Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Meta: Llama 4 Maverickmeta-llama/llama-4-maverick | Meta |
9.3 | 128K | $0.2 | $0.696 | — | ||
| OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batch | OpenAI |
9.0 | 131.072K | $0.05 | $0.2 | — | ||
| Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta |
7.8 | 131.072K | $0.05 | $0.08 | — | ||
| Upstage: Solar Pro 3upstage/solar-pro-3 | Upstage |
7.8 | 131.072K | $0.15 | $0.6 | — | ||
| Qwen: Qwen3 32Bqwen/qwen3-32b | Alibaba Qwen |
7.2 | 40.96K | $0.08 | $0.28 | — | ||
| Meta: Llama 4 Scoutmeta-llama/llama-4-scout | Meta |
6.5 | 327.68K | $0.1 | $0.3 | — | ||
| Qwen: Qwen3 14Bqwen/qwen3-14b | Alibaba Qwen |
6.4 | 131.072K | $0.227 | $0.91 | — | ||
| Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 | Mistral AI |
6.0 | 262.144K | $0.2 | $0.2 | — | ||
| Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batch | Mistral AI |
5.5 | 262.144K | $0.075 | $0.075 | — | ||
| Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | Mistral AI |
5.5 | 262.144K | $0.15 | $0.15 | — | ||
| Qwen: Qwen3 8Bqwen/qwen3-8b | Alibaba Qwen |
5.2 | 131.072K | $0.117 | $0.455 | — | ||
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | Mistral AI |
4.8 | 131.072K | $0.1 | $0.1 | — |