Compare recurring free API tiers, signup credits and limited-time offers. Check eligibility, usage limits and billing terms before claiming.
Create a key in Google AI Studio in a supported location. Check the free-tier column for your model and the limits for your project. Paid projects have separate billing.
Models consume different numbers of Neurons. The allowance resets at 00:00 UTC. The Free plan stops at the limit. Workers Paid bills excess usage.
Choose a :free endpoint from the free model collection. Account limits apply per day and per minute. Check your key for remaining calls. A separately selected paid endpoint has its own price.
Limits apply to the organization. Check the request and token ceilings for your model. Hitting a limit returns HTTP 429. Your console shows the limits that apply to you.
Selected models in Singapore with International deployment qualify, including eligible Qwen variants. Each has its own balance. Validity starts at the latest of activation, model release or approval. Enable Free Quota Only to stop before paid usage.
The November 5 release notes offer the first two weeks free for text, image and video input. The provider specifies a two-week window without an exact closing hour. Check the current rate before calling the API.
OpenCode Console lists MiniMax M3.1 Flash Free under the ID minimax-m3.1-flash-free. Input, output, and cached read are Free; cached write is "-", not Free. Context is 1,000,000 tokens, with a 512,000-token output limit. OpenCode says it is free for a limited time and gives no end date. The provider follows a zero-retention policy and does not use your data for model training. Free-tier chat models require OpenCode. This is not MiniMax’s paid API pricing, and it is not the OpenCode Go paid model minimax-m3.1-flash ($0.15 input / $0.60 output per 1M tokens).
From November 9, 00:00 to November 15, 23:59 Beijing time, logging in to AutoClaw on the China site (autoclaw.zhipuai.cn) can claim 50 million tokens, once per account. The credits remain valid through November 15, 23:59. The official post does not give a credit conversion for the 50M. Actual balances follow the in-app activity page after login.
From November 9, 00:00 to November 15, 23:59 UTC+8, logging in to AutoClaw on the international site (autoclaw.z.ai) can claim 100 million tokens (worth 10,000 credits), once per account. The reward expires on November 15 at 23:59 UTC+8. Actual balances follow the in-app activity page after login.
OpenCode Console lists MiniMax M3.1 Flash Free (minimax-m3.1-flash-free) as free for a limited time. Input, output and cached read are Free; cached write is "-", not Free. The models API lists a 1,000,000-token context and a 512,000-token output limit, with no end date. The provider uses zero retention and does not use the data for training. Free-tier chat models require OpenCode. This is not MiniMax's paid API ($0.15/$0.60 per 1M; cached read $0.015) or OpenCode Go's paid minimax-m3.1-flash. Terms are on the Console Models page; enter via OpenCode Console. We haven't logged in to try it.
Through November 8, 2026, CodeRabbit says it will cover up to $5,000 in Deep Scan usage for any organization with two or more members, against a pool of up to $1 million that is first come, first served until it runs out. Eligible orgs include open-source projects, current or former customers, and teams that have never used CodeRabbit. CodeRabbit Secure uses GPT 6.1 Sol and GPT Cyber; Deep Scan examines committed code across a repository, independently verifies exploitability, and can draft fixes for eligible findings—developers still review and ship. As of October 27, 2026.
China’s National Supercomputing Internet (SCNet) MaaS page is running a new-user flash sale: DeepSeek-V4.1-Flash-1017 and GLM-5.3-Flash token packs at ¥0.10 each, 50 million tokens per pack. The campaign runs through Beijing time 2026-11-10 23:59. This is a domestic supercomputing-channel promo, not a global DeepSeek or Zhipu announcement.
The international AutoClaw official blog lists an M11W2 login perk from November 9, 00:00 to November 15, 23:59 UTC+8. Logging in during that window can claim 100 million tokens (worth 10,000 credits), once per account; the reward expires at November 15, 23:59 UTC+8. The China site (autoclaw.zhipuai.cn) uses the same dates in Beijing time, with 50 million tokens once per account, valid through November 15, 23:59; that official post does not give a credit conversion for the 50M. We have not claimed the perk; figures are for reference, and balances follow the in-app activity page after login.
OpenCode now lists Beam Free on Console under the ID beam-free, with a 1M context and a limited-time free tier. The docs say the provider does not train on your data and keeps it for 30 days for safety; some regions are blocked.
OpenCode now offers GLM 5.3 Flash as a free Console model under the ID glm-5.3-flash-free. The docs call it a limited-time free tier with zero retention and no training on your data.