Qwen3 8B
by Alibaba (Qwen) · qwen/qwen3-8b · #65 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:42 AM UTC · refreshed hourly
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.117
per 1M tokens
Output
$0.455
per 1M tokens
Blended (3:1)
$0.202
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 8B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.202 | $0.0124 | — |
| 50% | $0.202 | $0.0124 | −0% |
| 90% | $0.202 | $0.0124 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000195 | $0.195 |
| Document summary | 8,000 | 1,000 | $0.001391 | $1.39 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00442 | $4.42 |
| Long-context analysis | 150,000 | 5,000 | $0.0198 | $19.82 |
Performance
Intelligence Index
8.3
AA composite quality
Coding Index
9
Math Index
—
Agentic Index
1.5
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
131K
tokens
Max output
8K
tokens
Input modalities
text
Tokenizer
Qwen3