No credit card required
180 models across 8 providers offer a free developer tier that doesn't ask for a card up front — useful for prototyping before you commit spend.
"No card required" is recorded per provider from its own signup flow. Free tiers carry rate limits and can change; open each endpoint page for current price and terms.
Novita AI · 88 models
- Apodex 1.1 Mini (Novita)
- Baichuan M2 32B (Novita)
- DeepSeek R1 (Novita)
- DeepSeek V3.1 (Novita)
- DeepSeek V3.1 Terminus (Novita)
- DeepSeek V3.2 (Novita)
- DeepSeek V3.2 Exp (Novita)
- DeepSeek V4 Flash 0731 (Novita)
- DeepSeek V4 Flash Vision Exp (Novita)
- DeepSeek V4 Pro 0423 (Novita)
- DeepSeek V4 Pro 0813 (Novita)
- DeepSeek V4.1 Flash (Novita)
- DeepSeek V4.1 Flash 1017 (Novita)
- ERNIE 4.5 21B A3B (Novita)
- ERNIE 4.5 VL 424B A47B (Novita)
- Gemma 3 12B (Novita)
- Gemma 3 27B (Novita)
- Gemma 4 26B A4B (Novita)
- Gemma 4 31B (Novita)
- GLM 4.5 Air (Novita)
- GLM 4.5V (Novita)
- GLM 4.6 (Novita)
- GLM 4.6V (Novita)
- GLM 4.7 (Novita)
- GLM 4.7 Flash (Novita)
- GLM 5 (Novita)
- GLM 5.1 (Novita)
- GLM 5.3 Flash (Novita)
- GLM-4 32B (Novita)
- GLM-5.2 (Novita)
- GLM-5.3 (Novita)
- GLM-5V Turbo (Novita)
- GPT-OSS 20B (Novita)
- gpt-oss-120b (Novita)
- Hunyuan 3 (Novita)
- Hunyuan 4 Preview (Novita)
- Kimi K2 Thinking (Novita)
- Kimi K2.5 (Novita)
- Kimi K2.6 (Novita)
- Kimi K2.7 Code (Novita)
- Kimi K3 (Novita)
- Ling 3.0 Flash (Novita)
- Ling 3.0 Flash Fin (inclusionAI)
- Ling 3.0 Flash Sante (inclusionAI)
- Ling 3.0 Flash VL (inclusionAI)
- Ling 3.1 Flash (inclusionAI)
- Llama 3.1 8B (Novita)
- Llama 3.3 70B (Novita)
- Llama 4 Maverick (Novita)
- Llama 4 Scout (Novita)
- MiMo v2.5 (Novita)
- MiMo v2.5 Pro (Novita)
- MiMo-V2.6-Flash (Novita)
- MiMo-V2.6-Pro (Novita)
- MiniMax M1 (Novita)
- MiniMax M2 (Novita)
- MiniMax M2.1 (Novita)
- MiniMax M2.5 (Novita)
- MiniMax M2.7 (Novita)
- MiniMax M3 (Novita)
- Mistral Nemo (Novita)
- Nemotron 3 Nano 30B A3B (Novita)
- Qwen 2.5 72B (Novita)
- Qwen3 235B A22B Instruct 2507 (Novita)
- Qwen3 235B A22B Thinking 2507 (Novita)
- Qwen3 Coder (Novita)
- Qwen3 Coder 30B A3B Instruct (Novita)
- Qwen3 Coder Next (Novita)
- Qwen3 Max (Novita)
- Qwen3 Next 80B A3B Instruct (Novita)
- Qwen3 Omni 30B A3B Instruct (Novita)
- Qwen3 Omni 30B A3B Thinking (Novita)
- Qwen3 VL 235B A22B Instruct (Novita)
- Qwen3 VL 235B A22B Thinking (Novita)
- Qwen3 VL 30B A3B Instruct (Novita)
- Qwen3.5 397B A17B (Novita)
- Qwen3.5-122B-A10B (Novita)
- Qwen3.5-27B (Novita)
- Qwen3.5-35B-A3B (Novita)
