VSLLM

VSLLM provides API access to various AI models through a marketplace, offering services for developers and businesses.

VSLLM offers 86 LLM API models.

API pricing per token ranges from $0.0002 to $24.86/M (input).

Speed benchmark average: 335 tok/s.

Avg Speed334.56 tok/s

Latency10.76 s

Total Tests50

Models8

Updated4/17/2026

Created At3/8/2026

Claim this provider

HVerified by hanrin yany

Model Pricing

Pricing for 86 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
claude-neptune-v3	Free	Free	0	0
mimo-v2-pro-free	$0.0002	$0.0010	0.00005	5
glm-5[free]	$0.0002	$0.0002	0.00005	1
gemini-3.1-flash-imageFixed	$0.0010	$0.0010	0	0
gemini-3-flash-preview[codex]Fixed	$0.0050	$0.0050	0	0
grok-4.20-betaFixed	$0.015	$0.015	0	0
claude-opus-4.6Fixed	$0.025	$0.025	0	0
glm-5.1-code-planFixed	$0.025	$0.025	0	0
test1Fixed	$0.025	$0.025	0	0
gemini-3.1-pro[codex]Fixed	$0.025	$0.025	0	0
gpt-5.2[codex]Fixed	$0.025	$0.025	0	0
claude-opus-4-7[svip]Fixed	$0.025	$0.025	0	0
gpt-5.3-codexFixed	$0.025	$0.025	0	0
glm-5.1[test]Fixed	$0.025	$0.025	0	0
gpt-5.3-codex-sparkFixed	$0.025	$0.025	0	0
claude-opus-4-7[codex]Fixed	$0.025	$0.025	0	0
claude-opus-4-6-thinking[codex]Fixed	$0.025	$0.025	0	0
glm-5-turbo[test]Fixed	$0.025	$0.025	0	0
gpt-5.4[codex]Fixed	$0.025	$0.025	0	0
claude-opus-4-6-thinking[max20]Fixed	$0.025	$0.025	0	0

Showing 20 of 86 models.