Qwen3 VL 8B Thinking with Jev
Qwen3 VL 8B Thinking is a model from Qwen, released 2025-10-14. It costs $0.180 per million input tokens and $2.10 per million output tokens, reads up to 131K tokens of context, and writes up to 32,768 tokens in one reply. Through llm11, set model to qwen/qwen3-vl-8b-thinking.
The catalogue lists 2026-10-09 as the date Qwen3 VL 8B Thinking stops being served.
- Input price
- $0.180 / 1M
- Output price
- $2.10 / 1M
- Context window
- 131K tokens
- Max output
- 33K tokens
- Released
- 2025-10-14
- Accepts
- image, text
Read from the live catalogue and refreshed daily. At blended list price, 53% of the 332 priced models we can call cost more.
Using Qwen3 VL 8B Thinking with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Qwen3 VL 8B Thinking does the answering when Jev sends it work, or when you name it yourself. Qwen3 VL 8B Thinking falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
Jev is new, so we have not published results for Qwen3 VL 8B Thinking with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00051 | $0.510 |
| Question over retrieved documents | 4,000 / 500 | $0.00177 | $1.77 |
| Long document summary | 30,000 / 1,000 | $0.00750 | $7.50 |
Cheaper models to try
The catalogue has no benchmark score for Qwen3 VL 8B Thinking, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3 VL 235B A22B Instruct | $0.210 | $1.90 | 262K | |
| Cohere Command A+ | $0.300 | $1.50 | 192K | |
| Qwen Qwen3.5 Plus 2026-02-15 | $0.260 | $1.56 | 1M | |
| Google Gemini 3.1 Flash Lite | $0.250 | $1.50 | 1.05M |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="qwen/qwen3-vl-8b-thinking",
messages=[{"role": "user", "content": "Hello"}],
)More from Qwen
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen3.8 Max Prime | $4.00 | $12 | 1M | |
| Qwen3.8 Omni Flash | $0.150 | $0.470 | 1M | |
| Qwen3.8 Max (0902) | $2.00 | $6.00 | 1M | |
| Qwen3.8 Flash | $0.150 | $0.470 | 1M | |
| Qwen3.8 27B | $0.045 | $4.40 | 1M | |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 1.05M |
Questions
- What is Qwen3 VL 8B Thinking with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Qwen3 VL 8B Thinking does the answering when Jev sends it work, or when you name it yourself. Qwen3 VL 8B Thinking falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Qwen3 VL 8B Thinking a System One model?
- No. Qwen3 VL 8B Thinking answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Qwen3 VL 8B Thinking cost?
- $0.180 per million input tokens and $2.10 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00177, so a thousand of them is about $1.77. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Qwen3 VL 8B Thinking context window?
- 131,072 tokens, with up to 32,768 tokens in a single reply.
- Does Qwen3 VL 8B Thinking support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Qwen3 VL 8B Thinking through llm11?
- Yes. Set model to qwen/qwen3-vl-8b-thinking on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Qwen3 VL 8B Thinking?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Qwen3 VL 8B Thinking falls in the llm11-balanced band, and the labs and limits it meets make it eligible for that pack. Packs keep a spread of eight models per band, and it is not one of the eight today, so it is only picked when you name it in a custom pool.
- What is a cheaper alternative to Qwen3 VL 8B Thinking?
- Nearest in price and below it: Qwen Qwen3 VL 235B A22B Instruct at $0.210 in and $1.90 out, Cohere Command A+ at $0.300 in and $1.50 out and Qwen Qwen3.5 Plus 2026-02-15 at $0.260 in and $1.56 out. The catalogue has no benchmark score for Qwen3 VL 8B Thinking, so this is a price ordering. It does not claim these answer as well.
- Is Qwen3 VL 8B Thinking being retired?
- The catalogue lists 2026-10-09 as the date it stops being served. Move traffic before then.