Qwen: Qwen3 235B A22B Thinking 2507
kilo / qwen/qwen3-235b-a22b-thinking-2507
Input price
$0.45
per 1M tokens
Output price
$3.5
per 1M tokens
Context
128K
tokens
Capabilities
✓ Reasoning✓ Tool calls— Image input✓ Open weights
| Context | 128,000 tokens |
| max output | 16,384 tokens |
| Released | 2025-07-25 |
| Data updated | 2025-07-25 |
⚠ The two sources disagree on price
models.dev says $0.45, LiteLLM says $0.3. We do not average or guess — both raw values are in models.json, see for yourself.
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.
Other models from this provider
Anthropic: Claude Fable Latest ($$$$)$10 · 1,000KAnthropic: Claude Haiku Latest$0.1 · 1,000KAnthropic: Claude Opus Latest$4 · 1,000KAnthropic: Claude Sonnet Latest$2 · 1,000KDeepSeek: DeepSeek Flash Latest$0.032 · 1,049KDeepSeek: DeepSeek Pro Latest$0.1035 · 1,049KDeepSeek: DeepSeek V4 Flash Latest$0.059 · 1,049KGoogle: Gemini Flash Latest$0.75 · 1,049K