AI Modellar

DeepSeek: DeepSeek V3 0324

deepseek/deepseek-chat-v3-0324

star Featured

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

Kirish

3 302/M so'm

$0.26

Chiqish

12 713/M so'm

$1.00

data_array 164K context

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

star Featured

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

Kirish

4 458/M so'm

$0.35

Chiqish

15 685/M so'm

$1.24

data_array 164K context

DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

star Featured

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Kirish

4 458/M so'm

$0.35

Chiqish

6 769/M so'm

$0.53

data_array 164K context

DeepSeek: DeepSeek V4 Flash

deepseek/deepseek-v4-flash

star Featured

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Kirish

1 486/M so'm

$0.12

Chiqish

2 972/M so'm

$0.23

data_array 1,049K context

Google: Gemma 2 27B

google/gemma-2-27b-it

star Featured

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

Kirish

10 732/M so'm

$0.85

Chiqish

10 732/M so'm

$0.85

data_array 8K context

Google: Gemma 3n 4B

google/gemma-3n-e4b-it

star Featured

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

Kirish

991/M so'm

$0.08

Chiqish

1 981/M so'm

$0.16

data_array 33K context

Meta: Llama 3 8B Instruct

meta-llama/llama-3-8b-instruct

star Featured

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

Kirish

2 311/M so'm

$0.18

Chiqish

2 311/M so'm

$0.18

data_array 8K context

Meta: Llama 3.1 70B Instruct

meta-llama/llama-3.1-70b-instruct

star Featured

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

Kirish

6 604/M so'm

$0.52

Chiqish

6 604/M so'm

$0.52

data_array 131K context

Meta: Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

star Featured

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...

Kirish

330/M so'm

$0.03

Chiqish

495/M so'm

$0.04

data_array 131K context

Meta: Llama 3.2 1B Instruct

meta-llama/llama-3.2-1b-instruct

star Featured

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

Kirish

446/M so'm

$0.04

Chiqish

3 319/M so'm

$0.26

data_array 131K context

OpenAI: GPT Audio

openai/gpt-audio

star Featured

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

Kirish

41 275/M so'm

$3.25

Chiqish

165 100/M so'm

$13.00

data_array 128K context

OpenAI: GPT Audio Mini

openai/gpt-audio-mini

star Featured

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

Kirish

9 906/M so'm

$0.78

Chiqish

39 624/M so'm

$3.12

data_array 128K context

OpenAI: GPT-3.5 Turbo 16k

openai/gpt-3.5-turbo-16k

star Featured

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

Kirish

49 530/M so'm

$3.90

Chiqish

66 040/M so'm

$5.20

data_array 16K context

OpenAI: GPT-3.5 Turbo Instruct

openai/gpt-3.5-turbo-instruct

star Featured

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Kirish

24 765/M so'm

$1.95

Chiqish

33 020/M so'm

$2.60

data_array 4K context

OpenAI: GPT-4 Turbo Preview

openai/gpt-4-turbo-preview

star Featured

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...

Kirish

165 100/M so'm

$13.00

Chiqish

495 300/M so'm

$39.00

data_array 128K context

OpenAI: GPT-4o Search Preview

openai/gpt-4o-search-preview

star Featured

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Kirish

41 275/M so'm

$3.25

Chiqish

165 100/M so'm

$13.00

data_array 128K context

OpenAI: GPT-4o-mini Search Preview

openai/gpt-4o-mini-search-preview

star Featured

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Kirish

2 477/M so'm

$0.20

Chiqish

9 906/M so'm

$0.78

data_array 128K context

OpenAI: gpt-oss-20b

openai/gpt-oss-20b

star Featured

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...

Kirish

479/M so'm

$0.04

Chiqish

2 311/M so'm

$0.18

data_array 131K context

OpenAI: gpt-oss-20b (free)

openai/gpt-oss-20b:free

free_breakfast Free star Featured

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...

Kirish

Free

Chiqish

Free

data_array 131K context

Claude 3.5 Sonnet

anthropic/claude-3.5-sonnet

star Featured

Anthropic flagship model

Kirish

49 530/M so'm

$3.90

Chiqish

247 650/M so'm

$19.50

data_array 200K context

Gemini Pro 1.5

google/gemini-pro-1.5

star Featured

Google multimodal AI

Kirish

20 638/M so'm

$1.63

Chiqish

82 550/M so'm

$6.50

data_array 2,000K context

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

star Featured

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Kirish

1 651/M so'm

$0.13

Chiqish

5 283/M so'm

$0.42

data_array 131K context

Meta: Llama 3.3 70B Instruct (free)

meta-llama/llama-3.3-70b-instruct:free

free_breakfast Free star Featured

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Kirish

Free

Chiqish

Free

data_array 131K context

DeepSeek: DeepSeek V3

deepseek/deepseek-chat

star Featured

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Kirish

3 305/M so'm

$0.26

Chiqish

13 210/M so'm

$1.04

data_array 131K context