per 1M tokens
Qwen: Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
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.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| SiliconFlow | siliconflow/fp8 | fp8 | $0.29/1M | $1/1M | 262K | — | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$1.29 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.29/1M | $1/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.2 | $2.4 | Not published— |
| 2026-09-16 | token | $0.2 | $2.4 | Not published— |
| 2026-09-17 | token | $0.2 | $2.4 | Not published— |
| 2026-09-18 | token | $0.2 | $2.4 | Not published— |
| 2026-09-19 | token | $0.2 | $2.4 | Not published— |
| 2026-09-20 | token | $0.2 | $2.4 | Not published— |
| 2026-09-21 | token | $0.2 | $2.4 | Not published— |
| 2026-09-22 | token | $0.2 | $2.4 | Not published— |
| 2026-09-23 | token | $0.2 | $2.4 | Not published— |
| 2026-09-24 | token | $0.2 | $2.4 | Not published— |
| 2026-09-25 | token | $0.2 | $2.4 | Not published— |
| 2026-09-26 | token | $0.2 | $2.4 | Not published— |
| 2026-09-27 | token | $0.2 | $2.4 | Not published— |
| 2026-09-28 | token | $0.2 | $2.4 | Not published— |
| 2026-09-29 | token | $0.2 | $2.4 | Not published— |
| 2026-09-30 | token | $0.2 | $2.4 | Not published— |
| 2026-10-01 | token | $0.2 | $2.4 | Not published— |
| 2026-10-02 | token | $0.2 | $2.4 | Not published— |
| 2026-10-03 | token | $0.2 | $2.4 | Not published— |
| 2026-10-04 | token | $0.2 | $2.4 | Not published— |
| 2026-10-05 | token | $0.2 | $2.4 | Not published— |
| 2026-10-06 | token | $0.2 | $2.4 | Not published— |
| 2026-10-07 | token | $0.2 | $2.4 | Not published— |
| 2026-10-08 | token | $0.2 | $2.4 | Not published— |
| 2026-10-09 | token | $0.29 | $1 | Not published— |
| 2026-10-10 | token | $0.29 | $1 | Not published— |
| 2026-10-11 | token | $0.29 | $1 | Not published— |
| 2026-10-12 | token | $0.29 | $1 | Not published— |
| 2026-10-13 | token | $0.29 | $1 | Not published— |
| 2026-10-14 | token | $0.29 | $1 | Not published— |
| 2026-10-15 | token | $0.29 | $1 | Not published— |
| 2026-10-16 | token | $0.29 | $1 | Not published— |
| 2026-10-17 | token | $0.29 | $1 | Not published— |
| 2026-10-18 | token | $0.29 | $1 | Not published— |
| 2026-10-19 | token | $0.29 | $1 | Not published— |
| 2026-10-20 | token | $0.29 | $1 | Not published— |
| 2026-10-21 | token | $0.29 | $1 | Not published— |
| 2026-10-22 | token | $0.29 | $1 | Not published— |
| 2026-10-23 | token | $0.29 | $1 | Not published— |
| 2026-10-24 | token | $0.29 | $1 | Not published— |
| 2026-10-25 | token | $0.29 | $1 | Not published— |
| 2026-10-26 | token | $0.29 | $1 | Not published— |
| 2026-10-27 | token | $0.29 | $1 | Not published— |
| 2026-10-28 | token | $0.29 | $1 | Not published— |
| 2026-10-29 | token | $0.29 | $1 | Not published— |
| 2026-10-30 | token | $0.29 | $1 | Not published— |
Alternatives
- DeepSeek: DeepSeek V3 0324$0.29/1M · Compare
- @cf/meta/llama-3.1-70b-instruct-fp8-fast$0.293/1M · Compare
- @cf/meta/llama-3.3-70b-instruct-fp8-fast$0.293/1M · Compare
- MiniMax M2.5$0.295/1M · Compare
- @cf/meta/llama-3-8b-instruct$0.282/1M · Compare
- @cf/meta/llama-3.1-8b-instruct$0.282/1M · Compare
Parameters (11)
frequency_penaltyinclude_reasoningmax_tokensreasoningresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p
Call this model
OpenRouter id qwen/qwen3-vl-30b-a3b-thinking. 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":"qwen/qwen3-vl-30b-a3b-thinking","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: "qwen/qwen3-vl-30b-a3b-thinking",
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": "qwen/qwen3-vl-30b-a3b-thinking", "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())