Docs
Providers
Prompt Management Studio chats with these providers through their OpenAI-compatible APIs. Each one has a free tier; add your own API key in the Chat tab to use it.
Prices are listed paid rates in USD per 1M tokens. Requests within a provider's free tier cost nothing; set a price to 0 in the Models tab to track them that way. You can also edit any price, or add models that aren't listed here.
NVIDIA NIM
Phone verificationNeeds CORS proxyGet API keyThis provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://integrate.api.nvidia.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| z-ai/glm-5.3-flash | 1M | Up to 40 RPM | $0.15 | $0.5 |
| z-ai/glm-5.2 | 1M | Up to 40 RPM | $1.4 | $4.4 |
| z-ai/glm-5.1 | 202K | Up to 40 RPM | $1.285 | $4.07 |
ModelScope
RegistrationGet API keyBase URL https://api-inference.modelscope.cn/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
MiniMax-M2.5-highspeedMiniMax/MiniMax-M2.5 |
204K | — | $0.3 | $1.2 |
Qwen/Qwen3.5-35B-A3Bqwen-qwen3-5-35b-a3b |
256K | 2,000 RPD total; <=500 | $0.25 | $2 |
Qwen/Qwen3.5-27Bqwen-qwen3-5-27b |
256K | 2,000 RPD total; <=500 | $0.3 | $2.4 |
Cloudflare Workers AI
No card neededNeeds CORS proxyGet API keyReplace {account_id} in the Base URL with your Cloudflare account ID.
This provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Mistral 7B@cf/mistral/mistral-7b-instruct-v0.1 |
32K | — | — | — |
Qwen 1.5 7B@cf/qwen/qwen1.5-7b-chat |
32K | — | — | — |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | 24K | 10K neurons/day (shared) | $0.71 | $0.72 |
OpenCode Zen
RegistrationNeeds CORS proxyGet API keyThis provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://opencode.ai/zen/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| big-pickle | — | — | $0 | $0 |
DeepSeek V4 Flashdeepseek-v4-flash-free |
1M | — | $0 | $0 |
MiMo-V2.5mimo-v2.5-free |
1M | — | $0 | $0 |
OpenRouter
RegistrationGet API keyBase URL https://openrouter.ai/api/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
NVIDIA: Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:free |
1M | — | $0 | $0 |
NVIDIA: Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:free |
1M | — | $0.06 | $0.2 |
Poolside: Laguna S 2.1 (free)poolside/laguna-s-2.1:free |
262K | — | $0 | $0 |
LLM7.io
No card neededGet API keyBase URL https://api.llm7.io/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
gpt-oss:20bgpt-oss-20b |
128K | 60 RPM, 250 req/hr (fre | — | — |
| mistral-Nemo-Instruct-2407 | 128K | 60 RPM, 250 req/hr (fre | — | — |
| minimax-m2.7 | 180K | 60 RPM, 250 req/hr (fre | $0.3 | $1.2 |
Kilo Code
No card neededNeeds CORS proxyGet API keyThis provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://api.kilo.ai/api/gateway
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| nvidia/nemotron-3-ultra-550b-a55b:free | 1M | 200 req/hr | $0 | $0 |
stepfun/step-3.7-flash:freestepfun/step-3.7-flash |
262K | 200 req/hr | $0.2 | $1.15 |
| nvidia/nemotron-3-super-120b-a12b:free | 262K | 200 req/hr | $0 | $0 |
Google Gemini
No card neededGet API keyBase URL https://generativelanguage.googleapis.com/v1beta/openai
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Gemini 3.8 Flashgemini-3.8-flash |
1M | — | $0.75 | $3.75 |
Gemini 3.7 Flashgemini-3.7-flash |
1M | — | $0.75 | $3.75 |
Gemini 3.6 Flashgemini-3.6-flash |
1M | 15 RPM, 1,500 RPD | $0.75 | $3.75 |
Ollama Cloud
RegistrationNeeds CORS proxyGet API keyThis provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://ollama.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| deepseek-v4-pro | 1M | Session/weekly limits ( | $1.32 | $3.96 |
| deepseek-v4-flash | 1M | Session/weekly limits ( | $0.44 | $1.32 |
| minimax-m3 | 512K | Session/weekly limits ( | $0.3 | $1.2 |
Mistral AI
No card neededGet API keyBase URL https://api.mistral.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Mistral 7Bopen-mistral-7b |
