Compact GPT model for low-latency assistance and high-volume workloads
14 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
13 providers
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.
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
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,...
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...
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Open multimodal Gemma instruction model for multilingual text generation and image understanding
10 providers
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...
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Efficient on-device Gemma 3n model for text, image, and audio understanding
1 provider
Open multimodal Gemma instruction model for efficient text generation and image understanding
9 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-3.5-turboopenai/gpt-3.5-turbo | OpenAI |
10.7 | 16.385K | $0.5 | $1.5 | 2023-03-01 | ||
| OpenAI: GPT-3.5 Turbo (batch)openai/gpt-3.5-turbo:batch | OpenAI |
10.7 | 16.385K | $0.25 | $0.75 | — | ||
| Gemma 3 27B ITgoogle/gemma-3-27b-it | Google |
10.1 | 131.072K | $0.08 | $0.16 | 2025-03-12 | ||
| Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | Mistral AI |
9.7 | 262.144K | $0.15 | $0.15 | — | ||
| Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batch | Mistral AI |
9.7 | 262.144K | $0.075 | $0.075 | — | ||
| IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM |
9.5 | 131.072K | $0.05 | $0.1 | — | ||
| Qwen: Qwen3 8Bqwen/qwen3-8b | Alibaba Qwen |
9.0 | 131.072K | $0.117 | $0.455 | — | ||
| Meta: Llama 4 Scoutmeta-llama/llama-4-scout | Meta |
8.2 | 327.68K | $0.1 | $0.3 | — | ||
| LiquidAI: LFM2.5-2.6Bliquid/lfm-2.5-2.6b | 7.7 | 128K | $0.35 | $0.5 | — | |||
| LiquidAI: LFM2.5-2.6B (free)liquid/lfm-2.5-2.6b:free | 7.7 | 65.536K | Free | Free | — | |||
| Gemma 3 12B ITgoogle/gemma-3-12b-it | Google |
5.8 | 131.072K | $0.04 | $0.12 | 2025-03-12 | ||
| Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta |
5.4 | 131.072K | $0.05 | $0.08 | — | ||
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | Mistral AI |
4.8 | 131.072K | $0.1 | $0.1 | — | ||
| Gemma 3n E4B ITgoogle/gemma-3n-e4b-it | Google |
3.2 | 32.768K | — | — | 2025-06-26 | ||
| Gemma 3 4B ITgoogle/gemma-3-4b-it | Google |
2.7 | 131.072K | $0.04 | $0.08 | 2025-03-12 |