Reference dashboard · AI providers
AI providers for developers & RAG
Independent landscape view: context windows, API pricing, deployment type, and aggregator flags — all data baked at build time from curated YAML + live merge pipeline. Browse all 444 models.
Data debug & refresh fresh
Optional enrichments partial: HF Hub meta-llama/Llama-3.1-8B: HTTP Error 401: Unauthorized
Force-fetch runs in GitHub Actions (not in the browser). Each button opens the workflow to run manually.
Providers at a glance
Google Gemini
Gemini 3.1 Pro Preview (batch) google/gemini-3.1-pro-preview:batch
API- Context:
- 1,048,576 aggregator
- Input/1M:
- $1.00 aggregator
- Output/1M:
- $6.00 aggregator
Deep Google ecosystem integration and strong multimodal capabilities.
Anthropic Claude
Claude Sonnet 5 (batch) anthropic/claude-sonnet-5:batch
API- Context:
- 1,000,000 aggregator
- Input/1M:
- $1.00 aggregator
- Output/1M:
- $5.00 aggregator
Safety-first design with Constitutional AI.
OpenAI ChatGPT
GPT-5.6 Sol Pro (batch) openai/gpt-5.6-sol-pro:batch
API- Context:
- 1,050,000 aggregator
- Input/1M:
- $1.00 aggregator
- Output/1M:
- $5.00 aggregator
Market leader with custom GPTs and broad tooling.
X Grok
Grok 4.6 x-ai/grok-4.6
API- Context:
- 500,000 aggregator
- Input/1M:
- $2.00 aggregator
- Output/1M:
- $6.00 aggregator
Real-time X platform data integration.
Mistral AI
Mistral Medium 3.5 (batch) mistralai/mistral-medium-3-5:batch
APISelf-hosted- Context:
- 262,144 aggregator
- Input/1M:
- $0.75 aggregator
- Output/1M:
- $3.75 aggregator
European provider — privacy, open weights, efficiency.
Meta Llama
Llama 4 Maverick meta-llama/llama-4-maverick
APISelf-hosted- Context:
- 1,048,576 aggregator
- Input/1M:
- $0.19 aggregator
- Output/1M:
- $0.65 aggregator
Open weights with very large context windows.
Perplexity AI
Sonar Pro Search perplexity/sonar-pro-search
API- Context:
- 200,000 aggregator
- Input/1M:
- $3.00 aggregator
- Output/1M:
- $15.00 aggregator
Cited answers with verifiable sources.
Context length
Context window via OpenRouter (log scale)
API pricing (USD / 1M tokens)
Input and output USD per 1M tokens via OpenRouter