Free Tier Providers

These providers offer a genuine free tier or quota. You need a free API key from each provider -- no credit card required. Each preset includes a Get API Key link directly in the Add Provider form.

Version 1.0.18

Client configuration: Ready-to-paste setups for every client (OpenClaw, OpenCode, Claude Code, Codex CLI, Qwen Code, DeepSeek Harness, custom) live in the Client Setup section -- or open the provider's Prompt for AI dialog in the dashboard, which generates the config for you with your real proxy key and current model list included.

---

Ollama Cloud

Access frontier open-weight models hosted on Ollama's cloud. No local hardware or credit card required.

Models

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official catalog: ollama.com/search?c=cloud

Dashboard Setup

1. Quick Setup > Ollama Cloud > Create Provider.
2. Go to API Keys tab > add sk-not-required as the key (Ollama Cloud uses header auth; ClawRouter manages the flow).
3. Copy the Base URL.

Plan-gated models: Ollama Cloud returns HTTP 403 "this model requires a subscription, upgrade for access" for models outside your plan. ClawRouter classifies this as a model error -- your key stays enabled, and Model Fallback / the model circuit handle it automatically. There is no free-vs-paid marker in Ollama's API, so gated models are discovered at runtime: after a couple of failures they show an amber "Skipped" badge on the Models tab. Remove those models from your list (or upgrade your plan) to avoid fallback hops.

---

Google AI Studio (Gemini)

The most generous free tier with high rate limits. Requires a free API key from Google AI Studio.

Models

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list (includes per-model token limits and thinking support). Official catalog: ai.google.dev/gemini-api/docs/models

Note: Google Gemini uses v1beta in the Base URL, not v1.

Dashboard Setup

1. Quick Setup > Google Gemini > Create Provider.
2. Add your Google AI Studio API key(s) in the API Keys tab.
3. Copy the Base URL.

---

Groq (LPU Inference)

Extreme speed inference for open models. Free tier is rate-limited but completely free.

Models

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official catalog: console.groq.com/docs/models

Dashboard Setup

1. Quick Setup > Groq > Create Provider.
2. Add your Groq API key(s) in the API Keys tab.
3. Copy the Base URL.

---

OpenRouter (Free Tier)

Aggregator with many free models. Requires a free OpenRouter API key.

Free Models

The :free roster rotates constantly -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official catalog: openrouter.ai/models

Dashboard Setup

1. Quick Setup > OpenRouter > Create Provider.
2. Add your OpenRouter API key(s) in the API Keys tab.
3. Copy the Base URL.

---

NVIDIA NIM

High-performance hosted models. Free tier available via developer program.

Models

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official catalog: build.nvidia.com/models

Dashboard Setup

1. Quick Setup > NVIDIA NIM > Create Provider.
2. Add your NVIDIA API key(s) in the API Keys tab.
3. Copy the Base URL.

---

Cohere

Excellent for RAG and multilingual tasks. Free for development/research.

Two Cohere APIs: the preset targets Cohere's OpenAI-compatibility API (/compatibility/v1), which is fully OpenAI-shaped for both chat and /models. The native API (/v1) has no /v1/chat/completions endpoint and is not supported.

Models

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official catalog: docs.cohere.com/docs/models

---

Cerebras

Ultra-fast inference on open models.

Models

llama-3.3-70b, gpt-oss-120b, zai-glm-4.7, qwen-3-235b-a22b-instruct-2507, qwen-3-32b

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official docs: inference-docs.cerebras.ai

---

Cloudflare Workers AI

Models hosted on Cloudflare's global network. Free tier available.

Important: After creating the provider, open its Settings tab and replace YOUR_ACCOUNT_ID in the Upstream URL with your actual Cloudflare account ID.

Models

@cf/meta/llama-3.3-70b-instruct-fp8-fast, @cf/moonshotai/kimi-k2.6

Model lists change over time -- snapshot from August 2026. Official catalog: developers.cloudflare.com/workers-ai/models

Dashboard Setup

1. Quick Setup > Cloudflare Workers AI > Create Provider.
2. Edit the Upstream URL in the Settings tab to include your account ID.
3. Add your Cloudflare API token in the API Keys tab.
4. Copy the Base URL.

---

BytePlus ModelArk

ByteDance coding models (international endpoint). Free tier available during promotion.

Models

seed-2-0-pro-260328, seed-2-0-code-preview-260328, seed-2-0-mini-260215, kimi-k2-thinking-251104, glm-4-7-251222

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list. Official docs: docs.byteplus.com/en/docs/ModelArk

Dashboard Setup

1. Quick Setup > BytePlus ModelArk > Create Provider.
2. Add your BytePlus API key(s) in the API Keys tab.
3. Copy the Base URL.

---

API.airforce

Community free-tier gateway.

Models

anthropic/claude-3.7-sonnet, moonshot/kimi-k2.6, google/gemini-2.5-flash

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list.

---

Bazaarlink

Aggregated free & paid models.

Models

auto:free, claude-sonnet-4.6, gpt-5.4, kimi-k2.6, glm-5

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list.

---

Poolside

Coding-focused models.

Models

poolside/laguna-s-2.1, poolside/laguna-xs-2.1

Model lists change over time -- snapshot from August 2026. Use Models tab > Fetch Models for the live list.