DeepSeek has no free API path in our catalog. Verified 2026-10-08. Our row: DeepSeek API.
Free API paths in our catalog from other providers:
BazaarLink free gateway tier (BazaarLink): Free tier on an OpenAI-compatible gateway: 10 requests/minute and 60 weighted units/day per account (longer inputs use more units), shared across the free models, no credit card and no waitlist (“Sign up and get a free key in under 60 seconds. No credit card, no waitlist.”). Accounts that have added credit get 20 RPM and 120 units/day. Verified 2026-10-06. Full caveats.
Workers AI free daily neurons (Cloudflare): 10,000 Neurons/day (~$0.11 of compute) at no charge, resetting 00:00 UTC — the same allocation on both the Workers Free and Workers Paid plans. Covers most of the catalog (Llama, DeepSeek distills, Gemma, Qwen, embeddings, image gen), but NOT all of it: see caveats. Verified 2026-10-06. Full caveats.
OpenRouter :free model variants (OpenRouter): Rotating set of :free model variants — 16 of 467 models carried a :free suffix at $0 prompt and completion when read from openrouter.ai/api/v1/models on 2026-10-08: NVIDIA Nemotron 3 (nano-omni-30b reasoning, super-120b, ultra-550b, 3.5-content-safety, 3.5-lightning), Thinking Machines Inkling and Inkling Small, Poolside Laguna S/XS 2.1, InclusionAI Ling 3.0 Flash Sante, Google Gemma 4 (26b-a4b-it, 31b-it), Cohere North Mini Code, Liquid LFM 2.5 2.6b, dots-studio Dots 3 Note Preview, Apodex 1.1 Mini. Limits: 20 req/min; 50 req/day if lifetime purchases < $10, 1,000 req/day after a one-time $10 credit purchase. Verified 2026-10-08. Full caveats.
GLM Flash models ($0) (Z.ai (Zhipu)): GLM-4.7-Flash and GLM-4.5-Flash (text) and GLM-4.6V-Flash (vision) priced $0 for input, cached input, and output — ongoing, OpenAI-compatible endpoint. Verified 2026-10-06. Full caveats.
Not affiliated with DeepSeek or any provider named here; names are their owners' marks.