Verified 2026-11-18 · rates follow the live catalog
3 Qwen models are in the catalog, from Qwen3.8 27b at $0.0012 for one request to Qwen3.5 at $0.0072, a 5.9× spread inside one family. Prices are what each model bills at its most expensive hour of the day. One request is a 20,000-token prompt with a 1,000-token reply and nothing cached, an illustration and not a measurement of your traffic.
| Model | Context | Input / 1M | Output / 1M | Cached input / 1M | One request (20,000 in, 1,000 out) | 1,000 requests |
|---|---|---|---|---|---|---|
Qwen3.8 27b | 256K | $0.045 | $0.32 | — | $0.0012 | $1.22 |
Qwen3.8 Flash | 1M | $0.075 | $0.235 | $0.008 | $0.0017 | $1.74 |
Qwen3.5 | 256K | $0.30 | $1.20 | — | $0.0072 | $7.20 |
| Model | Image input | Video input | Tool calling | Reasoning tiers | Serving precision |
|---|---|---|---|---|---|
Qwen3.8 27b | Yes | No | Yes | low, medium, xhigh | FP8 |
Qwen3.8 Flash | Yes | Yes | Yes | — | — |
Qwen3.5 | No | No | Yes | — | BF16 |
These models publish a discount against their list price:
Qwen3.8 27b: 90% off at every hour, already inside the prices above.Qwen3.8 Flash: 50% off at every hour, already inside the prices above.Each model's page shows its list price, its rates and its schedule.
Create an account, make a key in the dashboard and send it as a bearer token. Between model families, only the model field changes.
curl https://api.openference.com/v1/chat/completions \
-H "Authorization: Bearer $OPENFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "Qwen3.8 Flash",
"messages": [{"role": "user", "content": "Say hello"}]}'
Send Qwen3.8 Flash exactly as written. OpenAI-format clients use https://api.openference.com/v1; Claude Code and other Anthropic-format clients use https://api.openference.com. The OpenAI-compatible API guide covers every endpoint.
See also the cheap AI API guide, the model catalog and pricing.
Across the 3 billed Qwen models, input runs $0.045 to $0.30 and output $0.235 to $1.20 per million tokens at the most expensive hour of the day. Qwen3.8 27b is the least expensive per request.
https://api.openference.com/v1 for OpenAI-format clients and https://api.openference.com for Anthropic-format clients.
Some do: Qwen3.8 27b and Qwen3.8 Flash accept image input, and the other one is text-only.
Not at the moment. The least expensive billed Qwen model is Qwen3.8 27b, at $0.0012 for the request described above.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API