Home / Models AI model directory Search 395 stable model pages across every model type available from OpenRouter. Temporary aliases and automatic-routing entries are excluded.
Text: 294 Video: 16 Embeddings: 25 Image: 34 Speech: 13 Reranking: 3 Transcription: 10
No models match these filters.
Model I Current pricing & context
Input price $2.5 / 1M tokens
Context 8K Speed measurements
500-token response N/a
Response starts N/a
Output speed N/a Model details
Model type Text
Provider options 1 Model T Current pricing & context
Input price $0.25 / 1M tokens
Context 65.5K Speed measurements
500-token response 12.88 s
Response starts 0.38 s
Output speed 40.0 tok/s Model details
Model type Text
Provider options 1 Model ML Current pricing & context
Input price $0.345 / 1M tokens
Context 131.1K Speed measurements
500-token response 12.08 s
Response starts 0.45 s
Output speed 43.0 tok/s Model details
Model type Text
Provider options 1 Model ML Current pricing & context
Input price $0.027 / 1M tokens
Context 131.1K Speed measurements
500-token response 9.22 s
Response starts 0.13 s
Output speed 55.0 tok/s Model details
Model type Text
Provider options 1 Model ML Current pricing & context
Input price $0.05 / 1M tokens
Context 131.1K Speed measurements
500-token response 7.67 s
Response starts 0.20 s
Output speed 68.0 tok/s Model details
Model type Text
Provider options 2 Model Q Current pricing & context
Input price $0.36 / 1M tokens
Context 131.1K Speed measurements
500-token response 25.49 s
Response starts 0.49 s
Output speed 23.0 tok/s Model details
Model type Text
Provider options 2 Model C Current pricing & context
Input price $0.15 / 1M tokens
Context 128K Speed measurements
500-token response 11.36 s
Response starts 0.25 s
Output speed 45.0 tok/s Model details
Model type Text
Provider options 1 Model C Current pricing & context
Input price $2.5 / 1M tokens
Context 128K Speed measurements
500-token response 12.05 s
Response starts 0.15 s
Output speed 42.0 tok/s Model details
Model type Text
Provider options 1 Model S Current pricing & context
Input price $0.85 / 1M tokens
Context 131.1K Speed measurements
500-token response 10.46 s
Response starts 0.26 s
Output speed 49.0 tok/s Model details
Model type Text
Provider options 2 Model N Current pricing & context
Input price $0.7 / 1M tokens
Context 131.1K Speed measurements
500-token response 17.72 s
Response starts 0.48 s
Output speed 29.0 tok/s Model details
Model type Text
Provider options 1 Model N Current pricing & context
Input price $1 / 1M tokens
Context 131.1K Speed measurements
500-token response 26.98 s
Response starts 0.67 s
Output speed 19.0 tok/s Model details
Model type Text
Provider options 1 Model S Current pricing & context
Input price $0.04 / 1M tokens
Context 8.2K Speed measurements
500-token response 7.62 s
Response starts 0.16 s
Output speed 67.0 tok/s Model details
Model type Text
Provider options 2 Model O Current pricing & context
Input price $2.5 / 1M tokens
Context 128K Speed measurements
500-token response 17.68 s
Response starts 1.01 s
Output speed 30.0 tok/s Model details
Model type Text
Provider options 2 Model ML Current pricing & context
Input price $0.4 / 1M tokens
Context 131.1K Speed measurements
500-token response 9.05 s
Response starts 0.28 s
Output speed 57.0 tok/s Model details
Model type Text
Provider options 3 Model ML Current pricing & context
Input price $0.05 / 1M tokens
Context 131.1K Speed measurements
500-token response 4.67 s
Response starts 0.17 s
Output speed 115.0 tok/s Model details
Model type Text
Provider options 5 Model M Current pricing & context
Input price $0.02 / 1M tokens
Context 131.1K Speed measurements
500-token response 26.92 s
Response starts 0.60 s
Output speed 19.0 tok/s Model details
Model type Text
Provider options 4 Model O Current pricing & context
Input price $0.15 / 1M tokens
Context 128K Speed measurements
500-token response 14.04 s
Response starts 0.52 s
Output speed 37.0 tok/s Model details
Model type Text
Provider options 2 Model O Current pricing & context
Input price $0.15 / 1M tokens
Context 128K Speed measurements
500-token response 8.25 s
Response starts 0.56 s
Output speed 65.0 tok/s Model details
Model type Text
Provider options 1 Model G Current pricing & context
Input price $0.65 / 1M tokens
Context 8.2K Speed measurements
500-token response 22.53 s
Response starts 0.79 s
Output speed 23.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $2.5 / 1M tokens
