Model Directory

Explore AI models from leading providers.
More models coming soon.

⌕

OpenAI

7 models

Get API Key ↗

Claude

9 models

Get API Key ↗

GLM

3 models

Get API Key ↗

Kimi

1 model

Get API Key ↗

DeepSeek

3 models

Get API Key ↗

Qwen

3 models

Get API Key ↗

Gemini

6 models

Get API Key ↗

No models match your search.

glm-5.3

Zhipu AI

VisionLong contextTool useChat

GLM 5.3 supports a one-million-token context window, visual inputs, tool calling, and prompt caching.

Pricing Save 90%

Input / output: $0.238 / $0.832 / 1M ~~$2.38 / $8.32~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image

Get API Key ↗

glm-5.3-flash

Zhipu AI

VisionLong contextTool useChat

GLM 5.3 Flash combines a one-million-token context window with lower input and output prices. It supports visual inputs, tool calling, and prompt caching.

Pricing Save 90%

Input / output: $0.014 / $0.049 / 1M ~~$0.14 / $0.49~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image

Get API Key ↗

glm-5.2

Zhipu AI

VisionLong contextTool useChat

GLM 5.2 is a multimodal model from Zhipu AI with a 200K-token context window. It supports visual inputs, tool calling, and prompt caching.

Pricing Save 90%

Input / output: $0.238 / $0.832 / 1M ~~$2.38 / $8.32~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 200K tokens
Max output: 131K tokens
Input: Text, image

Get API Key ↗

kimi-k3

Moonshot AI

VisionLong contextTool useChat

Kimi K3 is Moonshot AI's flagship model with a one-million-token context window. It supports reasoning, visual inputs, tool calling, and prompt caching.

Pricing Save 90%

Input / output: $2.10 / $10.50 / 1M ~~$21.00 / $105.00~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 131K tokens
Input: Text, image

Get API Key ↗

deepseek-v4-pro

DeepSeek

Long contextChat

DeepSeek V4 Pro is the flagship model in the V4 series. It provides a one-million-token context window and supports up to 384K output tokens.

Pricing Save 90%

Input / output: $0.132 / $0.396 / 1M ~~$1.32 / $3.96~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 384K tokens

Get API Key ↗

deepseek-v4.1-flash

DeepSeek

Long contextChat

DeepSeek V4.1 Flash provides a one-million-token context window and up to 384K output tokens, with lower input and output prices than DeepSeek V4 Pro.

Pricing Save 90%

Input / output: $0.057 / $0.17 / 1M ~~$0.57 / $1.70~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 384K tokens

Get API Key ↗

deepseek-v4-flash

DeepSeek

Long contextChat

DeepSeek V4 Flash is a V4-series model with a one-million-token context window and support for up to 384K output tokens.

Pricing Save 90%

Input / output: $0.113 / $0.34 / 1M ~~$1.13 / $3.40~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 384K tokens

Get API Key ↗

qwen3.8-flash

Alibaba

VisionLong contextTool useChat

Qwen 3.8 Flash supports visual inputs, tool calling, and prompt caching. It offers a one-million-token context window and up to 128K output tokens.

Pricing Save 90%

Input / output: $0.035 / $0.105 / 1M ~~$0.35 / $1.05~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image

Get API Key ↗

qwen3.7-plus

Alibaba

VisionLong contextTool useChat

Qwen 3.7 Plus supports visual inputs and tool calling, with a one-million-token context window and up to 131K output tokens.

Pricing Save 90%

Input / output: $0.04 / $0.16 / 1M ~~$0.40 / $1.60~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 131K tokens
Input: Text, image

Get API Key ↗

qwen3.8-max

Alibaba

VisionLong contextTool useChat

Qwen 3.8 Max supports visual inputs, tool calling, and prompt caching. It provides a one-million-token context window and up to 128K output tokens.

Pricing Save 90%

Input / output: $0.42 / $1.259 / 1M ~~$4.20 / $12.59~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image

Get API Key ↗

gpt-6.1-sol

OpenAI

VisionLong contextChat

GPT-6.1 Sol is an upgrade to GPT-6 Sol, positioned below the flagship GPT-6 Astra. It is suited to agentic coding, computer use, and document-heavy professional work, balancing intelligence and cost.

Pricing Save 90%

Input / output: $0.20 / $1.00 / 1M ~~$2.00 / $10.00~~
Cache read / write: $0.01 / $0.25 / 1M ~~$0.10 / $2.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-6-sol

OpenAI

VisionLong contextChat

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series. Positioned below GPT-6 Astra and above GPT-6 Luna, it is designed for demanding professional work with text, image, and file inputs.

