中文 | English

Grok2API rebuilt with FastAPI, fully aligned with the latest web call format. Supports streaming and non-streaming chat, image generation/editing, deep thinking, token pool concurrency, and automatic load balancing.

• Local development

uv sync

uv run main.py

• Deployment

git clone https://github.com/chenyme/grok2api

docker compose up -d

URL: http://<host>:8000/admin
Default password: grok2api (config key app.app_key, change it in production).

Variable	Description	Default	Example
LOG_LEVEL	Log level	INFO	DEBUG
SERVER_HOST	Bind address	0.0.0.0	0.0.0.0
SERVER_PORT	Service port	8000	8000
SERVER_WORKERS	Uvicorn worker count	1	2
SERVER_STORAGE_TYPE	Storage type (local/redis/mysql/pgsql)	local	pgsql
SERVER_STORAGE_URL	Storage URL (empty for local)	""	postgresql+asyncpg://user:password@host:5432/db

MySQL example: mysql+aiomysql://user:password@host:3306/db (if you set mysql://, it will be normalized to mysql+aiomysql://)

• Basic account: 80 requests / 20h
• Super account: not tested by the author

Model	Cost	Account	Chat	Image	Video
grok-3	1	Basic/Super	Yes	Yes	-
grok-3-fast	1	Basic/Super	Yes	Yes	-
grok-4	1	Basic/Super	Yes	Yes	-
grok-4-mini	1	Basic/Super	Yes	Yes	-
grok-4-fast	1	Basic/Super	Yes	Yes	-
grok-4-heavy	4	Super	Yes	Yes	-
grok-4.1	1	Basic/Super	Yes	Yes	-
grok-4.1-thinking	4	Basic/Super	Yes	Yes	-
grok-imagine-1.0	4	Basic/Super	-	Yes	-
grok-imagine-1.0-video	-	Basic/Super	-	-	Yes

Generic endpoint: chat, image generation, image editing, video generation, video upscaling

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GROK2API_API_KEY" \
  -d '{
    "model": "grok-4",
    "messages": [{"role":"user","content":"Hello"}]
  }'

Supported request parameters

Field	Type	Description	Allowed values
model	string	Model ID	-
messages	array	Message list	developer, system, user, assistant
stream	boolean	Enable streaming	true, false
thinking	string	Thinking mode	enabled, disabled, null
video_config	object	Video model only	-
└─ aspect_ratio	string	Video aspect ratio	16:9, 9:16, 1:1, 2:3, 3:2
└─ video_length	integer	Video length (seconds)	6, 10
└─ resolution_name	string	Resolution	480p, 720p
└─ preset	string	Style preset	fun, normal, spicy

Note: any other parameters will be discarded and ignored.

Image endpoint: image generation, image editing

curl http://localhost:8000/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GROK2API_API_KEY" \
  -d '{
    "model": "grok-imagine-1.0",
    "prompt": "A cat floating in space",
    "n": 1
  }'

Supported request parameters

Field	Type	Description	Allowed values
model	string	Image model ID	grok-imagine-1.0
prompt	string	Prompt	-
n	integer	Number of images	1 - 10 (streaming: 1 or 2 only)
stream	boolean	Enable streaming	true, false

Note: any other parameters will be discarded and ignored.

Config file: data/config.toml

Module	Field	Key	Description	Default
app	app_url	App URL	External access URL for Grok2API (used for file links).	http://127.0.0.1:8000
	app_key	Admin password	Password for the Grok2API admin panel (required).	grok2api
	api_key	API key	Token for calling Grok2API (optional).	""
	image_format	Image format	Output image format (url or base64).	url
	video_format	Video format	Output video format (html tag or processed url).	html
grok	temporary	Temporary chat	Enable temporary conversation mode.	true
	stream	Streaming	Enable streaming by default.	true
	thinking	Thinking chain	Enable model thinking output.	true
	dynamic_statsig	Dynamic fingerprint	Enable dynamic Statsig value generation.	true
	filter_tags	Filter tags	Auto-filter special tags in Grok responses.	["xaiartifact", "xai:tool_usage_card", "grok:render"]
	timeout	Timeout	Timeout for Grok requests (seconds).	120
	base_proxy_url	Base proxy URL	Base service address proxying Grok official site.	""
	asset_proxy_url	Asset proxy URL	Proxy URL for Grok static assets (images/videos).	""
	cf_clearance	CF Clearance	Cloudflare clearance cookie for verification.	""
	max_retry	Max retries	Max retries on Grok request failure.	3
	retry_status_codes	Retry status codes	HTTP status codes that trigger retry.	[401, 429, 403]
	retry_backoff_base	Backoff base	Base delay for retry backoff (seconds).	0.5
	retry_backoff_factor	Backoff factor	Exponential multiplier for retry backoff.	2.0
	retry_backoff_max	Backoff max	Max wait per retry (seconds).	30.0
	retry_budget	Backoff budget	Max total retry time per request (seconds).	90.0
	stream_idle_timeout	Stream idle timeout	Idle timeout for streaming responses (seconds).	45.0
	video_idle_timeout	Video idle timeout	Idle timeout for video generation (seconds).	90.0
token	auto_refresh	Auto refresh	Enable automatic token refresh.	true
	refresh_interval_hours	Refresh interval	Token refresh interval (hours).	8
	fail_threshold	Failure threshold	Consecutive failures before a token is disabled.	5
	save_delay_ms	Save delay	Debounced save delay for token changes (ms).	500
	reload_interval_sec	Consistency refresh	Token state refresh interval in multi-worker setups (sec).	30
cache	enable_auto_clean	Auto clean	Enable cache auto clean; cleanup when exceeding limit.	true
	limit_mb	Cleanup threshold	Cache size threshold (MB) that triggers cleanup.	1024
performance	nsfw_max_concurrent	NSFW enable concurrency	Concurrency cap for enabling NSFW in batch. Recommended 10.	10
	nsfw_batch_size	NSFW enable batch size	Batch size for enabling NSFW. Recommended 50.	50
	nsfw_max_tokens	NSFW enable max tokens	Max tokens per NSFW batch to avoid mistakes. Recommended 1000.	1000
	usage_max_concurrent	Token usage refresh concurrency	Concurrency cap for batch usage refresh. Recommended 25.	25
	usage_batch_size	Token usage refresh batch size	Batch size for usage refresh. Recommended 50.	50
	usage_max_tokens	Token usage refresh max tokens	Max tokens per usage refresh batch. Recommended 1000.	1000
	assets_max_concurrent	Online assets find/delete concurrency	Concurrency cap for online asset find/delete. Recommended 25.	25
	assets_batch_size	Online assets find/delete batch size	Batch size for online asset find/delete. Recommended 10.	10
	assets_max_tokens	Online assets find/delete max tokens	Max tokens per online asset find/delete batch. Recommended 1000.	1000
	assets_delete_batch_size	Online assets delete batch	Batch concurrency for online asset deletion. Recommended 10.	10
	media_max_concurrent	Media concurrency	Concurrency cap for video/media generation. Recommended 50.	50