Seamee API

Seamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.

Seamee API offers 695 LLM API models.

API pricing per token ranges from $0.010 to $75.00/M (input).

Speed benchmark average: 96 tok/s.

Seamee API is an API aggregator, offering models from multiple vendors.

Avg Speed96.09 tok/s

Latency4.32 s

Total Tests87

Models7

Updated4/17/2026

Created At1/28/2026

Model Pricing

Pricing for 695 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
meta/llama-3.2-1b-instruct	$0.010	$0.010	0.005	1
Qwen/Qwen3-Embedding-4B	$0.010	$0.010	0.005	1
google/gemma-2-2b-it	$0.020	$0.060	0.01	3
google/gemma-3n-e4b-it	$0.020	$0.040	0.01	2
text-embedding-3-small	$0.020	$0.040	0.01	2
openai/gpt-oss-20b	$0.020	$0.100	0.01	5
meta/llama-3.2-3b-instruct	$0.020	$0.020	0.01	1
meta/llama-3.1-8b-instruct	$0.025	$0.025	0.0125	1
qwen/qwen2.5-coder-7b-instruct	$0.030	$0.090	0.015	3
Qwen/Qwen2.5-Coder-32B-Instruct	$0.030	$0.110	0.015	3.6666667
google/gemma-3-27b-it	$0.030	$0.110	0.015	3.6666667
google/gemma-2-9b-it	$0.030	$0.090	0.015	3
deepseek-ai/DeepSeek-R1-Distill-Llama-70B	$0.030	$0.110	0.015	3.6666667
google/gemma-3-12b-it	$0.040	$0.130	0.02	3.25
google/gemma-3-4b-it	$0.040	$0.080	0.02	2
Qwen/Qwen3-14B	$0.050	$0.220	0.025	4.4
gpt-oss-20b	$0.050	$0.200	0.025	4
Qwen/Qwen2.5-VL-32B-Instruct	$0.050	$0.220	0.025	4.4
Qwen/Qwen2.5-7B-Instruct	$0.050	$0.050	0.025	1
openai/gpt-oss-120b	$0.050	$0.250	0.025	5

Showing 20 of 695 models.