ModelBench
Alibaba Qwen logo
Models/Alibaba Qwen

Alibaba Qwen: Qwen3-Coder 30B-A3B Instruct

Smaller Qwen coder for efficient local agents and repo-level fixes

Source-linked qwen Open weights Released 2025-04
API record Report
InputT
OutputT
Input price$0.45/M
Output price$2.25/M
Context262.144K
Max output65.536K
Providers12
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Qwen3-Coder 30B-A3B Instruct
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Pendra qwen3-coder:30b 262.144K 65.536K — — — Tools Docs ↗
TensorX qwen/qwen3-coder-30b-a3b-instruct 262K 65.536K $0.06 $0.25 $0.015 Tools Docs ↗
Cortecs qwen3-coder-30b-a3b-instruct 262.144K 262.144K $0.067 $0.245 $0.014 ToolsJSON Docs ↗
OpenRouter qwen/qwen3-coder-30b-a3b-instruct 262.144K 235.929K $0.07 $0.28 — ToolsJSON Docs ↗
Hugging Face Qwen/Qwen3-Coder-30B-A3B-Instruct 262.144K 65.536K $0.07 $0.26 — ToolsJSON Docs ↗
DevPass (LLM Gateway) qwen3-coder-30b-a3b-instruct 262K 65.536K $0.07 $0.27 — Tools Docs ↗
Scaleway qwen3-coder-30b-a3b-instruct 128K 32.768K $0.2 $0.8 — Tools Docs ↗
Alibaba (China) qwen3-coder-30b-a3b-instruct 262.144K 65.536K $0.216 $0.861 — Tools Docs ↗
GreenPT qwen3-coder-30b-a3b-instruct 128K 32.768K $0.285 $1.083 — Tools Docs ↗
Kilo Gateway qwen/qwen3-coder-30b-a3b-instruct 262.144K 235.929K $0.292 $1.462 — ToolsJSON Docs ↗
Alibaba qwen3-coder-30b-a3b-instruct 262.144K 65.536K $0.45 $2.25 — Tools Docs ↗
Eden AI qwen/qwen3-coder-30b-a3b-instruct 262.144K 65.536K $0.45 $2.25 — ToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.06/M

Across 11 priced providers

Median input $0.2/M

Midpoint of listed rates

Highest input $0.45/M

7.5× the lowest listed rate

Output range $0.245 – $2.25

Per million output tokens

TensorX $0.06/MLowest
Cortecs $0.067/M
OpenRouter $0.07/M
Hugging Face $0.07/M
DevPass (LLM Gateway) $0.07/M
Scaleway $0.2/M
Alibaba (China) $0.216/M
GreenPT $0.285/M
Kilo Gateway $0.292/M
Alibaba $0.45/M
Eden AI $0.45/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 128K to 262.144K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
✓ Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
✓ Open weights Yes
Model family
qwen
Knowledge cutoff
2025-04
License
Not documented
Release date
2025-04
Model ID
alibaba/qwen3-coder-30b-a3b-instruct

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
SciCodeSciCode AA Coding IndexArtificial Analysis Coding Index Terminal-Bench…Terminal-Bench Hard This model — SciCode: 27.8 percent correct (24.1th percentile) This model — Artificial Analysis Coding Index: 19.4 index (40.4th percentile) This model — Terminal-Bench Hard: 15.2 success rate (43.2th percentile)

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

SciCode percent correct · 2026-06-02 Source ↗
SciCode #21 of 27
Artificial Analysis Coding Index index · 2026-06-02 Source ↗
Artificial Analysis Coding Index #16 of 26
Terminal-Bench Hard success rate · 2026-06-02 Source ↗
Terminal-Bench Hard #13 of 22

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against SciCode, the benchmark with the widest published coverage that this model appears in.

