All coding subscriptions

Qoder Free (international)

Qoderfree
$0
Last checked: 2026-10-27

This tier is sold in China too, at a price the vendor sets for that market: Qoder CN 个人体验版¥0 per month

First limit you hit
No published credit rate
Equivalent API value
—
Value multiple
—
When it runs out
Stops until the window resets
Scenario
Interactive use only

Allowances

300Credits, one-off grant with the 2-week trial
›The vendor's own wording
"The 2-week Pro Trial includes - 300 credits". The Free column of the plan table states its own quota without a figure — "- Basic models for limited user messages." — so the 300 is the trial grant, not a monthly refresh. The trial is once per person: "This offer is limited to one account per user; any additional trial accounts created will be frozen."
Open the source page
Vendor publishes no figure

code completions and next edits, size unstated

›The vendor's own wording
The Free column lists completions without a figure: "- Limited completions and next edits (NES)".
Open the source page

Models included

ModelCapabilityBurn rate
Autodefaultuntiered0.5"Intelligently selects the most suitable model, balancing performance and cost" — "recommended as default".
Ultimateuntiered2"Expert-level deep reasoning and thinking capabilities"
Performanceuntiered1.1"Advanced reasoning capabilities, high-quality output"
Efficientuntiered0.3"Standard reasoning capabilities, high cost-effectiveness". 0.0× for paid users while an open-ended promotion runs; 0.3× is the regular rate.
Qwen3.8-Maxuntiered0.5"Qwen's latest foundation model, with 2.4T parameters, leading in software engineering, office work, and deep reasoning"
Qwen3.8-Flashuntiered0.1"Qwen's open-weight multimodal MoE model"
Qwen3.7-Maxuntiered0.5"top-tier agentic capabilities, autonomously handles complex tasks up to 35 hours long"
Qwen3.7-Plusuntiered0.1"Comprehensive leap in reasoning capability, efficiency, and multimodal experience"
DeepSeek-V4-Prountiered0.5"Excels at complex reasoning, code generation, and engineering tasks"
DeepSeek-Flashuntiered0.1"Fast reasoning and low cost with balanced capabilities"
GLM-5.3untiered0.8"Zhipu's open-source flagship model, with coding capabilities competitive with leading international models"
GLM-5.3-Flashuntiered0.1"natively multimodal model, with deep image and video understanding"
Kimi-K3untiered1.4"Kimi's most powerful model, with 2.8T parameters, built for software engineering, knowledge work, and deep reasoning"
Kimi-K2.8-Previewuntiered0.8"Built for long-context coding: precise instruction following and reliable execution of long-running tasks."
MiniMax-M3untiered0.2"Native multimodal perception, frontier coding, and 1M context depth for highly demanding workflows"

Subscription versus your own API key

This compares two ways of working the same way — in an IDE or CLI, where BYOK tools make a direct API key a real option. It is not a claim that subscriptions are cheaper than the API in general.

ModelEffective price / 1M tokensvs API rateBreakeven
Qwen3.8-Maxuntiered——0.0M
Qwen3.8-Flashuntiered——0.0M
Qwen3.7-Maxuntiered——0.0M
Qwen3.7-Plusuntiered——0.0M
DeepSeek-V4-Prountiered——0.0M
DeepSeek-Flashuntiered——0.0M
GLM-5.3untiered——0.0M
GLM-5.3-Flashuntiered——0.0M
Kimi-K3untiered——0.0M
MiniMax-M3untiered——0.0M

Usage terms

Quoted from the vendor's own terms. We do not give legal advice.

A seat is bounded to Qoder's own clients. The Teams comparison enumerates the supported products as "Qoder Desktop", "QoderWork", "QoderWake", "Qoder JetBrains Plugin", "Qoder CLI", "Cloud Agents" and "Qoder Mobile", with no third-party client named anywhere. No inference endpoint is published for a plan: the individual tiers have no entry at all in the "Openness / OpenAPI" row of the pricing page's feature matrix, which reaches "Basic API" only at Teams, and that API is administrative — "Use the **Qoder Teams OpenAPI** to query members, usage, and AI code metrics at the organization level."

Change history

  1. 2026-10-14Recorded from the seed file
  2. 2026-07-29Recorded from the seed file