Usually strongest for direct vendor trust
LLMEndpoint
LLM API Provider Directory
Browse official APIs, inference platforms, aggregators, and OpenAI-compatible providers by model support, pricing notes, capabilities, and transparency signals.
Short answer
Use the directory for broad market scanning, not final selection. Filter down to a small shortlist, then switch to compare pages, provider reviews, and cost modeling before choosing a production provider.
22 providers indexed across official APIs, inference platforms, aggregators, and OpenAI-compatible endpoints.
Use the category chips for a quick pass, then switch to detailed filters when you are narrowing a shortlist.
Often useful for cost and speed research
Useful for migration and fallback planning
Start from the path that sounds like your job
If the full table feels too broad, use one of these entry points first.
I want the safest production starting point
Start in Official APIs first, then compare OpenAI, Anthropic, and Gemini before exploring cheaper or more flexible routes.
I want lower-cost or faster open-model routes
Go to inference providers if your main goal is cheaper open-model serving, speed experiments, or broader model access.
I want OpenAI-compatible migration options
Use the compatibility category if the team wants a lower-friction migration path before rewriting app logic.
I want routing, fallback, or gateway control
Go to aggregators and gateways if your problem is multi-provider operations rather than picking one direct model vendor.
How to use the directory well
The fastest path is filter, shortlist, compare, then model cost.
Workflow
Start from your app's use case
Use the finder first if you are not yet sure which provider category belongs in the shortlist.
WorkflowCompare finalists after filtering
Once the directory narrows the field, move into side-by-side comparisons rather than staying in the table.
WorkflowTurn browsing into a shortlist process
Use the shortlist guide when you need a more structured path from directory research to a buying decision.
22 providers match the current filters.
Use category chips for a quick pass, then combine filters to narrow the shortlist.
| Provider | Category | Supported models | OpenAI-compatible | Starting price | Context | Tool calling | Vision | Streaming | Status | Trust | Links |
|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenAI | Official APIs | GPT, reasoning models, embeddings, image | Yes | Budget to premium GPT tiers | Short to very long, model based | Yes | Yes | Yes | Available | 12/15 | |
| Anthropic | Official APIs | Claude, Claude Haiku, Claude Sonnet, Claude Opus | No | Mid to premium Claude tiers | Long context options | Yes | Yes | Yes | Available | 10/15 | |
| Google Gemini | Official APIs | Gemini, embedding models, multimodal models | Yes | Low-cost flash to premium tiers | Short to million-token-class options | Yes | Yes | Yes | Available | 11/15 | |
| Mistral AI | Official APIs | Mistral, Mixtral, Codestral, embeddings | Yes | Open and premium model tiers | Short to long, model based | Yes | No | Yes | Available | 11/15 | |
| DeepSeek | Official APIs | DeepSeek-V4-Flash, DeepSeek-V4-Pro | Yes | Low-cost flash to discounted pro tiers | 1M context, up to 384K output | Yes | No | Yes | Available | 11/15 | |
| xAI | Official APIs | Grok | Yes | Frontier-model pricing tiers | Mid to long, model based | Yes | Yes | Yes | Available | 11/15 | |
| Cohere | Official APIs | Command, Embed, Rerank | No | Enterprise and task-specific tiers | Task and model based | Yes | No | Yes | Available | 10/15 | |
| Together AI | Inference Providers | Llama, Qwen, DeepSeek-V4, Mistral | Yes | Often competitive for open models | Broad open-model range | No | Yes | Yes | Available | 11/15 | |
| Fireworks AI | Inference Providers | Llama, Qwen, DeepSeek-V4, Mistral | Yes | Competitive serverless tiers for open models | Broad open-model range, model specific | No | Yes | Yes | Available | 11/15 | |
| Groq | Inference Providers | Llama, Mixtral, Gemma, Whisper-like speech models | Yes | Speed-oriented model tiers | Selected fast-serving model range, model specific | Yes | No | Yes | Available | 11/15 | |
| DeepInfra | Inference Providers | Llama, Qwen, DeepSeek-V4, Mistral | Yes | Often low for open models | Broad open-model range, model specific | No | Yes | Yes | Available | 10/15 | |
| Replicate | Inference Providers | open models, image models, audio models, video models | No | Runtime dependent | Model dependent | No | Yes | Yes | Available | 10/15 | |
| Baseten | Inference Providers | custom models, open models | No | Deployment dependent | Model dependent | No | Yes | Yes | Available | 10/15 | |
| OpenRouter | LLM API Aggregators | GPT, Claude, Gemini, DeepSeek-V4 | Yes | Varies by model route | Model dependent across upstream routes | No | Yes | Yes | Available | 11/15 | |
| Portkey | LLM API Aggregators | GPT, Claude, Gemini, DeepSeek-V4 | Yes | Plan dependent plus provider spend | Provider dependent | No | Yes | Yes | Available | 11/15 | |
| LiteLLM Cloud | LLM API Aggregators | GPT, Claude, Gemini, Mistral | Yes | Plan dependent | Provider dependent | No | Yes | Yes | Unclear | 10/15 | |
| Helicone | LLM API Aggregators | provider dependent | Yes | Plan dependent | Provider dependent | No | Yes | Yes | Available | 11/15 | |
| Perplexity API | OpenAI-Compatible APIs | Sonar, online models | Yes | Varies by model | Model dependent | No | No | Yes | Available | 10/15 | |
| Novita AI | OpenAI-Compatible APIs | Llama, Qwen, DeepSeek-V4, image models | Yes | Varies by model | Model dependent | No | Yes | Yes | Unclear | 10/15 | |
| AI/ML API | OpenAI-Compatible APIs | GPT-style models, Claude-style access, Gemini-style access, open models | Yes | Varies by model | Model dependent | No | Yes | Yes | Unclear | 9/15 | |
| Anyscale Endpoints | Inference Providers | open models, custom deployments | Yes | Unclear | Model dependent | No | No | Yes | Unclear | 10/15 | |
| Voyage AI | Official APIs | embeddings, rerankers | No | Varies by model | Model dependent | No | No | No | Unclear | 9/15 |
Most practical starting points
These are common providers when teams want one strong baseline in each decision direction.
OpenAI
Official API for GPT models, multimodal capabilities, embeddings, realtime use cases, and broad developer tooling.
- general AI apps
- Budget to premium GPT tiers
- Trust 12/15
Anthropic
Official Claude API with strong long-context, coding, writing, and agent-oriented use cases.
- coding
- Mid to premium Claude tiers
- Trust 10/15
DeepSeek
Official DeepSeek API for the DeepSeek-V4 family, with OpenAI and Anthropic compatible formats plus very large context windows.
- cost-effective long-context apps
- Low-cost flash to discounted pro tiers
- Trust 11/15
OpenRouter
Unified API for accessing many models and providers through a routing and marketplace-style interface.
- model comparison
- Varies by model route
- Trust 11/15
DeepInfra
Serverless inference platform with a broad model catalog and OpenAI-compatible endpoints for many models.
- low-cost open model inference
- Often low for open models
- Trust 10/15
Compare these next
Once the table has helped you narrow the field, move into head-to-head decisions.
OpenAI vs AnthropicBest starting comparison for many production teams
OpenAI vs DeepSeekUseful if DeepSeek-V4 pricing and 1M context are part of the shortlist
OpenAI vs Google GeminiUseful if multimodal and ecosystem fit matter
Groq vs DeepInfraUseful if you are weighing speed against cheap open-model breadth