OVHcloud AI Endpoints logo

Qwen3-Coder-30B-A3B-Instruct Free API on OVHcloud AI Endpoints

Free API
★★★★★★★★★★ 3.5 Benchmark-backed score

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

Free APIOpenAI compatibleTool callingJSON modeTextCode
API Details

Copy-ready connection details

Use these values in your client or SDK.
Base URL
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
Model ID
qwen3-coder-30b-a3b-instruct
API format OpenAI-style
Technical Details

Qwen3-Coder-30B-A3B-Instruct specifications

Provider and model catalog
Context window 262K
Max output 32K
Status Online
Family qwen
Knowledge cutoff 2025-04
Released Apr 1, 2025
Last updated Aug 6, 2026
Free listing since Jul 31, 2025
Input text
Output text
Capabilities tool calling, structured output, temperature control
Open weights Yes

External benchmark references

Benchmark Score Metric Date
Artificial Analysis Coding Index 19.4 index 2026-06-02
SciCode 27.8 percent correct 2026-06-02
Terminal-Bench Hard 15.2 success rate 2026-06-02
AI Recommendation

Should you use Qwen3-Coder-30B-A3B-Instruct?

Qwen3-Coder-30B-A3B-Instruct is listed for chat, coding workloads and supports a 262K context window.

Use it when OVHcloud AI Endpoints's free tier is enough for evaluation, demos, or light production traffic.

Best for
  • Chat
  • Coding
Strengths & Weaknesses

Strengths

  • Useful for coding workflows
  • Long context window
  • Tool calling support
  • Structured JSON output

Watch outs

  • Free-tier rate limits apply
  • Vision support is not listed
Benchmark Overview

Benchmark signals for Qwen3-Coder-30B-A3B-Instruct

Measured data
Intelligence General reasoning and instruction following
20/100
Coding Programming and code generation
19.4/100
Agentic Tool use and multi-step tasks
21.1/100
Speed Observed generation speed
90 tok/s
Context Maximum listed context window
262K
Pricing

Qwen3-Coder-30B-A3B-Instruct pricing per 1M tokens

Free tier listed
Input $0.45 per 1M tokens
Output $2.25 per 1M tokens
Free access Available OVHcloud AI Endpoints
Rate limit 2 RPM (anonymous) provider policy
Typical Use Cases

Qwen3-Coder-30B-A3B-Instruct use cases

Chat

Qwen3-Coder-30B-A3B-Instruct is tagged for chat in this catalog and works with OpenAI-compatible client libraries.

Coding

Qwen3-Coder-30B-A3B-Instruct is tagged for coding in this catalog and works with OpenAI-compatible client libraries.

FAQ

Qwen3-Coder-30B-A3B-Instruct free API FAQ

Is Qwen3-Coder-30B-A3B-Instruct free to use?

Qwen3-Coder-30B-A3B-Instruct is listed with free API access on OVHcloud AI Endpoints, subject to the provider's quota and account policy.

What is the Qwen3-Coder-30B-A3B-Instruct model ID?

The model ID shown in this catalog is qwen3-coder-30b-a3b-instruct.

What are the Qwen3-Coder-30B-A3B-Instruct free tier rate limits on OVHcloud AI Endpoints?

The listed free tier limit is 2 RPM (anonymous). Limits can change per account tier, so confirm against the provider dashboard.

What context window does Qwen3-Coder-30B-A3B-Instruct support?

The listed context window is 262K tokens with up to 32K output tokens.

More about Qwen3-Coder-30B-A3B-Instruct

Qwen3 Coder 30B (3B active via MoE) on OVHcloud AI Endpoints is Alibaba's latest code-specialized model with 262K context — making it one of the few free coding models that can handle full codebase-level context. The 32K output ceiling supports generating full files and functions. OpenAI-compatible API on OVHcloud's European infrastructure. Registration required; ideal for EU developers seeking a coding-optimized model.

For API keys, setup steps, and provider-level limits, see the OVHcloud AI Endpoints provider page.