Ernie Bot vs Kritt

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Ernie Bot Agents	Kritt Agents
Tagline	Baidu's Mandarin-first ChatGPT rival, powered by the ERNIE model family	AI-assisted code security research with parallel agents and verified findings
Category	Agents	Agents
Pricing	Freemium· Free tier for Ernie 3.5 access; Ernie 4.0 and premium features require a paid subscription (approximately CNY 59.9/month for individual plans); enterprise API pricing via Baidu AI Cloud Qianfan platform is metered per 1K tokens.	Freemium· open-kritt: Free (self-hosted, AGPL-3.0) / Single managed scan: $5,000 (up to 200k LoC) / Enterprise: custom pricing for CI/CD integration and dedicated support
Model	Baidu ERNIE 4.0 / ERNIE X1 / ERNIE Turbo (in-house)	Codex and Claude Code (as agent harnesses)
Editorial score	8.7 / 10	—
Use cases	Mandarin content writing and marketing copyChinese-language document Q&A and summarisationBaidu-search-grounded research briefsCustom agents built on the Qianfan platformRetrieval-augmented chat over internal Chinese corporaCode generation and explanation in ChineseImage generation from Chinese promptsCustomer-service chatbots for mainland usersFine-tuning ERNIE models on domain data	Pre-launch security audit of a new serviceContinuous vulnerability scanning in CI/CDBug bounty research on open-source targetsAttack-surface mapping for acquired codebasesVerified proof-of-concept generation for reported bugsCustom-rule appsec review at scaleTriage reduction for existing SAST pipelinesDeep-dive review of security-sensitive modules (auth, crypto, parsers)
Pros	Best-in-class Mandarin fluency and Chinese cultural/idiomatic understanding among major LLMs Deep integration with Baidu Search, Wenku, Netdisk and Maps for grounded Chinese-language answers Full agent/plugin platform (Qianfan) with function calling, RAG, and fine-tuning for enterprise developers Multiple model tiers (Ernie 4.0, X1 reasoning, Turbo) covering quality-vs-cost trade-offs Native image generation and document/PDF understanding built into the chat UI Compliant, in-country hosting that satisfies Chinese data-residency and regulatory requirements Very large free tier makes it accessible for individual and small-team experimentation	Parallel-agent architecture covers large codebases faster than sequential AI review passes Verification stage attempts to confirm exploitability, cutting the LLM false-positive rate that plagues single-shot audits Open-source self-hosted build (AGPL-3.0) lets teams run it against private code with their own model keys Bring-your-own harness: works with Codex and Claude Code so you can pick the frontier model that fits your budget Custom severity rules and verification scripts let security teams encode their own threat model Fixed-price managed scan option ($5k up to 200k LoC) gives a predictable path for teams without in-house AI-sec expertise
Cons	Subject to Chinese government censorship; refuses politically sensitive topics and self-censors on sovereignty issues Web app and most documentation are Chinese-only, with a steep onboarding curve for non-Mandarin teams Requires a mainland Chinese phone number for sign-up, which blocks most international users English-language performance and reasoning lag Western frontier models (GPT-4o, Claude, Gemini) Data submitted may be processed under PRC data laws, which is a non-starter for many Western enterprises Ecosystem lock-in to Baidu AI Cloud for serious production use	Managed scan pricing is steep for indie developers or small startups compared to traditional SAST tools Self-hosting still requires paying for the underlying frontier model API usage, which can be substantial on large repos AGPL-3.0 licensing on the open-source build is incompatible with some proprietary product integrations No standalone REST API documented publicly; automation lives at the CLI/workflow layer Effectiveness is bounded by the underlying LLMs' understanding of the language and framework; niche stacks may see weaker coverage Newer entrant relative to established SAST/DAST vendors, so tooling maturity and integrations are still evolving
Website	yiyan.baidu.com	kritt.ai

Pick Ernie Bot if

✅ Best-in-class Mandarin fluency and Chinese cultural/idiomatic understanding among major LLMs
✅ Deep integration with Baidu Search, Wenku, Netdisk and Maps for grounded Chinese-language answers
✅ Full agent/plugin platform (Qianfan) with function calling, RAG, and fine-tuning for enterprise developers
✅ Multiple model tiers (Ernie 4.0, X1 reasoning, Turbo) covering quality-vs-cost trade-offs

Pick Kritt if

✅ Parallel-agent architecture covers large codebases faster than sequential AI review passes
✅ Verification stage attempts to confirm exploitability, cutting the LLM false-positive rate that plagues single-shot audits
✅ Open-source self-hosted build (AGPL-3.0) lets teams run it against private code with their own model keys
✅ Bring-your-own harness: works with Codex and Claude Code so you can pick the frontier model that fits your budget

Compare a different pair →