Qwen models
43 Qwen models you can call through UberLLM’s OpenAI-compatible API. The cheapest is Qwen: Qwen3.8 Omni Flash at $0.0002/1M input tokens, as of October 24, 2026. Every request is routed to the cheapest healthy seller; the price shown includes UberLLM’s 10% fee.
| Model | Price (from) | Context | Type | Capabilities |
|---|---|---|---|---|
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.1925 in · $0.8250 out | 256K | Text | |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.0009 in · $0.0104 out | 262K | Text | ToolsJSON |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.3438 in · $2.06 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0660 in · $0.2750 out | 256K | Text | ToolsReasoningJSON |
| Qwen3.5 Plus qwen/qwen3.5-plus | $0.2574 in · $1.54 out | 1000K | Text | ToolsJSON |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.0006 in · $0.0038 out | 128K | Text | ToolsReasoningJSON |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0157 in · $0.0408 out | 32K | Text | |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0033 in · $0.0109 out | 256K | Text | ToolsJSON |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0550 in · $0.0825 out | 256K | Text | Tools |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0328 in · $0.2624 out | 256K | Text | ToolsReasoningVisionJSON |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.0827 in · $0.7486 out | 256K | Text | ToolsReasoningJSON |
| Qwen3.5 Flash qwen/qwen3.5-flash | $0.0990 in · $0.3960 out | 1000K | Text | ToolsJSON |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1100 in · $0.4950 out | 128K | Text | ToolsReasoningJSON |
| Qwen3.5 122B A10B qwen/e2ee-qwen3-5-122b-a10b | 128K | Text | ||
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0898 in · $0.5984 out | 256K | Text | Tools |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.1001 in · $0.1001 out | 128K | Text | ToolsReasoningJSON |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0212 in · $0.1525 out | 128K | Text | ToolsReasoningVisionJSON |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0577 in · $0.3740 out | 128K | Text | ToolsJSON |
| Qwen 3 235B A22B Instruct 2507 (Morpheus Web) qwen/qwen3-235b-a22b-2507:web | $0.1237 in · $0.6188 out | 128K | Text | ToolsReasoningJSON |
| Qwen 3.6 35B A3B Uncensored (E2EE) qwen/e2ee-qwen3-6-35b-a3b-uncensored-p | $0.2200 in · $0.6600 out | 128K | Text | ToolsJSON |
| Qwen 3 Next 80b (Morpheus Web) qwen/qwen3-next-80b-a3b-instruct:web | $0.2888 in · $1.57 out | 256K | Text | ToolsJSON |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1813 in · $0.7253 out | 256K | Text | ToolsJSON |
| Qwen3.7 Max qwen/qwen3.7-max | $1.10 in · $3.30 out | 1000K | Text | ToolsJSON |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0103 in · $0.1035 out | 262K | Text | ToolsReasoningVisionJSON |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.0008 in · $0.0030 out | 256K | Text | ToolsJSON |
| Qwen3 32B qwen/qwen3-32b | $0.0009 in · $0.0030 out | 32K | Text | ToolsJSON |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0013 in · $0.0087 out | 256K | Text | ToolsJSON |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0023 in · $0.0207 out | 256K | Text | ToolsVisionJSON |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0083 in · $0.0357 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.2801 in · $0.8404 out | 1000K | Text | ToolsReasoning |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0023 in · $0.0069 out | 1000K | Text | ToolsReasoningJSON |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.0009 in · $0.0108 out | 262K | Text | ToolsReasoningVisionJSON |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0016 in · $0.0051 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0019 in · $0.0057 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.0002 in · $0.0005 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $2.20 in · $6.60 out | 1000K | Text | ToolsReasoningVisionJSON |
| Qwen3 0.6B TTS qwen/tts-qwen3-0-6b | Audio | JSON | ||
| Qwen3 1.7B TTS qwen/tts-qwen3-1-7b | Audio | JSON | ||
| Qwen Image 2 (image-to-image) qwen/qwen-image-2-edit | $0.055 per image | Image | JSON | |
| Qwen Image 2 Pro (image-to-image) qwen/qwen-image-2-pro-edit | $0.11 per image | Image | JSON | |
| Qwen Edit Uncensored (image-to-image) qwen/qwen-edit-uncensored | $0.044 per image | Image | JSON | |
| Qwen Image 2.1 Turbo (Venice) qwen/venice-qwen-image-2-1-turbo | $0.022 per image | Image | JSON | |
| Qwen Image 2.1 Pro (Venice) qwen/venice-qwen-image-2-1-pro | $0.055 per image | Image | JSON |
Compare Qwen models
Qwen models — FAQ
What is the cheapest Qwen model?
Qwen: Qwen3.8 Omni Flash is the cheapest Qwen model on UberLLM right now, at $0.0002/1M input tokens. UberLLM routes each request to the cheapest healthy seller and bills the price shown, which includes UberLLM's 10% fee.
How many Qwen models can I use through UberLLM?
43 Qwen models are on the UberLLM marketplace today. One OpenAI-compatible API key and base URL (https://api.uberllm.dev/v1) calls every one of them — no per-provider contracts.
How do I call a Qwen model with the API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM key, and the model id (for example "qwen/qwen3-coder-turbo"). Anthropic SDKs work against https://api.uberllm.dev/v1/messages.