Context 128K Speed measurements
500-token response 7.95 s
Response starts 0.69 s
Output speed 71.0 tok/s Model details
Model type Text
Provider options 2 Model O Current pricing & context
Input price $5 / 1M tokens
Context 128K Speed measurements
500-token response 7.97 s
Response starts 0.39 s
Output speed 66.0 tok/s Model details
Model type Text
Provider options 2 Model M Current pricing & context
Input price $2 / 1M tokens
Context 65.5K Speed measurements
500-token response 5.06 s
Response starts 0.35 s
Output speed 106.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $0.62 / 1M tokens
Context 65.5K Speed measurements
500-token response 39.52 s
Response starts 1.06 s
Output speed 13.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $10 / 1M tokens
Context 128K Speed measurements
500-token response 39.63 s
Response starts 1.17 s
Output speed 13.0 tok/s Model details
Model type Text
Provider options 1 Model A Current pricing & context
Input price $0.25 / 1M tokens
Context 200K Speed measurements
500-token response 6.94 s
Response starts 0.45 s
Output speed 77.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $2 / 1M tokens
Context 128K Speed measurements
500-token response 12.91 s
Response starts 0.72 s
Output speed 41.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $1 / 1M tokens
Context 4.1K Speed measurements
500-token response 27.01 s
Response starts 0.69 s
Output speed 19.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $10 / 1M tokens
Context 128K Speed measurements
500-token response N/a
Response starts N/a
Output speed N/a Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $1.5 / 1M tokens
Context 4.1K Speed measurements
500-token response 10.45 s
Response starts 1.28 s
Output speed 54.5 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $3 / 1M tokens
Context 16.4K Speed measurements
500-token response 24.49 s
Response starts 0.51 s
Output speed 21.0 tok/s Model details
Model type Text
Provider options 2 Model M Current pricing & context
Input price $0.75 / 1M tokens
Context 8K Speed measurements
500-token response 6.39 s
Response starts 1.13 s
Output speed 95.0 tok/s Model details
Model type Text
Provider options 1 Model U Current pricing & context
Input price $0.45 / 1M tokens
Context 6.1K Speed measurements
500-token response 15.82 s
Response starts 0.90 s
Output speed 33.5 tok/s Model details
Model type Text
Provider options 2 Model G Current pricing & context
Input price $0.06 / 1M tokens
Context 4.1K Speed measurements
500-token response 11.90 s
Response starts 0.27 s
Output speed 43.0 tok/s Model details
Model type Text
Provider options 3 Model O Current pricing & context
Input price $0.5 / 1M tokens
Context 16.4K Speed measurements
500-token response 8.74 s
Response starts 0.54 s
Output speed 61.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $30 / 1M tokens
Context 8.2K Speed measurements
500-token response 7.17 s
Response starts 0.72 s
Output speed 77.5 tok/s Model details
Model type Text
Provider options 2 Previous 1 … 6 7 Next Model data fetched Jul 15, 2026, 11:20 PM UTC .
Practical comparison guide
Find an AI model and compare its inference providers This directory indexes 395 stable AI model pages across text generation, image and video generation, embeddings, speech, transcription, and reranking. Use it to move from a model name or capability to the provider endpoints that actually serve it, then compare published prices, context limits, performance measurements, and routing details on one page.
Start with the workload Text models suit chat, coding, reasoning, and structured generation, while embeddings and rerankers support retrieval systems. Image, video, speech, and transcription models use different billing units, so the directory keeps their modalities explicit instead of forcing unlike prices into one ranking.
Check model and endpoint limits Context length, maximum output, accepted input types, quantization, and supported parameters can differ by model or route. Open a comparison page to confirm that an endpoint supports the request shape and scale required by your application.
Choose the host after the model The same model can vary substantially in token price, first-token wait, output speed, uptime, and regional availability across providers. Comparing the endpoint options helps avoid choosing a host based only on its headline price.
LLM provider leaderboard → Fastest inference providers → How comparisons are calculated → 
