Venice
Inference providerUS Westprices checked Oct 23, 06:00 UTC
Venice serves 40 models at a verified price. On the 39 it shares with other hosts, it is the cheapest on 6 and charges a median 45% above the cheapest.
Models served4038 with open weights
Cheapest input, per M$0.03gpt-oss-120b
Uptime, last 24 h96.2%average of its 40 OpenRouter endpoints
Sign-upCard requiredno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| Nemotron 3.5 Super VL | fp4 | 256K | ✓ | $0.25 | $1.25 | $0.13 |
| MiMo-V2.6-Flash | fp8 | 1M | ✓ | $0.17 | $0.35 | $0.0037 |
| DeepSeek V4.1 Flash | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.0075 |
| GLM-5.3-Flash | not read: host terms | 1M | ✓ | $0.15 | $0.50 | $0.03 |
| GLM-5.3 | not read: host terms | 1M | ✓ | $1.40 | $4.40 | $0.26 |
| Qwen3.8 27B | fp8 | 256K | ✓ | $0.45 | $3.20 | — |
| Qwen3.8 2.4T A95Bcheapest | not read: host terms | 256K | ✓ | $2.00 | $6.00 | $0.25 |
| DeepSeek V4 Flash 0731 | not read: host terms | 1M | ✓ | $0.13 | $0.26 | $0.028 |
| GLM 5.2 | fp8 | 1M | ✓ | $1.40 | $4.40 | $0.26 |
| Kimi K2.7 Code | int4 | 250K | ✓ | $0.75 | $3.50 | $0.16 |
| Nemotron 3 Ultra | fp8 | 250K | ✓ | $0.63 | $3.13 | $0.19 |
| MiniMax-M3 | fp8 | 512K | ✓ | $0.30 | $1.20 | $0.06 |
| DeepSeek V4 Flash 0423 | not read: host terms | 1M | ✓ | $0.0966 | $0.19 | $0.0196 |
| DeepSeek V4 Pro 0423 | not read: host terms | 1M | ✓ | $1.65 | $3.30 | $0.33 |
| DeepSeek V4 Pro 0813 | not read: host terms | 1M | ✓ | $1.65 | $4.95 | $0.17 |
| MiMo-V2.5 | fp8 | 1.05M | ✓ | $0.40 | $2.00 | $0.08 |
| Qwen3.6 27B | fp8 | 250K | ✓ | $0.33 | $3.25 | — |
| Kimi K2.6 | int4 | 250K | ✓ | $0.75 | $3.50 | $0.16 |
| Qwen3.6 35B A3B | fp8 | 250K | ✓ | $0.10 | $1.00 | — |
| GLM 5.1 | fp8 | 200K | ✓ | $1.40 | $4.40 | $0.26 |
| Gemma 4 26B A4B | bf16 | 250K | ✓ | $0.13 | $0.40 | $0.05 |
| Gemma 4 31B | fp4 | 250K | ✓ | $0.12 | $0.36 | $0.09 |
| Mistral Small 4 | not read: host terms | 256K | — | $0.19 | $0.75 | — |
| Qwen3.5 9Bcheapest | fp8 | 256K | ✓ | $0.10 | $0.15 | — |
| Qwen3.5-35B-A3B | not read: host terms | 250K | ✓ | $0.15 | $1.00 | $0.05 |
| Qwen3.5 397B A17B | not read: host terms | 125K | ✓ | $0.75 | $4.50 | — |
| GLM 5 | fp8 | 198K | ✓ | $1.00 | $3.20 | $0.20 |
| MiniMax M2.5cheapest | not read: host terms | 198K | ✓ | $0.27 | $0.95 | $0.03 |
| Kimi K2.5 | not read: host terms | 250K | ✓ | $0.53 | $3.33 | $0.21 |
| GLM 4.7 Flashcheapest | fp8 | 125K | ✓ | $0.06 | $0.40 | $0.01 |
| GLM 4.7 | fp4 | 198K | ✓ | $0.40 | $1.93 | $0.0801 |
| DeepSeek V3.2 | not read: host terms | 160K | ✓ | $0.27 | $0.39 | $0.13 |
| GLM 4.6cheapest | fp4 | 198K | ✓ | $0.43 | $1.75 | $0.08 |
| Qwen3 VL 235B A22B Instruct | fp8 | 125K | ✓ | $0.21 | $1.90 | $0.10 |
| gpt-oss-120bcheapest | int4 | 125K | ✓ | $0.03 | $0.15 | $0.03 |
| Qwen3 235B A22B Thinking 2507 | fp8 | 125K | ✓ | $0.45 | $3.50 | — |
| Qwen3 Coder | fp8 | 250K | ✓ | $0.35 | $1.50 | $0.04 |
| Qwen3 235B A22B Instruct 2507 | fp8 | 125K | ✓ | $0.15 | $0.75 | — |
| Uncensored | fp16 | 125K | — | $0.20 | $0.90 | — |
| Mistral Small 3.2 24B | fp8 | under review | ✓ | $0.0938 | $0.25 | — |
10 of 40 models · prices per million tokens · precision and context: read at Venice's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Venice declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Card required | docs.venice.ai |
| Free credits | None stated | — |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | docs.venice.ai |
| API documentation | Its own docs | docs.venice.ai |
| Status page | Outages and incidents, as Venice reports them | veniceai-status.com |
| Terms of service | Its terms | venice.ai |
Links checked Oct 8.