awesome-free-ai-coding · every free model · every provider · filter the list

Where glm-4.6v-flash is free

2 rows on the list serve glm-4.6v-flash free: Z.ai (Zhipu GLM) and NovAI. None asks for a card. The providers’ last scheduled probes were on 2026-11-05; their offers are rechecked twice a week.

Every free model · the whole list

Who serves it free

Z.ai (Zhipu GLM)

🔌 LLM APIs with free tier · no card · last probe 2026-11-05 · listed since 2026-08-14

GLM Flash models free on the API, vision included (OpenAI-compatible at api.z.ai/api/paas/v4)

Provider-wide limits

• Limits, in the vendor’s words: Free Flash models: Usage allowance: amount not published (period not published) per account

GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash have free input and output prices. The flagship rows’ limited-time-free cached-storage column does not make their input or output free. No numerical rate or usage allowance is published.

• Base URL: https://api.z.ai/api/paas/v4
• Key: ZAI_GLM_API_KEY — get one at https://z.ai/manage-apikey/apikey-list
• Anthropic-format base (Claude Code’s ANTHROPIC_BASE_URL): https://api.z.ai/api/anthropic
• Callable ids: glm-4.6v-flash
• What you send is not used to train models (the vendor’s words).

NovAI

🧭 Aggregators (one key, many providers) · no card · last probe 2026-11-05 · listed since 2026-11-05

Hong Kong OpenAI-compatible gateway with a recurring free allowance on selected text and vision models, separate from its signup credit

Provider-wide limits

• Limits, in the vendor’s words: Shared free-model calls: 10 requests/day per account (before the first completed top-up). 00:00 UTC+8

5 requests/minute per account (before the first completed top-up)

Separate signup credit: $2 once per account (valid for 14 days)

Free chat calls: Unmetered requests per account (after any completed top-up; upstream provider limits still apply)

The daily allowance is shared across free chat, image and video models; media keep separate caps after a top-up. Calls at a cap return 429 until reset. An email account and API key are required. Signup accepts selected email providers and is screened for abuse. Paid models and top-ups are optional. The gateway says it does not store or train on prompts; upstream providers apply their own policies. Users must be at least 18.

• Base URL: https://aiapi-pro.com/v1
• Key: NOVAI_API_KEY — get one at https://aiapi-pro.com/register.html
• Callable ids: glm-4.6v-flash

Rows that listed it before

• Vercel AI Gateway — listed 2026-08-14 to 2026-08-20

Related models

• glm-5.3-flash — free at opencode, NVIDIA NIM (build.nvidia.com), Freebuff, AIHubMix (free models), ZCode (Z.ai) and FreeInference (Harvard SEAS)
• glm-4.7-flash — free at AIHubMix (free models), Z.ai (Zhipu GLM), NovAI and MegaNova (requires $1 top-up)
• glm-5.2 — free at AIHubMix (free models), Alibaba Cloud Model Studio (DashScope, international), Regolo AI and AtomCode
• glm-5.3 — free at AIHubMix (free models), Alibaba Cloud Model Studio (DashScope, international) and ZCode (Z.ai)
• glm-5 — free at Kiro and AIHubMix (free models)
• glm-5-turbo — free at AIHubMix (free models) and ZCode (Z.ai)
• glm-5.1 — free at AIHubMix (free models) and Alibaba Cloud Model Studio (DashScope, international)
• glm-4.6 — free at AIHubMix (free models)
• glm-4.7 — free at AIHubMix (free models)

---

Generated from registry.yaml on 2026-11-05 and re-verified twice a week; every free model on the list is at https://mvalentsev.github.io/awesome-free-ai-coding/models/, and the full list, the Atom feed and the machinery at https://github.com/mvalentsev/awesome-free-ai-coding.

Something wrong or missing? Suggest a service or a change — or read how the list works.