Free tokens for your coding agent. On open models.

• 
  DeepSeek V4.1 Flash (includes the 1017 update)deepseek-ai/DeepSeek-V4.1-FlashFree, then$0.0735 in, $0.221 out / 1M on shared capacity$0.147 in, $0.441 out when it's busy
• 
  GLM 5.3 Flashzai-org/GLM-5.3-FlashFree, then$0.0788 in, $0.263 out / 1M on shared capacity$0.158 in, $0.525 out when it's busy
• 
  GLM 5.3zai-org/GLM-5.3Free, then$0.295 in, $1.31 out / 1M on shared capacity$0.591 in, $2.63 out when it's busy
• 
  gpt-oss 120Bopenai/gpt-oss-120bFree, then$0.0194 in, $0.0893 out / 1M on shared capacity$0.0389 in, $0.179 out when it's busy
• 
  Qwen3.8 FlashQwen/Qwen3.8-FlashFree, then$0.0593 in, $0.201 out / 1M on shared capacity$0.119 in, $0.401 out when it's busy

• Free usage comes in a current session, which starts with your first free request, and a week, which resets every Monday. Whichever runs out first stops free requests until it resets.

• Your API keys page shows how much of each you have used, and when each resets.

• Every request counts: the prompt, cached tokens included, and the reply. Longer requests and larger models use more of it.

• The free usage is the workspace's: every key and member of it shares it.

• Past your free usage, a workspace with credit carries on at half the list price on shared capacity, and the list price when it's busy. Without credit, requests stop until it resets, and the answer says when (free_allowance_used).

• When free capacity is busy, a workspace with credit is served instead at half the list price on shared capacity, and the list price when it's busy. Without credit, retry in a minute (free_capacity_busy).

• Free requests are served by third-party model providers, who handle prompts and outputs under their own terms. Read the privacy policy.

Paste it into your coding agent. It sets itself up with DeepSeek V4.1 Flash and asks you for an API key: sign in with GitHub first, and the free tokens apply to it.