Qwen3 8B
Qwen released 2025-04-28
$0.202 per million tokens, balanced
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +43.5 higher and costs 48% less ($0.105/M against $0.202/M) on this workload — and it does everything this model does.
Llama 4 Scout is cheaper still (26% less) but drops no extended reasoning.
Every price dimension
| Input | $0.117/M |
|---|---|
| Output | $0.455/M |
Independent scores
| Intelligence | 8.3 |
|---|---|
| Coding | 9 |
| Agentic | 1.6 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 131K |
|---|---|
| Max output | 8K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2025-03-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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,...