- Qwen3.6 27B (Novita)
- Qwen3.6 35B A3B (Novita)
- Qwen3.7 Max (Novita)
- Qwen3.8 2.4T A95B (Novita)
- Qwen3.8 27B (Novita)
- Qwen3.8 Flash (Novita)
- Qwen3.8 Max (Novita)
- Step 3.7 Flash (Novita)
- Step 5 Preview (StepFun)
Google · 28 models
- Claude Fable 5 (Google Vertex)
- Claude Fable 5.1 (Google Vertex)
- Claude Opus 5 (Google Vertex)
- Claude Sonnet 5 (Google Vertex)
- DeepSeek V3.2 (Google Vertex)
- DeepSeek V4.1 Flash (Google)
- Gemini 2.5 Flash (Google)
- Gemini 2.5 Pro (Google)
- Gemini 3 Flash Preview (Google)
- Gemini 3.1 Pro Preview (Google)
- Gemini 3.5 Flash Lite (Google)
- Gemini 3.6 Flash
- Gemini 3.7 Flash (Google)
- Gemini 3.8 Flash (Google)
- Gemini 4 Argon (Google)
- Gemma 4 26B A4B (Google)
- GLM 4.7 (Google)
- gpt-oss-120b (Google)
- gpt-oss-20b (Google)
- Kimi K2 Thinking (Google)
- Llama 3.3 70B Instruct (Google)
- Llama 4 Maverick (Google)
- Llama 4 Scout (Google)
- MiniMax M2 (Google)
- Qwen3 235B A22B Instruct 2507 (Google)
- Qwen3 Coder (Google Vertex)
- Qwen3 Next 80B A3B Instruct (Google)
- Qwen3 Next 80B A3B Thinking (Google)
Cloudflare · 21 models
- DeepSeek V4 Flash 0423 (Cloudflare)
- DeepSeek V4 Flash 0731 (Cloudflare)
- DeepSeek V4 Pro 0423 (Cloudflare)
- DeepSeek V4 Pro 0813 (Cloudflare)
- DeepSeek V4.1 Flash (Cloudflare)
- DeepSeek V4.1 Flash 1017 (Cloudflare)
- Gemma 4 26B A4B (Cloudflare)
- GLM 4.7 Flash (Cloudflare)
- GLM 5.2 (Cloudflare)
- GLM 5.3 (Cloudflare)
- GLM 5.3 Flash (Cloudflare)
- Granite 4.0 Micro (Cloudflare)
- Kimi K2.6 (Cloudflare)
- Kimi K2.7 Code (Cloudflare)
- Llama 3.1 8B Instruct (Cloudflare)
- Llama 3.2 1B Instruct (Cloudflare)
- Llama 3.2 3B Instruct (Cloudflare)
- Llama 3.3 70B Instruct (Cloudflare)
- Mistral Small 3.1 24B (Cloudflare)
- Qwen2.5 Coder 32B Instruct (Cloudflare)
- Qwen3.8 27B (Cloudflare)
Mistral AI · 19 models
- Codestral 2508 (Mistral)
- Devstral 2 2512 (Mistral)
- GLM 5.2 (Mistral)
- GLM 5.3 (Mistral)
- Ministral 3 14B 2512 (Mistral)
- Ministral 3 3B 2512 (Mistral)
- Ministral 3 8B 2512 (Mistral)
- Mistral Large 3 (Mistral)
- Mistral Large 4 (Mistral)
- Mistral Medium (Mistral)
- Mistral Medium 3 (Mistral)
- Mistral Medium 3.1 (Mistral)
- Mistral Medium 3.5 (Mistral)
- Mistral Nemo (Mistral)
- Mistral Small 3.2 24B (Mistral)
- Mistral Small 4 (Mistral)
- Mixtral 8x22B Instruct (Mistral)
- Saba (Mistral)
- Voxtral Small 24B 2507 (Mistral)
Cohere · 10 models
Groq · 7 models
DeepSeek · 4 models
NVIDIA · 3 models
Looking for paid pricing? See best value and the cheapest-by-category pages from the index.