0 23 45 $0.1 $1 $10 Qwen3-Coder 30B-A3B Instruct — $0.45/M, score 27.8 Qwen3 Max — $1.2/M, score 38.3 DeepSeek-R1 — $0.7/M, score 35.7 Gemini 2.5 Flash — $0.3/M, score 39.4 Gemini 2.5 Flash-Lite — $0.1/M, score 19.3 Gemini 2.5 Pro — $1.25/M, score 42.8 Llama-3.3-70B-Instruct — $0.1/M, score 26.0 Devstral 2 — $0.4/M, score 33.1 Mistral Large 2.1 — $2/M, score 29.2 Mistral Large 3 — $0.5/M, score 36.2 Mistral Medium 3 — $0.4/M, score 33.1 Mistral Small 4 — $0.15/M, score 38.0 GPT-4 Turbo — $10/M, score 31.9 GPT-4o (2024-05-13) — $5/M, score 30.9 GPT-4o (2024-08-06) — $2.5/M, score 33.1 GPT-4o (2024-11-20) — $2.5/M, score 33.3 GPT-4o mini — $0.15/M, score 22.9 GPT-5-Codex — $1.1/M, score 40.9 Sonar — $1/M, score 22.9 Sonar Pro — $3/M, score 22.6 Step 3.5 Flash — $0.1/M, score 40.4 Step 3.5 Flash 2603 — $0.1/M, score 38.5 Step 3.7 Flash — $0.185/M, score 40.0 GLM-4.5 — $0.6/M, score 34.8 GLM-4.5-Air — $0.2/M, score 30.6 GLM-4.5V — $0.6/M, score 22.1 GLM-4.6 — $0.6/M, score 38.4 Qwen3-Coder 30B-A3B Instruct Input price per million tokens (log scale) Percent correct

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Price Completion0.26 → 2.25
Price Prompt0.07 → 0.45
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Pendra documentationprovider documentation ↗TensorX documentationprovider documentation ↗Cortecs documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Hugging Face documentationprovider documentation ↗DevPass (LLM Gateway) documentationprovider documentation ↗Scaleway documentationprovider documentation ↗Alibaba documentationprovider documentation ↗GreenPT documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗Eden AI documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/alibaba/qwen3-coder-30b-a3b-instruct
curl
curl "https://model.kyssta.lol/api/v1/models/alibaba/qwen3-coder-30b-a3b-instruct"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Qwen3-Coder 30B-A3B Instruct?

Smaller Qwen coder for efficient local agents and repo-level fixes. It is published by Alibaba Qwen and catalogued here from Models.dev.

How much does Qwen3-Coder 30B-A3B Instruct cost?

Listed input pricing starts at $0.06 per million tokens from TensorX, rising to $0.45 across 11 listed providers.

What is the context length of Qwen3-Coder 30B-A3B Instruct?

Qwen3-Coder 30B-A3B Instruct accepts up to 262.144K tokens of context and returns up to 65.536K output tokens.

Does Qwen3-Coder 30B-A3B Instruct support tool calling and structured output?

Provider catalogs list support for tool calling.

Which providers serve Qwen3-Coder 30B-A3B Instruct?

12 providers list this model: Pendra, TensorX, Cortecs, OpenRouter, Hugging Face, DevPass (LLM Gateway) and 6 more.

Are the weights for Qwen3-Coder 30B-A3B Instruct open?

Yes. The weights are published and downloadable from Hugging Face.

When was Qwen3-Coder 30B-A3B Instruct released?

The catalog records a release date of 2025-04, last verified Sep 11, 2026.

More models from Alibaba Qwen

View all →
Qwen: Qwen3 VL 32B Instruct

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...

131.072K ctx $0.104/M in Qwen: Qwen Plus 0728

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

1M ctx $0.26/M in Qwen3.8 Flash

Qwen vision-language model for visual reasoning, documents, and agent tasks

1M ctx $0.15/M in Qwen3.5 9B

Qwen instruction model for multilingual chat, reasoning, and tool use

262.144K ctx $0.04/M in