Qwen3 235B A22B Thinking 2507 pricing & benchmarks
Qwen3 235B A22B Thinking 2507 is available from Alibaba at $0.230 per million input tokens and $2.30 per million output tokens ($0.747 blended at 3:1). It accepts up to 262,144 tokens of context. Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Pricing
Per million tokens · OpenRouter
Input$0.230
Output$2.30
Blended (3:1)$0.747
Specification
qwen/qwen3-235b-a22b-thinking-2507
Context window262K
Max output—
ReleasedJul 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Qwen3 235B A22B Thinking 2507 yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen3 235B A22B Thinking 2507
4 hosts · 1.6× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra | $0.747 | $0.230 / $2.30 | 262K | fp8 | 97.9% |
| Alibaba ⚠ 131K context, not 262K |
$0.747 | $0.230 / $2.30 | 131K | fp8 | 98.8% |
| Novita ⚠ 131K context, not 262K |
$0.975 | $0.300 / $3.00 | 131K | fp8 | 88.0% |
| Venice ⚠ 128K context, not 262K |
$1.21 | $0.450 / $3.50 | 128K | fp8 | 89.6% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 vs DeepSeek V4 Flash 0731
Qwen3 235B A22B Thinking 2507 vs Claude Opus 5
Qwen3 235B A22B Thinking 2507 vs Gemini 3.6 Flash
Qwen3 235B A22B Thinking 2507 vs Kimi K3
Qwen3 235B A22B Thinking 2507 vs GPT-5.6 Luna
Qwen3 235B A22B Thinking 2507 vs GPT-5.6 Terra
Qwen3 235B A22B Thinking 2507 vs GPT-5.6 Sol
Qwen3 235B A22B Thinking 2507 vs Grok 4.5
FAQ
How much does Qwen3 235B A22B Thinking 2507 cost?
Qwen3 235B A22B Thinking 2507 costs $0.230 per million input tokens and $2.30 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.747 per million tokens.
What is Qwen3 235B A22B Thinking 2507's context window?
Qwen3 235B A22B Thinking 2507 accepts up to 262,144 tokens of context.