Medium	gemini-2.5-flash (default)	$0.15 / $0.60	1048K ctx / 65K out
Strong	gemini-2.5-pro (default)	$1.25 / $5.00	1048K ctx / 65K out

Defaults: gemini-2.5-pro (strong), gemini-2.5-flash (medium), gemini-2.0-flash-lite (weak)

Copilot

Env var: GH_COPILOT_TOKEN or ~/.config/github-copilot/{hosts.json,apps.json}
API: https://api.githubcopilot.com (or GraphQL-discovered Copilot API endpoint)
Features: Native Copilot Chat HTTP API with model endpoint discovery

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	gpt-5-mini, gpt-5 mini, claude-haiku-4.5 (default)	$0.00 / $0.00	200K ctx / 100K out
Medium	gpt-5.2, gpt-4.1, claude-sonnet-4.5 (default)	$0.00 / $0.00	200K ctx / 100K out
Strong	gpt-5.4, gpt-5.3-codex, claude-opus-4.6, grok-code-fast-1 (default)	$0.00 / $0.00	200K ctx / 100K out

Defaults: gpt-5-mini (weak), gpt-5.2 (medium), gpt-5.4 (strong)

Ollama

Env var: OLLAMA_HOST for local/remote (e.g. http://localhost:11434), OLLAMA_API_KEY for auth
API: http://localhost:11434/v1
Features: Local or remote inference via OLLAMA_HOST, cloud fallback via OLLAMA_API_KEY

This provider talks the OpenAI-compatible /v1 API, so it also works with llama.cpp's server, LocalAI, or anything else that speaks the same protocol. Just point OLLAMA_HOST to the right address (e.g. http://localhost:8080 for llama.cpp).

Maki asks the server for the list of installed models, so there's no built-in catalog. Tiers are guessed from list order: the first model becomes strong, the second medium, and the rest weak. If that guess is wrong, open /model and press Alt+1, Alt+2, or Alt+3 on any row to reassign it. Your choices are saved to ~/.maki/model-tiers.

Mistral

Env var: MISTRAL_API_KEY
API: https://api.mistral.ai/v1

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	mistral-small-latest, mistral-small-2603 (default)	$0.15 / $0.60	262K ctx / 262K out
Medium	mistral-large-latest, mistral-large-2512 (default)	$0.50 / $1.50	262K ctx / 262K out
Strong	devstral-latest, devstral-medium-latest, devstral-2512 (default)	$0.40 / $2.00	262K ctx / 262K out

Defaults: devstral-latest (strong), mistral-large-latest (medium), mistral-small-latest (weak)

Z.AI

Env var: ZHIPU_API_KEY (shared across both endpoints)
API endpoints:
- https://api.z.ai/api/paas/v4
- https://api.z.ai/api/coding/paas/v4

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	glm-4.7-flash (default), glm-4.5-flash, glm-4.5-air	$0.00 / $0.00	200K ctx / 131K out
Medium	glm-4.7, glm-4.6 (default), glm-4.5	$0.60 / $2.20	200K ctx / 131K out
Strong	glm-5-code (default), glm-5	$1.20 / $5.00	200K ctx / 131K out

Defaults: glm-5-code (strong), glm-4.7-flash (weak), glm-4.7 (medium)

DeepSeek

Env var: DEEPSEEK_API_KEY
API: https://api.deepseek.com
Features: Thinking mode toggle (on/off), open-weight models

Tier	Models	Pricing (in/out per 1M tokens)	Context
Medium	deepseek-v4-flash (default)	$0.14 / $0.28	1000K ctx / 384K out
Strong	deepseek-v4-pro (default)	$0.43 / $0.87	1000K ctx / 384K out

Defaults: deepseek-v4-flash (medium), deepseek-v4-pro (strong)

Synthetic

Env var: SYNTHETIC_API_KEY
API: https://api.synthetic.new/openai/v1
Features: Reasoning effort support (low/medium/high), open-weight models

Tier	Models	Pricing (in/out per 1M tokens)	Context
Weak	hf:zai-org/GLM-4.7-Flash (default)	$0.10 / $0.50	200K ctx / 131K out
Medium	hf:deepseek-ai/DeepSeek-V3.2 (default)	$0.56 / $1.68	200K ctx / 131K out
Strong	hf:moonshotai/Kimi-K2.5 (default)	$0.45 / $3.40	200K ctx / 131K out

Defaults: hf:moonshotai/Kimi-K2.5 (strong), hf:deepseek-ai/DeepSeek-V3.2 (medium), hf:zai-org/GLM-4.7-Flash (weak)

Model Identifiers

Models are referenced as provider/model_id:

anthropic/claude-sonnet-4-6
openai/gpt-4.1
zai/glm-4.7

If the model name is unique across providers, the prefix can be omitted.

Dynamic Providers

To add a custom provider or proxy, drop an executable script into ~/.maki/providers/. The script must handle these subcommands:

Subcommand	Timeout	What it does
`info`	5s	Return JSON with `display_name`, `base` provider, `has_auth`
`models`	5s	Return JSON array of model entries (optional)
`resolve`	30s	Return auth JSON (`base_url`, `headers`)
`login`	interactive	OAuth or credential flow
`logout`	interactive	Clear credentials
`refresh`	30s	Refresh auth tokens

resolve is called each time a new agent spawns, so scripts should read tokens from disk instead of caching them in memory. That way auth changes from other processes get picked up.

The base field specifies which built-in provider to inherit the model catalog from. Valid values: anthropic, openai, google, copilot, ollama, mistral, zai, zai-coding-plan, deepseek, synthetic.

If your provider serves models not in the base catalog, add a models subcommand returning:

[{"id": "my-model-v2", "tier": "strong", "context_window": 200000, "max_output_tokens": 16384}]

Only id is required. Optional fields: tier (default medium), context_window (128K), max_output_tokens (16K), pricing ({input, output, cache_write, cache_read}, all per 1M tokens), supports_tool_examples (defaults to the base provider's setting). The first model listed per tier is used for sub-agents. Without this subcommand, the base provider's models are used.

Dynamic provider models are namespaced as {slug}/{model_id} (e.g. myproxy/claude-sonnet-4-6).

Script Name Rules

Must start with a letter or digit
Only letters, digits, underscores, and hyphens after that
Can't reuse a built-in provider's slug
Must be executable