32K | — | $0.25 | $0.25 |
Mixtral 8x7Bopen-mixtral-8x7b |
32K | — | $0.7 | $0.7 |
Mistral Medium 3.5 (128B)mistral-medium-3-5-128b |
256K | ~1 RPS, 500K TPM | — | — |
OVHcloud AI Endpoints
RegistrationGet API keyBase URL https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Qwen3.5-397B-A17Bqwen3.5-397b-a17b |
262K | 2 RPM (anonymous) | $0.6 | $3.6 |
Meta-Llama-3_3-70B-Instructmeta-llama-3_3-70b-instruct |
131K | 2 RPM (anonymous) | $0.71 | $0.72 |
Qwen3.8-27Bqwen3.8-27b |
262K | 2 RPM (anonymous) | $0.5 | $3 |
Groq
No card neededGet API keyBase URL https://api.groq.com/openai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Moonshot Kimi K2moonshotai/kimi-k2-instruct |
131K | — | $0.6 | $2.5 |
Moonshot Kimi K2 0905moonshotai/kimi-k2-instruct-0905 |
131K | — | $0.6 | $2.5 |
| groq/compound | 131K | 30 RPM, 250 RPD | — | — |
Cohere
No card neededGet API keyBase URL https://api.cohere.ai/compatibility/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Command A+ (218B)command-a-218b |
128K | 20 RPM | — | — |
Command A (111B)command-a-111b |
256K | 20 RPM | — | — |
Command R+command-r |
128K | 20 RPM | — | — |
Aion Labs
RegistrationGet API keyBase URL https://api.aionlabs.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
aion-labs/aion-2.0aion-labs-aion-2-0 |
128K | 15 RPM, 20K TPD | — | — |
aion-labs/aion-rp-llama-3.1-8baion-labs-aion-rp-llama-3-1-8b |
32K | 15 RPM, 20K TPD | — | — |
aion-labs/aion-3.0aion-labs-aion-3-0 |
128K | 15 RPM, 20K TPD | — | — |
Hugging Face
No card neededGet API keyBase URL https://router.huggingface.co/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Meta-Llama-3.1-8B-Instructmeta-llama-3-1-8b-instruct |
128K | Credit-metered | $0.035 | $0.065 |
gemma-3-4b-itgoogle/gemma-3-4b-it |
131K | Credit-metered | $0 | $0 |
| phi-4 | 16K | Credit-metered | $0.125 | $0.5 |
Z AI (Zhipu AI)
No card neededGet API keyWorks with z.ai keys. Free models: glm-4.5-flash, glm-4.7-flash.
Base URL https://open.bigmodel.cn/api/paas/v4
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
GLM-4.5-Flashglm-4.5-flash |
128K | 1 concurrent request | $0 | $0 |
GLM-4.7-Flashglm-4.7-flash |
200K | 1 concurrent request | $0 | $0 |
GLM-4.5-Flash (retirement announced)glm-4-5-flash-retirement-announced |
128K | 1 concurrent request | — | — |
GLM-4.6V-Flashglm-4.6v-flash |
128K | 1 concurrent request | $0.575 | $2.2 |
Cerebras
No card neededGet API keyBase URL https://api.cerebras.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Llama 3.1 70Bllama3.1-70b |
131K | — | $0.56 | $0.56 |
zai-glm-4.7 (deprecated Aug 2026)zai-glm-4-7-deprecated-aug-2026 |
131K | 5 RPM, 30K TPM, 1M TPD | — | — |
| zai-glm-4.7 | 128K | 10 RPM, 100 RPD, 1M TPD | $2.25 | $2.75 |
Agnes AI
RegistrationGet API keyBase URL https://apihub.agnes-ai.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| agnes-1.5-flash | 256K | 30 RPM | — | — |
| agnes-2.0-flash | 256K | 30 RPM | $0 | $0 |
| agnes-image-2.0-flash | 4K | 30 RPM (1K) | — | — |
Alibaba Cloud Model Studio
RegistrationGet API keyBase URL https://dashscope-intl.aliyuncs.com/compatible-mode/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Qwen3-Maxqwen3-max |
128K | Tiered by region | $1.2 | $6 |
Qwen3-Plusqwen3-plus |
1M | Tiered by region | — | — |
Qwen3-VL-Plusqwen3-vl-plus |
128K | Tiered by region | $0.2 | $1.6 |
SiliconFlow
RegistrationGet API keyBase URL https://api.siliconflow.cn/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
| Qwen/Qwen3-8B | 128K | 1,000 RPM, 50,000 TPM | $0.2 | $0.2 |
deepseek-ai/DeepSeek-R1-Distill-Qwen-7Bdeepseek-ai-deepseek-r1-distill-qwen-7b |
131K | 30 RPM, 60K TPM | — | — |
SambaNova
RegistrationNeeds CORS proxyGet API keyThis provider rejects requests from browsers. It only works in Prompt Management Studio if you set its Base URL to a CORS proxy that forwards to it.
