Search for a model to see price trends.
LLM Inference Pricing
Model
Estimate cost for
Price history
Search for a model to see price trends.
Discover
1deepseek-v4.1-flash2deepseek-v4.1-flash-10173kimi-k34glm-5.35glm-5.3-flash6deepseek-v4-flash-07317glm-5.28gpt-oss-120b9deepseek-v4-pro-081310kimi-k2.611minimax-m312qwen3.6-35b-a3b13kimi-k2.7-code14qwen3.5-397b-a17b15qwen3.8-27b16deepseek-v3.217deepseek-v4-pro18gemma-4-31b-it19gpt-oss-20b20claude-opus-4.8
Select a model
qwen3.5-397b-a17b is available from 12 providers. Cheapest input price: $0.1720 per 1M tokens on OrcaRouter.
| Provider | Model ID | Input | Output | Context |
|---|---|---|---|---|
| OrcaRouter | qwen/qwen3.5-397b-a17b | $0.1720 | $1.03 | 32,768 |
| Liquid Inference | qwen3.5-397b-a17b | $0.3898 | $2.34 | 262,144 |
| Nous Research | qwen/qwen3.5-397b-a17b | $0.3900 | $2.34 | 262,144 |
| Liquid Inference | qwen3.5-397b-a17b:thinking | $0.3905 | $2.34 | 262,144 |
| DeepInfra | Qwen/Qwen3.5-397B-A17B | $0.4500 | $3.00 | 262,144 |
| CheapTokens | qwen3-5-397b-a17b | $0.4573 | $2.74 | 128,000 |
| Runcrate | Qwen/Qwen3.5-397B-A17B | $0.4725 | $3.15 | 262,144 |
| OpenRouter | qwen/qwen3.5-397b-a17b | $0.5000 | $3.60 | 262,144 |
| Atlas Cloud | qwen/qwen3.5-397b-a17b | $0.5500 | $3.50 | 262,144 |
| Featherless AI | Qwen/Qwen3.5-397B-A17B | $0.5500 | $3.50 | 262,144 |
| Novita | qwen/qwen3.5-397b-a17b | $0.6000 | $3.60 | 262,144 |
| Together AI | Qwen/Qwen3.5-397B-A17B | $0.6000 | $3.60 | 262,144 |
| Venice | qwen3-5-397b-a17b | $0.7500 | $4.50 | 128,000 |
Price history by provider
Search for a model to compare provider price history.
Search for a model to compare provider price history.