Qwen3 8B with Jev
Qwen3 8B is a model from Qwen, released 2025-04-28. It costs $0.117 per million input tokens and $0.455 per million output tokens, reads up to 131K tokens of context, and writes up to 8,192 tokens in one reply. Through llm11, set model to qwen/qwen3-8b.
The catalogue lists 2026-10-09 as the date Qwen3 8B stops being served.
- Input price
- $0.117 / 1M
- Output price
- $0.455 / 1M
- Context window
- 131K tokens
- Max output
- 8K tokens
- Released
- 2025-04-28
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 76% of the 332 priced models we can call cost more.
Using Qwen3 8B 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 8B does the answering when Jev sends it work, or when you name it yourself. Qwen3 8B falls in the llm11-fast 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 8B 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 | $0.00015 | $0.149 |
| Question over retrieved documents | 4,000 / 500 | $0.00070 | $0.696 |
| Long document summary | 30,000 / 1,000 | $0.00396 | $3.96 |
Cheaper models to try
The catalogue has no benchmark score for Qwen3 8B, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| OpenAI GPT-6 Luna | $0.100 | $0.500 | 1.05M | |
| OpenAI GPT-6 Luna Pro | $0.100 | $0.500 | 1.05M | |
| Mistral Ministral 3 14B 2512 | $0.200 | $0.200 | 262K | |
| Qwen Qwen3 VL 32B InstructRetires 2026-10-09 | $0.104 | $0.416 | 131K |
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/qwen3-8b",
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 8B 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 8B does the answering when Jev sends it work, or when you name it yourself. Qwen3 8B falls in the llm11-fast 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 8B a System One model?
- No. Qwen3 8B 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 8B cost?
- $0.117 per million input tokens and $0.455 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00070, so a thousand of them is about $0.696. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Qwen3 8B context window?
- 131,072 tokens, with up to 8,192 tokens in a single reply.
- Does Qwen3 8B support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Qwen3 8B through llm11?
- Yes. Set model to qwen/qwen3-8b on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Qwen3 8B?
- Routing decisions are made by Jev, TypeSafe AI's System One model. Qwen3 8B falls in the llm11-fast 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 8B?
- Nearest in price and below it: OpenAI GPT-6 Luna at $0.100 in and $0.500 out, OpenAI GPT-6 Luna Pro at $0.100 in and $0.500 out and Mistral Ministral 3 14B 2512 at $0.200 in and $0.200 out. The catalogue has no benchmark score for Qwen3 8B, so this is a price ordering. It does not claim these answer as well.
- Is Qwen3 8B being retired?
- The catalogue lists 2026-10-09 as the date it stops being served. Move traffic before then.