per 1M tokens
Qwen3.8 Flash
novita/qwen/qwen3.8-flash
Qwen3.8-Flash is Alibaba's multimodal MoE model and an early preview of the Qwen4 architecture: 125B total parameters with only 6B activated per token, plus a 51B N-gram embedding, built on GDN + QSA hybrid attention. It accepts text, image and video input across a 1M-token context and emits up to 131K tokens, with thinking mode on by default and switchable off. Built for coding, agentic workflows, visual and long-document understanding, and long-video analysis at a fraction of the cost of comparable frontier models.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.62 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.15/1M | $0.47/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.15 | $0.47 | Not published— |
| 2026-10-09 | token | $0.15 | $0.47 | Not published— |
| 2026-10-10 | token | $0.15 | $0.47 | Not published— |
| 2026-10-11 | token | $0.15 | $0.47 | Not published— |
| 2026-10-12 | token | $0.15 | $0.47 | Not published— |
| 2026-10-13 | token | $0.15 | $0.47 | Not published— |
| 2026-10-14 | token | $0.15 | $0.47 | Not published— |
| 2026-10-15 | token | $0.15 | $0.47 | Not published— |
| 2026-10-16 | token | $0.15 | $0.47 | Not published— |
| 2026-10-17 | token | $0.15 | $0.47 | Not published— |
| 2026-10-18 | token | $0.15 | $0.47 | Not published— |
| 2026-10-19 | token | $0.15 | $0.47 | Not published— |
| 2026-10-20 | token | $0.15 | $0.47 | Not published— |
| 2026-10-21 | token | $0.15 | $0.47 | Not published— |
| 2026-10-22 | token | $0.15 | $0.47 | Not published— |
| 2026-10-23 | token | $0.15 | $0.47 | Not published— |
| 2026-10-24 | token | $0.15 | $0.47 | Not published— |
| 2026-10-25 | token | $0.15 | $0.47 | Not published— |
| 2026-10-26 | token | $0.15 | $0.47 | Not published— |
| 2026-10-27 | token | $0.15 | $0.47 | Not published— |
| 2026-10-28 | token | $0.15 | $0.47 | Not published— |
| 2026-10-29 | token | $0.15 | $0.47 | Not published— |
| 2026-10-30 | token | $0.15 | $0.47 | Not published— |
Alternatives
- @cf/cloudflare/clef-omni$0.15/1M · Compare
- @cf/zai-org/glm-5.3-flash$0.15/1M · Compare
- Cloudflare: Clef Omni$0.15/1M · Compare
- Cohere: Command R (08-2024)$0.15/1M · Compare
- GLM 5.3 Flash$0.15/1M · Compare
- GLM 5.3 Flash$0.15/1M · Compare
Call this model
OpenRouter id novita/qwen/qwen3.8-flash. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"novita/qwen/qwen3.8-flash","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "novita/qwen/qwen3.8-flash",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "novita/qwen/qwen3.8-flash", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())