PackyAPI

codex-api.packycode.com

LMSpeed tracks PackyAPI API pricing, model coverage, speed tests, and uptime signals for codex-api.packycode.com.

PackyAPI (codex-api.packycode.com) is an OpenAI-compatible API relay for Codex and other models via a single interface.

PackyAPI offers 48 LLM API models.

API pricing per token ranges from $0.0014 to $8.57/M (input).

Speed benchmark average: 78 tok/s.

Avg Speed77.79 tok/s

Latency8.40 s

Updated6/8/2026

Created At1/5/2026

Recharge Rate¥1.00 per $1 quota

DrawingTaskData Export

Main Endpoint
https://www.packyapi.com
Stable and reliable, suitable for production environments
Optimized Route Endpoint
https://api-slb.packyapi.com
Optimized route, suitable for latency-sensitive scenarios
Endpoint 3Historical / Unverified
https://codex-api.packycode.com
Endpoint 4Historical / Unverified
https://codex-api-slb.packycode.com

Model Pricing

Pricing for 48 models (group: cc, updated: 6/8/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
omni-moderation-latestFixed	$0.0014	$0.0014	0	0
gpt-image-2Fixed	$0.0057	$0.0057	0	0
gemini-3.1-flash-image-previewFixed	$0.0096	$0.0096	0	0
gemini-2.5-flash-imageFixed	$0.010	$0.010	0	0
qwen3-vl-flash	$0.043	$0.429	0.075	10
qwen3.5-flash	$0.057	$0.571	0.1	10
gemini-2.5-flash	$0.086	$0.714	0.15	8.333333
gemini-2.5-flash-thinking	$0.086	$0.714	0.15	8.333333
gemini-3-flash-preview	$0.143-71%	$0.857-71%	0.25	6
mimo-v2-flash	$0.200	$0.600	0.35	3
gpt-5.4-mini	$0.214-71%	$1.29-71%	0.375	6
qwen3.5-plus	$0.229	$1.37	0.4	6
deepseek-v4-flash	$0.286	$0.571	0.5	2
qwen3-coder-next	$0.286	$1.14	0.5	4
claude-haiku-4-5-20251001	$0.286-77%	$1.43-71%	0.5	5
mimo-v2.5	$0.286-21%	$0.571-68%	0.5	2
gemini-2.5-pro	$0.357-71%	$2.86-71%	0.625	8
gpt-5.3-codex	$0.500-71%	$4.00-71%	0.875	8
qwen3.6-plus	$0.571	$3.43	1	6
gemini-3.1-pro-preview	$0.571-71%	$3.43-71%	1	6

Showing 20 of 48 models.