Catalogue
Models
455 models, and deliberately not every model there is: one earns a place by being sold by a provider we track, measured by a leaderboard we follow, or published as open weights by a lab we follow. Pointer names like “-latest” stay out, because they answer for whatever the vendor aimed them at that week.
How we choose what to list18 models
Granite3 sizes here
Granite 4.2 8BIBMGranite 4.2 8B is a downloadable text model from IBM whose licence allows commercial use, changes and redistribution (Apache License 2.0).writing162nd of 168 coding132nd of 168 agentsnot measuredeveryday153rd of 168 $0.060 / $0.25per 1Mvia OpenRouterGranite 4.1 8BIBMGranite 4.1 8B is a downloadable text model from IBM that you can run yourself or reach through a host, and its licence allows commercial use, changes and redistribution.writing147th of 168 coding143rd of 168 agentsnot measuredeveryday145th of 168 $0.050 / $0.10per 1Mvia OpenRouterGranite 4.0 MicroIBMGranite 4.0 Micro is a compact text-only model from IBM with a permissive Apache licence and a 131,000-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.017 / $0.11per 1Mvia Cloudflare Workers AIHy-MT2-7BTencentHy-MT2-7B is a compact seven-billion-parameter text model from Tencent released in August 2026.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.074 / $0.29per 1Mvia OpenRouterHy-MT2-1.8BTencentHy-MT2-1.8B is a tiny downloadable text model from Tencent with 1.8 billion parameters and an 8,192-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.044 / $0.18per 1Mvia OpenRouterQwen3.5-9BQwenAlibaba's 9-billion-parameter small downloadable model has a permissive Apache licence and an unusually large request limit for its size.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.10 / $0.15per 1Mvia OpenRouter
Ministral3 sizes here
Ministral 3 3B 2512Mistral AIMinistral 3 is a compact text-and-image model from Mistral AI with a permissive Apache licence and a 131,072-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.10 / $0.10per 1Mvia Mistral AIMinistral 3 8B 2512Mistral AIMinistral is a small downloadable model with a permissive Apache licence and a 262,144-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.15 / $0.15per 1Mvia Mistral AIMinistral 3 14B 2512Mistral AIMinistral 3 is a compact downloadable model from Mistral AI that handles text and images with a permissive Apache licence.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.20 / $0.20per 1Mvia Mistral AI
Qwen3 VL2 sizes here
Qwen3 VL 8B InstructQwenQwen3 VL is a compact vision-language model from Alibaba that accepts text and images and returns text.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.12 / $0.46per 1Mvia OpenRouterQwen3 VL 8B ThinkingQwenQwen3 VL is a small downloadable vision-language model that accepts text and images and can show its reasoning step by step.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.18 / $2.10per 1Mvia Alibaba CloudQwen32 sizes here
Qwen3 8BQwenQwen3 is a compact downloadable text model with 8.2 billion parameters and a permissive Apache licence.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.12 / $0.46per 1Mvia Alibaba CloudQwen3 14BQwenQwen3 is a 14.8-billion-parameter text model with a permissive Apache licence and a 131,072-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.12 / $0.24per 1Mvia OpenRouterUI-TARS 7BByteDanceUI-TARS is a vision-language model from ByteDance that reads both text and images to understand and interact with software interfaces.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.10 / $0.20per 1Mvia OpenRouterPhi 4MicrosoftMicrosoft's Phi-4 is a 14.7-billion-parameter text-only model from late 2024 with a permissive MIT licence.writing159th of 168 coding155th of 168 agentsnot measuredeveryday159th of 168 $0.070 / $0.14per 1Mvia OpenRouterUnslopNemo 12BTheDrummerUnslopNemo 12B is a 12.2-billion-parameter text model released in October 2024 by TheDrummer.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.40 / $0.40per 1Mvia OpenRouter
Qwen2.51 sizes here
Qwen2.5 7B InstructQwenQwen 2.5 is a compact downloadable text model with a permissive Apache licence and a 32,768-token request limit.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.10 / $0.20per 1Mvia PhalaMistral NemoMistral AIMistral Nemo is a 12.2-billion-parameter text model released in 2024 with a permissive Apache licence.writingnot measuredcodingnot measuredagentsnot measuredeverydaynot measured$0.019 / $0.030per 1Mvia OpenRouter