Pricing Save 90%

Input / output: $0.20 / $1.00 / 1M ~~$2.00 / $10.00~~
Cache read / write: $0.02 / $0.25 / 1M ~~$0.20 / $2.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-6-luna

OpenAI

VisionLong contextFastChat

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited to high-volume, latency-sensitive workloads such as chat, classification, and lightweight agentic tasks.

Pricing Save 90%

Input / output: $0.01 / $0.05 / 1M ~~$0.10 / $0.50~~
Cache read / write: $0.001 / $0.0125 / 1M ~~$0.01 / $0.125~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-5.6-sol

OpenAI

VisionLong contextChat

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited to complex reasoning, coding, and agentic workflows, with particular strengths in command-line and multi-step coding tasks.

Pricing Save 90%

Input / output: $0.40 / $2.00 / 1M ~~$4.00 / $20.00~~
Cache read / write: $0.04 / $0.50 / 1M ~~$0.40 / $5.00~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-5.6-terra

OpenAI

VisionLong contextChat

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, between the Sol and Luna tiers. It is suited to everyday coding, reasoning, and agentic work, with support for text, image, and file inputs.

Pricing Save 90%

Input / output: $0.20 / $1.20 / 1M ~~$2.00 / $12.00~~
Cache read / write: $0.02 / $0.25 / 1M ~~$0.20 / $2.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-6-astra

OpenAI

VisionLong contextChat

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. Its uses include advanced analysis, software engineering, deep research, scientific work, and document creation, including long-horizon tasks.

Pricing Save 90%

Input / output: $1.00 / $5.00 / 1M ~~$10.00 / $50.00~~
Cache read / write: $0.10 / $1.25 / 1M ~~$1.00 / $12.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1.1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gpt-image-2

OpenAI

VisionImage generation

GPT Image 2 is an image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs. Text and images are accepted as input, and generated images are returned as output.

Pricing Save 90%

Text input / output: $0.50 / $0.00 / 1M ~~$5.00 / $0.00~~
Image input / output: $0.80 / $3.00 / 1M ~~$8.00 / $30.00~~
Cache read / write: $0.125 / $0.50 / 1M ~~$1.25 / $5.00~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: Not published
Max output: Not published
Input: Text, image

Get API Key ↗

claude-opus-5-5

Anthropic

VisionLong contextChat

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, and supports text, image, and file inputs.

Pricing Save 90%

Input / output: $0.40 / $2.00 / 1M ~~$4.00 / $20.00~~
Cache read / write: $0.02 / $0.50 / 1M ~~$0.20 / $5.00~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-opus-5

Anthropic

VisionLong contextChat

Claude Opus 5 is designed for demanding reasoning, coding, and long-horizon agentic work. Its strengths include end-to-end software tasks, code review, bug finding, and visual analysis, with a one-million-token context window.

Pricing Save 90%

Input / output: $0.50 / $2.50 / 1M ~~$5.00 / $25.00~~
Cache read / write: $0.05 / $0.625 / 1M ~~$0.50 / $6.25~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-fable-5

Anthropic

VisionLong contextChat

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, reasoning support, and a one-million-token context window.

Pricing Save 90%

Input / output: $1.00 / $5.00 / 1M ~~$10.00 / $50.00~~
Cache read / write: $0.10 / $1.25 / 1M ~~$1.00 / $12.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-sonnet-5

Anthropic

VisionLong contextChat

Claude Sonnet 5 is a Sonnet-class model for coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort, as well as text, image, and file inputs and a one-million-token context window.

Pricing Save 90%

Input / output: $0.20 / $1.00 / 1M ~~$2.00 / $10.00~~
Cache read / write: $0.02 / $0.25 / 1M ~~$0.20 / $2.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-haiku-4-5-20251001

Anthropic

VisionLong contextFastChat

Claude Haiku 4.5 is a fast, efficient model designed to deliver strong intelligence at lower cost and latency than larger Claude models. This dated snapshot supports text, image, and file inputs, with a 200K-token context window and up to 64K output tokens.

Pricing Save 90%

Input / output: $0.10 / $0.50 / 1M ~~$1.00 / $5.00~~
Cache read / write: $0.01 / $0.125 / 1M ~~$0.10 / $1.25~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 200K tokens
Max output: 64K tokens
Input: Text, image, file

Get API Key ↗

claude-sonnet-4-6

Anthropic

VisionLong contextChat

Claude Sonnet 4.6 is a model for coding, agents, and professional work. It is suited to iterative development, complex codebase navigation, and end-to-end project management, with text, image, and file inputs and a one-million-token context window.

