← Model list
Qwen3 235B-A22B
alibaba·alibaba/qwen3-235b-a22b·GA·Open weights·qwen series
Large open Qwen MoE for multilingual reasoning, coding, and tool use
At a glance
Official price$0.287 / $1.15 per 1M
Cache read — · Alibaba (China)
Lowest paid$0.30 / $0.50
NanoGPT Gateway · 3.5× spread
1 more $0 channels
Context131,072
⚠ Providers report 40,960–131,072; the table below is authoritative
Output limit16,384
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF
Knowledge cutoff2025-04
Released / updated2025-04 / 2025-04
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence13.5
Value39
Coding—
Agentic—
Output speed61 tok/s
TTFT2.73 s
Value formulaIQ 13.5 ÷ min blended $0.350 = 39
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 10.8 · 59 tok/s
ReasoningIQ 13.5 · 61 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 12 providers10 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| iFlow qwen3-235b | Gateway | Free | — | — | 128,000 ⚠ | 32,000 | ||
| NanoGPT | Gateway | $0.30 | $0.50 | $0.15 | — | 41,000 ⚠ | 32,768 | |
| Hugging Face Qwen/Qwen3-235B-A22B | Cloud | $0.20 | $0.80 | — | — | 40,960 ⚠ | 16,384 | |
| Jiekou.AI qwen/qwen3-235b-a22b-fp8 | Gateway | $0.20 | $0.80 | — | — | 40,960 ⚠ | 20,000 | |
| NovitaAI qwen/qwen3-235b-a22b-fp8 | Gateway | $0.20 | $0.80 | — | — | 40,960 ⚠ | 20,000 | |
| Alibaba (China)Official | First-party | $0.287 | $1.15 | — | — | 131,072 | 16,384 | |
| Merge Gateway | Gateway | $0.287 | $1.15 | $0.057 | — | 131,072 | 32,768 | |
| OpenRouter | Gateway | $0.455 | $1.82 | — | — | 131,072 | 8,192 | |
| Kilo Gateway | Gateway | $0.455 | $1.82 | — | — | 131,072 | 8,192 | |
| 302.AI | Gateway | $0.29 | $2.86 | — | — | 128,000 ⚠ | 16,384 | |
| AlibabaOfficial | First-party | $0.70 | $2.80 | — | — | 131,072 | 16,384 | |
| Qiniu | Gateway | — | — | — | — | 128,000 ⚠ | 32,000 | hostTable.undisclosed |
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
1NanoGPT$67.00
2Hugging Face$80.00
3Jiekou.AI$80.00
4NovitaAI$80.00
5Merge Gateway$87.20
6Alibaba (China) · Official$114.75
1 more channels offer $0 (iFlow); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to NanoGPT to save $47.75/mo (42%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark2 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 59.6 | percent correct | Source ↗ |
| SWE-Bench Pro | dataset: public | 21.41 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)budget_tokenseffort = noneeffort = high
4 / 12 providers expose no reasoning control (reasoning_options: []).
Related models
Qwen3.5 0.8Bsame series$0.06 / $0.12Qwen3.5 4Bsame series$0.10 / $0.20Qwen3.8 27B TEEsame series$0.40 / $3.00DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0MiMo-V2.5cheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended