← Model list
Qwen 3 235b A22B 2507
alibaba·alibaba/qwen3-235b-a22b-instruct-2507-2·GA·Open weights·qwen series
Qwen instruction model for multilingual chat, reasoning, and tool use
At a glance
Reference price$0.22 / $0.88 per 1M
Cache read — · Amazon Bedrock
Lowest paid$0.072 / $0.464
TensorX Gateway · 3.1× spread
Context262,144
⚠ Providers report 131,000–262,144; the table below is authoritative
Output limit131,072
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff2024-04
Released / updated2025-07-21 / 2025-09-18
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence19.9
Value117
Coding22.1
Agentic3.8
Output speed64 tok/s
TTFT2.69 s
Cost per task$0.0637
Value formulaIQ 19.9 ÷ min blended $0.170 = 117
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 3 providers3 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| TensorX qwen/qwen3-235b-a22b-2507 | Gateway | $0.072 | $0.464 | $0.018 | $0.09 | 131,000 ⚠ | 262,144 | |
| NanoGPT qwen/Qwen3-235B-A22B-Instruct-2507 | Gateway | $0.13 | $0.50 | $0.065 | — | 256,000 ⚠ | 262,144 | |
| Amazon Bedrock qwen.qwen3-235b-a22b-2507-v1:0 | Cloud | $0.22 | $0.88 | — | — | 262,144 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1TensorX$31.12
2NanoGPT$43.20
3Amazon Bedrock$88.00
The cheapest paid channel is the only channel.
Related models
Qwen3.5 0.8Bsame series$0.06 / $0.12Qwen3.5 4Bsame series$0.10 / $0.20Qwen3.8 27B TEEsame series$0.40 / $3.00Llama-3.1-8B-Instructcheaper alternative$0.15 / $0.45Llama 3.2 3B Instructcheaper alternative$0.10 / $0.335DeepSeek Chatcheaper alternative$0.14 / $0.28Llama 3.2 1B Instructcheaper alternative$0.10 / $0.201
Price historyone sample accumulated per data sync
Input listOutput listMin blended