Qwen3 VL 8B Instruct

qwen/qwen3-vl-8b-instruct
VisionToolsJSON
by Qwen · 2025-10-14

Qwen3-VL 8B Instruct — open-weight small vision-language model, 8B params, 128k context, no thinking mode.

Endpoints:/v1/chat/completions
ctx131.1K tokens
Max output32.8K
Inputtext + image + video
Outputtext
p50 TTFT3.64 s
INPUT$0.18/ 1M tokens
OUTPUT$0.70/ 1M tokens
p50 TTFT3.64 s7d
p95 TTFT10.00 s7d
TRAFFIC637.2Ktokens / 7d
Get the Qwen3 VL 8B Instruct API →▶ Try in playground</> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="qwen/qwen3-vl-8b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • enable_search
  • logprobs
  • max_tokens
  • n
  • parallel_tool_calls
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • stream
  • stream_options
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Pricing

Input / 1M tokens$0.180
Output / 1M tokens$0.700
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $3.36

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000354

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days
p50 TTFT
3.64 s
Output speed
53.3 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

Last evaluated 2025-10-14
7.3
AA Coding
Better than 0% of models compared
#106 of 106
14.3
AA Intelligence
Better than 12% of models compared
#97 of 110
27.3
AA Math
Better than 7% of models compared
#75 of 81
AIME 2025
27.3
GPQA Diamond
42.7
Humanity's Last Exam
2.9
IFBench
32.3
LiveCodeBench
33.2
Long-Context Recall
15.3
MMLU-Pro
68.6
SciCode
17.4
TerminalBench Hard
2.3
τ²-Bench
29.2
Source: artificialanalysis.ai

How it compares

Qwen3 VL 8B Instructqwen/qwen3-max-previewQwen3.5 397B A17Bqwen/qwen3.5-plus
Input $/M$0.18$0.86$0.17$0.12
Output $/M$0.70$3.44$1.03$0.69
Context131K262K33K1.0M
Quality4/108/108/108/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

More from Qwen

See all models from qwen →
Qwen3.6 35B A3BCheapest
qwen/qwen3.6-35b-a3b
$0.25 in · $1.49 out / 1M
262.1K ctx· quality 8/10
 Compare side-by-side
Qwen3.6 Plus
qwen/qwen3.6-plus
$0.50 in · $3.00 out / 1M
1.05M ctx· quality 8/10
 Compare side-by-side
Qwen3.7 Plus
qwen/qwen3.7-plus
$0.35 in · $1.42 out / 1M
1M ctx· quality 8/10
 Compare side-by-side

FAQ

How much does Qwen: Qwen3 VL 8B Instruct cost on OrcaRouter?
Qwen: Qwen3 VL 8B Instruct is priced at $0.18 per 1M input tokens and $0.70 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is Qwen: Qwen3 VL 8B Instruct's context window?
Qwen: Qwen3 VL 8B Instruct supports a context window of 131K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Qwen: Qwen3 VL 8B Instruct via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="qwen/qwen3-vl-8b-instruct" in the chat.completions.create call.
Does OrcaRouter rate-limit Qwen: Qwen3 VL 8B Instruct?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
Qwen: Qwen3 VL 8B Instruct•$0.18/M in•3636ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/qwen/qwen3-vl-8b-instruct" target="_blank"> <img src="https://www.orcarouter.ai/embed/qwen/qwen3-vl-8b-instruct.svg" alt="Qwen: Qwen3 VL 8B Instruct on OrcaRouter" /> </a>
Markdown [![Qwen: Qwen3 VL 8B Instruct](https://www.orcarouter.ai/embed/qwen/qwen3-vl-8b-instruct.svg)](https://www.orcarouter.ai/models/qwen/qwen3-vl-8b-instruct)

Model card as data

GET /api/public/models/qwen/qwen3-vl-8b-instructOpen
Machine-readable:/llms.txt/llms-full.txt