serves endpoints · 2026-08-14

Venice

Official site · 🇺🇸 United States

Plan

Venice (Free / Pro / Pro Plus / Max)

Tier	$/month	Included usage
Free	$0.00	$0.00
Pro	$18.00	$1.00
Pro Plus	$68.00	$75.00
Max	$200.00	$225.00

console only quota converts to units

As advertised. Free: 10 text prompts/day. Pro: unlimited text + 100 credits/month. Pro Plus: 7,500 credits/month. Max: 22,500 credits/month

What that actually means. Credits convert at a published, flat 100 credits = $1, so the allowance turns into dollars of API usage directly: $1 on Pro, $75 on Pro Plus, $225 on Max. That makes the two upper tiers worth more in credits than the subscription costs.

Where to check what is left. account dashboard

Models covered. serves open models it hosts; credits also cover video, music and image generation

Unusual among inference hosts, which almost all bill purely per token. API access is included on every paid tier and the credits cover API calls, so this is a subscription that genuinely substitutes for metered billing rather than a consumer chat plan bolted on beside it. Pro Plus banks unused credits for 2 months, Max for 3. READ THE TIERS CAREFULLY: Pro at $18 carries only $1 of credits, because what you are buying there is unlimited text prompts in the web interface, not API volume. For API work only Pro Plus and Max make sense, and both return more in credits than they cost -- $75 for $68 and $225 for $200. A value table ranking on credits alone makes Pro look far worse than it is for its actual purpose.

checked 2026-08-13 · high (official pricing page) · source

Models it serves

21 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.

Model	Quant	$/M in	$/M out	Context	Uptime 30m
Qwen3.5-9B	fp8	$0.10	$0.15	256,000	100.0%
Mistral Small 3.2	fp8	$0.09	$0.25	256,000	99.9%
Nemotron 3.5 Lightning	fp4	$0.10	$0.25	1,000,000	100.0%
Gemma 4 31B	bf16	$0.12	$0.36	256,000	96.5%
Gemma 4 26B A4B	bf16	$0.13	$0.40	256,000	99.0%
DeepSeek V4 Flash	unknown	$0.17	$0.35	1,000,000	97.0%
Qwen3.6 35B A3B	fp8	$0.10	$0.95	256,000	100.0%
Mistral Small 4	fp8	$0.19	$0.75	256,000	100.0%
DeepSeek V3.2	unknown	$0.33	$0.48	160,000	91.8%
MiniMax-M3	fp8	$0.30	$1.20	524,288	99.8%
Qwen3.5-35B-A3B	unknown	$0.31	$1.25	256,000	97.7%
GLM 4.6	fp4	$0.43	$1.75	198,000	100.0%
Qwen3.6 27B	fp8	$0.33	$3.25	256,000	100.0%
GLM 4.7	fp4	$0.55	$2.65	198,000	98.9%
Nemotron 3 Ultra 550B	fp8	$0.62	$3.12	256,000	87.4%
Kimi K2.5	unknown	$0.56	$3.50	256,000	100.0%
Kimi K2.6	int4	$0.75	$3.50	256,000	81.4%
Kimi K2.7 Code	int4	$0.75	$3.50	256,000	100.0%
Qwen3.5 397B A17B	unknown	$0.75	$4.50	128,000	—
GLM-5.2	fp8	$1.40	$4.40	1,000,000	98.9%
GLM-5.1	fp8	$1.54	$4.84	200,000	99.4%

◆ Some links on this page are referral links: if you sign up through them this site may earn a commission, at no extra cost to you. Rankings, prices and measurements are taken from the sources listed under Method, and are not influenced by whether a provider has a referral programme.