AI Providers
FleetRun supports 12+ AI model providers. All cloud providers use the OpenAI-compatible API format except Anthropic, which uses its native SDK. Add any provider in Settings → Providers.
How providers work
Each agent has a model_provider and model_name field. When a task runs, the agent worker resolves the provider from the providers table, reads the API key from the corresponding environment variable, and calls the model.
If the primary provider fails with a network error and ANTHROPIC_API_KEY is set, the router automatically falls back to Anthropic Claude.
Adding a provider
- Go to Settings → Providers in the FleetRun app.
- Click Add provider and select from the quickstart list, or enter custom values.
- Set the corresponding environment variable in your Vercel project settings.
- The provider health indicator turns green once the key is valid and the endpoint is reachable.
Provider reference
anthropic| Base URL | https://api.anthropic.com |
| Env var | ANTHROPIC_API_KEY |
| Get key | console.anthropic.com |
| Models | claude-opus-4-8claude-sonnet-4-6claude-haiku-4-5-20251001 |
Supports extended thinking and streaming. Native SDK used (not OpenAI-compat).
openai| Base URL | https://api.openai.com/v1 |
| Env var | OPENAI_API_KEY |
| Get key | platform.openai.com/api-keys |
| Models | gpt-4ogpt-4o-minio3o4-minigpt-4.1 |
OpenAI-compatible endpoint. Supports function calling and streaming.
gemini| Base URL | https://generativelanguage.googleapis.com/v1beta/openai |
| Env var | GEMINI_API_KEY |
| Get key | aistudio.google.com/app/apikey |
| Models | gemini-2.5-progemini-2.5-flashgemini-2.0-flashgemini-1.5-pro |
Uses the OpenAI-compatible endpoint exposed by Google AI Studio.
groq| Base URL | https://api.groq.com/openai/v1 |
| Env var | GROQ_API_KEY |
| Get key | console.groq.com |
| Models | llama-3.3-70b-versatilellama-3.1-8b-instantmixtral-8x7b-32768 |
LPU inference — fastest available latency for Llama and Mixtral models.
mistral| Base URL | https://api.mistral.ai/v1 |
| Env var | MISTRAL_API_KEY |
| Get key | console.mistral.ai |
| Models | mistral-large-latestmistral-small-latestcodestral-latestmistral-nemo |
Codestral is optimized for code completion and generation tasks.
deepseek| Base URL | https://api.deepseek.com/v1 |
| Env var | DEEPSEEK_API_KEY |
| Get key | platform.deepseek.com |
| Models | deepseek-chatdeepseek-reasoner |
deepseek-reasoner uses chain-of-thought and is ideal for multi-step reasoning.
xai| Base URL | https://api.x.ai/v1 |
| Env var | XAI_API_KEY |
| Get key | console.x.ai |
| Models | grok-3grok-3-minigrok-2-1212 |
Grok 3 has real-time web access. OpenAI-compatible API.
together| Base URL | https://api.together.xyz/v1 |
| Env var | TOGETHER_API_KEY |
| Get key | api.together.xyz/settings/api-keys |
| Models | meta-llama/Llama-3.3-70B-Instruct-Turbodeepseek-ai/DeepSeek-V3Qwen/Qwen2.5-72B-Instruct-Turbo |
200+ open-source models on a GPU cloud. Good balance of cost and quality.
perplexity| Base URL | https://api.perplexity.ai |
| Env var | PERPLEXITY_API_KEY |
| Get key | perplexity.ai/settings/api |
| Models | sonar-prosonarsonar-reasoning-prosonar-reasoning |
Sonar models include live web search. Ideal for research agents.
fireworks| Base URL | https://api.fireworks.ai/inference/v1 |
| Env var | FIREWORKS_API_KEY |
| Get key | fireworks.ai/account/api-keys |
| Models | accounts/fireworks/models/llama-v3p3-70b-instructaccounts/fireworks/models/deepseek-v3 |
Model IDs use the accounts/fireworks/models/<name> format.
openrouter| Base URL | https://openrouter.ai/api/v1 |
| Env var | OPENROUTER_API_KEY |
| Get key | openrouter.ai/keys |
| Models | anthropic/claude-opus-4google/gemini-2.5-prodeepseek/deepseek-r1 |
Single key routes to 200+ models. Prefix model names with the provider slug.
ollama_nas| Base URL | http://10.1.1.20:11434/v1 |
| Env var | OLLAMA_NAS_URL |
| Get key | ollama.com/download |
| Models | gemma4:26bllama3.3:70bqwen2.5:14bqwen2.5-coder:7b |
Runs locally on your NAS. No API key required. Model IDs are Ollama tag names.
Custom OpenAI-compatible endpoints
Any endpoint that speaks the OpenAI chat completions API can be added as a custom provider. In Settings → Providers, click Add provider and fill in:
- Key — a unique slug (e.g.
my_provider) - Label — display name
- Base URL — endpoint ending in
/v1 - API key env var — the env var name that holds the key (optional for local)
- Tag —
cloudorlocal