200 models · 1,226 open weights · 200 API-only · refreshed nightly
API-only models
Closed models whose weights are not published: you can only call them through a hosted API. Prices are USD per million tokens from OpenRouter, refreshed daily; intelligence and coding scores come from Artificial Analysis.
Unknown task "token-classification" ignored — showing all tasks.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 101 | Saba | — | 33 K | proprietary · API terms | — | API $0.30/M |
| 102 | Nova Micro 1.0 | — | 128 K | proprietary · API terms | — | API $0.061/M |
| 103 | Mistral Large | — | 128 K | proprietary · API terms | — | API $3.00/M |
| 104 | GPT-3.5 Turbo | — | 16 K | proprietary · API terms | — | API $0.75/M |
| 105 | Qwen3.6 Flash | — | 1.0 M | proprietary · API terms | — | API $0.42/M |
| 106 | GPT Audio | — | 128 K | proprietary · API terms | — | API $4.38/M |
| 107 | GPT Audio Mini | — | 128 K | proprietary · API terms | — | API $1.05/M |
| 108 | Sonar Pro Search | — | 200 K | proprietary · API terms | — | API $6.00/M |
| 109 | GPT-5 Image Mini | — | 400 K | proprietary · API terms | — | API $2.38/M |
| 110 | GPT-5 Image | — | 400 K | proprietary · API terms | — | API $10.00/M |
| 111 | Nano Banana (Gemini 2.5 Flash Image) | — | 33 K | proprietary · API terms | — | API $0.85/M |
| 112 | Relace Apply 3 | — | 256 K | proprietary · API terms | — | API $0.95/M |
| 113 | Qwen3 Coder Flash | — | 1.0 M | proprietary · API terms | — | API $0.39/M |
| 114 | Codestral 2508 | — | 256 K | proprietary · API terms | — | API $0.45/M |
| 115 | Morph V3 Large | — | 262 K | proprietary · API terms | — | API $1.15/M |
| 116 | Morph V3 Fast | — | 262 K | proprietary · API terms | — | API $0.90/M |
| 117 | Gemini 2.5 Pro Preview 06-05 | — | 1.0 M | proprietary · API terms | — | API $3.44/M |
| 118 | Sonar Deep Research | — | 128 K | proprietary · API terms | — | API $3.50/M |
| 119 | Aion-RP 1.0 (8B) | — | 33 K | proprietary · API terms | — | API $1.00/M |
| 120 | GPT-4o | — | 128 K | proprietary · API terms | — | API $4.38/M |
| 121 | WizardLM-2 8x22B | — | 66 K | proprietary · API terms | — | API $0.62/M |
| 122 | GPT-3.5 Turbo (older v0613) | — | 4 K | proprietary · API terms | — | API $1.25/M |
| 123 | GPT-3.5 Turbo Instruct | — | 4 K | proprietary · API terms | — | API $1.63/M |
| 124 | GPT-3.5 Turbo 16k | — | 16 K | proprietary · API terms | — | API $3.25/M |
| 125 | Weaver (alpha) | — | 8 K | proprietary · API terms | — | API $0.49/M |
| 126 | Glimpse | — | 262 K | proprietary · API terms | — | API $1.20/M |
| 127 | Pareto 26.10 | — | 1.0 M | proprietary · API terms | — | API $1.40/M |
| 128 | Pareto 26.9 | — | 262 K | proprietary · API terms | — | API $3.75/M |
| 129 | Summarize | — | 1.0 M | proprietary · API terms | — | API $0.03/M |
| 130 | Extract | — | 1.0 M | proprietary · API terms | — | API $0.03/M |
| 131 | Muse Wonder | — | 1.0 M | proprietary · API terms | — | API $8.00/M |
| 132 | Nano Banana 2.1 | — | 66 K | proprietary · API terms | — | API $3.00/M |
| 133 | GPT-6.1 Sol Pro | — | 1.1 M | proprietary · API terms | — | API $4.00/M |
| 134 | Perceptron Mk1.5 | — | 37 K | proprietary · API terms | — | API $0.49/M |
| 135 | Ember-1 | — | 1.0 M | proprietary · API terms | — | API $6.00/M |
| 136 | GLM 5.3 Prime | — | 1.0 M | proprietary · API terms | — | API $4.30/M |
| 137 | Qwen3.8 Max Prime | — | 1.0 M | proprietary · API terms | — | API $6.00/M |
| 138 | Aion 3.5 Mini | — | 262 K | proprietary · API terms | — | API $0.88/M |
| 139 | Aion 3.5 | — | 262 K | proprietary · API terms | — | API $3.75/M |
| 140 | Command A+ | — | 192 K | proprietary · API terms | — | API $0.60/M |
| 141 | GPT-6 Luna Pro | — | 1.1 M | proprietary · API terms | — | API $0.20/M |
| 142 | GPT-6 Sol Pro | — | 1.1 M | proprietary · API terms | — | API $4.00/M |
| 143 | MiMo-V2.6-Pro-UltraSpeed | — | 1.0 M | proprietary · API terms | — | API $5.44/M |
| 144 | Qwen3.8 Omni Flash | — | 1.0 M | proprietary · API terms | — | API $0.23/M |
| 145 | GLM 5.3 FlashX | — | 1.0 M | proprietary · API terms | — | API $0.59/M |
| 146 | Schematron V2 Turbo | — | 128 K | proprietary · API terms | — | API $0.06/M |
| 147 | Schematron V2 Small | — | 128 K | proprietary · API terms | — | API $0.095/M |
| 148 | Fugu Ultra v2 | — | 1.0 M | proprietary · API terms | — | API $11.25/M |
| 149 | Fugu Max | — | 1.0 M | proprietary · API terms | — | API $3.00/M |
| 150 | GPT-6 Astra Pro | — | 1.1 M | proprietary · API terms | — | API $20.00/M |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.