← Model list
Qwen3-Coder 30B-A3B Instruct
alibaba·alibaba/qwen3-coder-30b-a3b-instruct·GA·Open weights·qwen series
Smaller Qwen coder for efficient local agents and repo-level fixes
At a glance
Official price$0.216 / $0.861 per 1M
Cache read — · Alibaba (China)
Lowest paid$0.06 / $0.25
TensorX Gateway · 7.5× spread
1 more $0 channels
Context262,144
⚠ Providers report 128,000–262,144; the table below is authoritative
Output limit65,536
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-04
Released / updated2025-04 / 2025-04
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence13.6
Value127
Coding—
Agentic—
Output speed91 tok/s
TTFT2.54 s
Value formulaIQ 13.6 ÷ min blended $0.107 = 127
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 19 providers18 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| ModelScope Qwen/Qwen3-Coder-30B-A3B-Instruct | Cloud | Free | — | — | 262,144 | 65,536 | ||
| TensorX | Gateway | $0.06 | $0.25 | $0.015 | $0.075 | 262,000 ⚠ | 65,536 | |
| Cortecs | Gateway | $0.067 | $0.245 | $0.014 | — | 262,144 | 262,000 | |
| Hugging Face Qwen/Qwen3-Coder-30B-A3B-Instruct | Cloud | $0.07 | $0.26 | — | — | 262,144 | 65,536 | |
| OVHcloud AI Endpoints | Cloud | $0.07 | $0.26 | — | — | 262,144 | 262,144 | |
| NovitaAI | Gateway | $0.07 | $0.27 | — | — | 160,000 ⚠ | 32,768 | |
| DevPass (LLM Gateway) | Gateway | $0.07 | $0.27 | — | — | 262,000 ⚠ | 65,536 | |
| OpenRouter | Gateway | $0.07 | $0.28 | — | — | 262,144 | 262,144 | |
| Helicone | Gateway | $0.10 | $0.30 | — | — | 262,144 | 262,144 | |
| NanoGPT | Gateway | $0.10 | $0.40 | $0.05 | — | 128,000 ⚠ | 65,536 | |
| Alibaba (China)Official | First-party | $0.216 | $0.861 | — | — | 262,144 | 65,536 | |
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$19.10
2Cortecs$19.29
3Hugging Face$27.00
4OVHcloud AI Endpoints$27.00
5NovitaAI$27.50
6DevPass (LLM Gateway)$27.50
14Alibaba (China) · Official$86.25
1 more channels offer $0 (ModelScope); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to TensorX to save $67.15/mo (78%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark3 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 19.4 | index | Source ↗ |
| SciCode | — | 27.8 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 15.2 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
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