UniAiX

Unified API gateway providing access to multiple large language models with OpenAI-compatible endpoints.

UniAiX offers 93 LLM API models.

API pricing per token ranges from $0.020 to $75.00/M (input).

Speed benchmark average: 158 tok/s.

Avg Speed158.01 tok/s

Latency9.77 s

Updated4/18/2026

Created At2/25/2026

Recharge Rate¥7.30 per $1 quota

DrawingTaskData Export

Model Pricing

Pricing for 93 models (group: default, updated: 6/4/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
text-embedding-3-small	$0.020	$0.020	0.01	1
doubao-seed-1-6-flash-250828	$0.021	$0.205	0.0102739725	10
qwen-turbo-latest	$0.041	$0.411	0.02054795	10
gpt-5-nano	$0.050	$0.400	0.025	8
qwen-flash	$0.050	$0.400	0.025	8
qwen-long-latest	$0.068	$0.274	0.034247	4
doubao-seed-2-0-lite-260215	$0.082	$0.493	0.04109589	6
gemini-2.5-flash-lite	$0.100	$0.400	0.05	4
doubao-seed-1-6-251015	$0.110	$0.274	0.05479452	2.5
doubao-seed-1-8-251228	$0.110	$0.274	0.05479452	2.5
text-embedding-3-large	$0.130	$0.130	0.065	1
deepseek-v4-flash	$0.137-2%	$0.274-2%	0.06849315	2
DeepSeek-V4-Flash-global	$0.140	$0.280	0.07	2
gpt-4o-mini	$0.150	$0.600	0.075	4
grok-4-1-fast-reasoning	$0.200	$0.500	0.1	2.5
grok-4-1-fast-non-reasoning	$0.200	$0.500	0.1	2.5
gpt-5-mini	$0.250	$2.00	0.125	8
gemini-3.1-flash-lite	$0.250	$1.50	0.125	6
gemini-3.1-flash-lite-preview	$0.250	$1.50	0.125	6
gpt-5.1-codex-mini	$0.250	$2.00	0.125	8

Showing 20 of 93 models.