Base URL https://api.sambanova.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
DeepSeek-V3.1deepseek-v3-1 |
128K | 20 RPM, 20 RPD, 200K TPD | $0.56 | $1.68 |
DeepSeek-V3.2 (Preview)deepseek-v3-2-preview |
128K | 20 RPM, 20 RPD, 200K TPD | — | — |
MiniMax-M2.7minimax-m2-7 |
128K | 20 RPM, 20 RPD, 200K TPD | $0.3 | $1.2 |
xAI
RegistrationGet API keyBase URL https://api.x.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
grok-4.3grok-4-3 |
1M | Credit-based | $1.25 | $2.5 |
grok-4.1-fastgrok-4-1-fast |
2M | Credit-based | — | — |
| grok-3-mini | 131K | Credit-based | — | — |
Chutes.ai
RegistrationGet API keyBase URL https://api.chutes.ai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
DeepSeek-R1deepseek-ai/DeepSeek-R1 |
131K | Community-powered, no h | $1.35 | $3 |
Llama 3.1 70Bmeta-llama/Meta-Llama-3.1-70B-Instruct |
131K | Community-powered, no h | $0.56 | $0.56 |
Synthetic (formerly GLHF)
RegistrationGet API keyBase URL https://api.synthetic.new/openai/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Llama 3.1 70Bmeta-llama/Meta-Llama-3.1-70B-Instruct |
131K | Unlimited for free models | $0.56 | $0.56 |
Mixtral 8x7Bmistralai/Mixtral-8x7B-Instruct-v0.1 |
32K | Unlimited for free models | — | — |
AI21 Labs
RegistrationGet API keyBase URL https://api.ai21.com/studio/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Jamba Large 1.7jamba-large-1-7 |
256K | 200 RPM, 10 RPS | — | — |
Jamba Mini 2jamba-mini-2 |
256K | 200 RPM, 10 RPS | — | — |
DeepSeek
RegistrationGet API keyBase URL https://api.deepseek.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
deepseek-chat (V3.2)deepseek-chat-v3-2 |
128K | Dynamic | $0.28 | $0.42 |
deepseek-reasoner (R1)deepseek-reasoner-r1 |
128K | Dynamic | — | — |
Nscale
RegistrationGet API keyBase URL https://inference.api.nscale.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Llama-3.3-70B-Instructllama-3-3-70b-instruct |
128K | Fair-use | $0.71 | $0.72 |
DeepSeek-R1-Distill-Llama-70Bdeepseek-r1-distill-llama-70b |
128K | Fair-use | $0.7 | $1.1 |
Nebius
RegistrationGet API keyBase URL https://api.studio.nebius.com/v1
| Model | Context | Free tier limit | Input $ / 1M | Output $ / 1M |
|---|---|---|---|---|
Qwen3-235B-A22Bqwen3-235b-a22b |
128K | Tier-based | $0.22 | $0.88 |
Provider and model list: https://github.com/open-free-llm-api/awesome-freellm-apis (MIT); listed prices from freellm.net model pages. Free tiers, limits and prices change often; check the provider's own site before relying on them.