Venice
Explore Venice models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Venicevenice
These privacy labels describe Venice, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Venice |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://venice.ai/ |
| Models | 59 public models |
| Credits routes | 59 |
| Zero data retention | no |
| Verified confidential inference | Not verified |
| Policy note | Mixed model-specific posture. TrustedRouter cannot independently verify a complete chain from a live Venice endpoint through immutable source and hardware measurements to committed model weights. Venice is therefore not tracked as confidential or E2EE. Exact routes marked Private in Venice's live catalog qualify only as policy-backed ZDR through endpoint-specific records; Anonymized routes do not. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
181 samplesContinuously sampled across Venice's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 3388 ms |
|---|---|
| Effective throughput | 95 tok/s n=3 |
| Uptime | 99.45% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| qwen/qwen-3-8-flash | 3388 ms | — | 98.97% | — | 97 |
| meta-llama/llama-3.2-3b | 1078 ms | — | 100.00% | — | 4 |
| moonshotai/kimi-k3 | 1140 ms | 95 tok/s n=1 | 100.00% | — | 1 |
| minimax/minimax-m3-preview | 1270 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.7-flash | 1277 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-6 | 1357 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2-5 | 1524 ms | — | 100.00% | — | 2 |
| qwen/qwen3-6-35b-a3b | 1629 ms | — | 100.00% | — | 1 |
| qwen/qwen3-235b-a22b-instruct-2507 | 1653 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 1673 ms | 145 tok/s n=1 | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b | 1699 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2-7-code | 1991 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.7 | 2011 ms | — | 100.00% | — | 2 |
| qwen/qwen3-next-80b | 2222 ms | — | 100.00% | — | 1 |
| qwen/qwen3-5-35b-a3b | 2786 ms | — | 100.00% | — | 1 |
| qwen/qwen-3-7-max | 2854 ms | — | 100.00% | — | 2 |
| z-ai/glm-5v-turbo | 3216 ms | — | 100.00% | — | 2 |
| z-ai/glm-4.6 | 3488 ms | — | 100.00% | — | 1 |
| qwen/qwen-3-6-plus | 3537 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.1 | 9276 ms | — | 100.00% | — | 2 |
| google/gemma-4-uncensored | — | — | 100.00% | — | 56 |
| deepseek/deepseek-v4-pro-0423 | — | 45 tok/s n=1 | — | — | 0 |
Venice performance history · Full provider & model leaderboard.
Models served by Venice.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
alibaba/wan-2.7Alibaba Wan 2.7 |
— | 5,000 | selected route | Not published | selected route |
bytedance/seedance-2.0ByteDance Seedance 2.0 |
— | 10,000 | selected route | Not published | selected route |
bytedance/seedance-2.0-fastByteDance Seedance 2.0 Fast |
— | 10,000 | selected route | Not published | selected route |
bytedance/seedance-2.5ByteDance Seedance 2.5 |
— | 15,000 | selected route | Not published | selected route |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 102#105 | 163,840 | $0.34815/1M | $0.1688/1M | $0.5064/1M |
deepseek/deepseek-v4-1-flashDeepSeek V4.1 Flash |
— | 1,000,000 | $0.3165/1M | $0.01/1M | $1.266/1M |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.13715/1M | $0.02954/1M | $0.2743/1M |
deepseek/deepseek-v4-flash-0731-fastDeepSeek V4 Flash 0731 Fast |
— | 1,000,000 | $0.36925/1M | $0.092313/1M | $0.7385/1M |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 124#29 | 1,048,576 | $1.74075/1M | $0.34815/1M | $3.482555/1M |
deepseek/deepseek-v4-pro-0423DeepSeek V4 Pro 0423 |
— | 1,048,576 | $1.74075/1M | $0.34815/1M | $3.482555/1M |
google/gemini-omni-flashGoogle Gemini Omni Flash |
— | 1,048,576 | selected route | Not published | selected route |
google/gemma-4-uncensoredGemma 4 Uncensored |
— | 256,000 | $0.171438/1M | Not published | $0.5275/1M |
google/veo-3.1Google Veo 3.1 |
— | 2,500 | selected route | Not published | selected route |
google/veo-3.1-fastGoogle Veo 3.1 Fast |
— | 2,500 | selected route | Not published | selected route |
kling/o3-proKling Video 3.0 Omni Pro |
— | 3,072 | selected route | Not published | selected route |
kling/v3-proKling Video 3.0 Pro |
— | 3,072 | selected route | Not published | selected route |
lightricks/ltx-2.3Lightricks LTX 2.3 |
— | 5,000 | selected route | Not published | selected route |
lightricks/ltx-2.3-fastLightricks LTX 2.3 Fast |
— | 5,000 | selected route | Not published | selected route |
