Venice AI Models — Pricing & Benchmarks
3 models available
Last refreshed 2026-06-15. Next refresh: weekly.
Venice AI hosts 3 AI models in this catalog. Per-token pricing is not listed for these Venice AI rows yet; compare context windows, benchmarks, and hosting options instead. LLM Reference compares these models across all 94 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| Mistral Small 3.2 24B | — | — | 128k | |
| Qwen3-235B-A22B | — | — | 128k | |
| Qwen3-Next-80B-A3B | — | — | — |
Where else to run this
Mistral Small 3.2 24B on Venice AI
Provider setup and pricing
Qwen3-235B-A22B on Venice AI
Provider setup and pricing
Qwen3-Next-80B-A3B on Venice AI
Provider setup and pricing
Mistral Small 3.2 24B on OpenRouter
Alternative host
Qwen3-235B-A22B on Fireworks AI
Alternative host
Qwen3-Next-80B-A3B on AWS Bedrock
Alternative host
About Venice AI
Private, uncensored AI platform offering access to advanced open-source models for generative text, code, image generation, and conversations via decentralized compute resources.
Full provider profile →