meta-llama/llama-3.2-3bLlama 3.2 3B |
— | 128,000 | $0.15825/1M | Not published | $0.633/1M |
meta-llama/llama-3.3-70bLlama 3.3 70B |
— | 128,000 | $0.7385/1M | Not published | $2.954/1M |
minimax/hailuo-3MiniMax Hailuo 3 (H3) |
— | 7,000 | selected route | Not published | selected route |
minimax/minimax-m25MiniMax M2.5 |
— | 198,000 | $0.28485/1M | $0.03165/1M | $1.00225/1M |
minimax/minimax-m27MiniMax M2.7 |
— | 198,000 | $0.395625/1M | $0.072532/1M | $1.5825/1M |
minimax/minimax-m3-previewMiniMax M3 Preview |
IQ 115#54 | 524,288 | $0.3165/1M | $0.0633/1M | $1.266/1M |
moonshotai/kimi-k2-5Kimi K2.5 |
— | 256,000 | $0.5908/1M | $0.2321/1M | $3.6925/1M |
moonshotai/kimi-k2-6Kimi K2.6 |
— | 256,000 | $0.79125/1M | $0.1688/1M | $3.6925/1M |
moonshotai/kimi-k2-7-codeKimi K2.7 Code |
— | 256,000 | $0.79125/1M | $0.1688/1M | $3.6925/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#20 | 1,048,576 | $3.95625/1M | $0.395625/1M | $19.78125/1M |
moonshotai/kimi-k3-fast-apiKimi K3 Fast |
— | 1,000,000 | $4.7475/1M | $0.47475/1M | $23.7375/1M |
openai/sora-2OpenAI Sora 2 |
— | 2,500 | selected route | Not published | selected route |
openai/sora-2-proOpenAI Sora 2 Pro |
— | 2,500 | selected route | Not published | selected route |
pixverse/c1PixVerse C1 |
— | 2,500 | selected route | Not published | selected route |
qwen/qwen-3-6-plusQwen 3.6 Plus Uncensored |
— | 1,000,000 | $0.659375/1M | $0.065938/1M | $3.95625/1M |
qwen/qwen-3-7-maxQwen 3.7 Max |
— | 1,000,000 | $2.8485/1M | $0.28485/1M | $8.49275/1M |
qwen/qwen-3-7-plusQwen 3.7 Plus |
— | 1,000,000 | $0.5275/1M | $0.05275/1M | $2.11/1M |
qwen/qwen-3-8-2-4t-a95bQwen 3.8 2.4T |
— | 262,144 | $2.6375/1M | $0.329688/1M | $7.9125/1M |
qwen/qwen-3-8-flashQwen 3.8 Flash |
— | 1,000,000 | $0.1477/1M | $0.01477/1M | $0.51695/1M |
qwen/qwen-3-8-maxQwen 3.8 Max |
— | 1,000,000 | $2.6375/1M | $0.329688/1M | $7.9125/1M |
qwen/qwen3-235b-a22b-instruct-2507Qwen/Qwen3-235B-A22B-Instruct-2507 |
— | 262,144 | $0.15825/1M | Not published | $0.79125/1M |
qwen/qwen3-235b-a22b-thinking-2507Qwen: Qwen3 235B A22B Thinking 2507 |
— | 128,000 | $0.47475/1M | Not published | $3.6925/1M |
qwen/qwen3-5-35b-a3bQwen 3.5 35B A3B |
— | 256,000 | $0.15825/1M | $0.05275/1M | $1.055/1M |
qwen/qwen3-6-35b-a3bQwen 3.6 35B A3B |
— | 256,000 | $0.1055/1M | Not published | $1.055/1M |
qwen/qwen3-coder-480b-a35b-instruct-turboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo |
— | 262,144 | $0.36925/1M | $0.0422/1M | $1.5825/1M |
qwen/qwen3-next-80bQwen 3 Next 80b |
— | 256,000 | $0.36925/1M | Not published | $2.0045/1M |
qwen/qwen3-vl-235b-a22bQwen3 VL 235B |
— | 128,000 | $0.22155/1M | $0.1055/1M | $2.0045/1M |
qwen/qwen3.5-397b-a17bQwen: Qwen3.5 397B A17B |
— | 262,144 | $0.79125/1M | Not published | $4.7475/1M |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 98#131 | 262,144 | $0.1055/1M | Not published | $0.15825/1M |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 111#72 | 262,144 | $0.342875/1M | Not published | $3.42875/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 116#50 | 65,536 | $0.47475/1M | Not published | $3.376/1M |
runway/gen-4.5Runway Gen-4.5 |
— | 1,000 | selected route | Not published | selected route |
shengshu/vidu-q3ShengShu Vidu Q3 |
— | 2,500 | selected route | Not published | selected route |
z-ai/glm-4.6Z.ai: GLM 4.6 |
— | 202,752 | $0.45365/1M | $0.0844/1M | $1.84625/1M |
z-ai/glm-4.7Z.ai: GLM 4.7 |
IQ 105#90 | 202,752 | $0.58025/1M | $0.11605/1M | $2.79575/1M |
z-ai/glm-4.7-flashZ.ai: GLM 4.7 Flash |
— | 131,072 | $0.0633/1M | $0.01055/1M | $0.422/1M |
z-ai/glm-5Z.ai: GLM 5 |
IQ 107#83 | 202,752 | $1.055/1M | $0.211/1M | $3.376/1M |
z-ai/glm-5-turboZ.ai: GLM 5 Turbo |
— | 202,752 | $1.266/1M | $0.2532/1M | $4.22/1M |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 113#59 | 202,752 | $1.6247/1M | $0.30173/1M | $5.1062/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 119#45 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5v-turboZ.ai: GLM 5V Turbo |
— | 202,752 | $1.5825/1M | $0.3165/1M | $5.275/1M |
Questions
Does Venice have zero data retention?
TrustedRouter does not currently mark Venice as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Venice end-to-end encrypted?
TrustedRouter does not currently mark Venice as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Venice models are available through TrustedRouter?
This page currently lists 59 public Venice models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.