Pricing Save 90%

Input / output: $0.30 / $1.50 / 1M ~~$3.00 / $15.00~~
Cache read / write: $0.03 / $0.375 / 1M ~~$0.30 / $3.75~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-opus-4-6

Anthropic

VisionLong contextChat

Claude Opus 4.6 is a legacy Claude model with adaptive thinking. It accepts text and image inputs and produces text output. It supports a one-million-token context window and up to 128K output tokens at standard API settings.

Pricing Save 90%

Input / output: $0.50 / $2.50 / 1M ~~$5.00 / $25.00~~
Cache read / write: $0.05 / $0.625 / 1M ~~$0.50 / $6.25~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image

Get API Key ↗

claude-fable-5-1

Anthropic

VisionLong contextChat

Claude Fable 5.1 improves on Claude Fable 5, with its biggest gains in agentic coding, long-running agentic workflows, and knowledge work. Its applications include long code refactors and front-end and visual work, with text, image, and file inputs.

Pricing Save 90%

Input / output: $1.00 / $5.00 / 1M ~~$10.00 / $50.00~~
Cache read / write: $0.025 / $1.25 / 1M ~~$0.25 / $12.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

claude-opus-4-8

Anthropic

VisionLong contextChat

Claude Opus 4.8 is a reasoning-capable model in Anthropic's Opus family. It supports text, image, and file inputs with text output, a one-million-token context window, and up to 128K output tokens for complex tasks.

Pricing Save 90%

Input / output: $0.50 / $2.50 / 1M ~~$5.00 / $25.00~~
Cache read / write: $0.05 / $0.625 / 1M ~~$0.50 / $6.25~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 128K tokens
Input: Text, image, file

Get API Key ↗

gemini-3.5-flash

Google

VisionLong contextFastChat

Gemini 3.5 Flash is Google's high-efficiency multimodal model, combining coding and reasoning capabilities with Flash-tier speed. It is optimized for coding and parallel agentic execution and accepts text, image, video, file, and audio inputs.

Pricing Save 90%

Input / output: $0.15 / $0.90 / 1M ~~$1.50 / $9.00~~
Cache read / write: $0.015 / $0.15 / 1M ~~$0.15 / $1.50~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 66K tokens
Input: Text, image, video, file, audio

Get API Key ↗

gemini-2.0-flash-exp-image-generation

Google

VisionImage generation

Gemini 2.0 Flash Experimental Image Generation is a legacy experimental image model. Google announced its shutdown for November 14, 2025. No current official list price is published for this exact model; a zero-dollar rate is not shown as an active price.

Pricing USD per 1M tokens

Current official pricing is not listed for this model.

Specs

Context window: Not published
Max output: Not published
Input: Text, image

Google retired this model on November 14, 2025. Current official pricing is not listed. Availability through TokenAgentHub depends on the upstream provider.

Get API Key ↗

gemini-2.5-computer-use-preview-10-2025

Google

VisionLong contextComputer use

Gemini 2.5 Computer Use was designed for direct interaction with digital interfaces, including browser automation, multi-step software tasks, and UI testing with visual reasoning and precise cursor control. Google shut down this preview on July 28, 2026.

Pricing USD per 1M tokens

Current official pricing is not listed for this model.

Specs

Context window: 128K tokens
Max output: 64K tokens
Input: Text, image

Google retired this preview on July 28, 2026. Current official pricing is not listed. Availability through TokenAgentHub depends on the upstream provider.

Get API Key ↗

gemini-2.5-flash

Google

VisionLong contextFastChat

Gemini 2.5 Flash is a workhorse model for reasoning, coding, mathematics, and scientific tasks. It includes built-in thinking capabilities and a one-million-token context window, with support for text, file, image, audio, and video inputs.

Pricing Save 90%

Input / output: $0.03 / $0.25 / 1M ~~$0.30 / $2.50~~
Cache read / write: $0.003 / $0.03 / 1M ~~$0.03 / $0.30~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 66K tokens
Input: Text, image, file, audio, video

Get API Key ↗

gemini-2.5-flash-image

Google

VisionImage generationFast

Gemini 2.5 Flash Image, also known as Nano Banana, is an image generation model with contextual understanding. It accepts image and text inputs for image generation and editing, with an output limit of 8K tokens.

Pricing Save 90%

Input / output: $0.03 / $3.00 / 1M ~~$0.30 / $30.00~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 33K tokens
Max output: 8K tokens
Input: Image, text

Google's current documentation lists this model as retired on October 2, 2026. Prices shown are the reference catalog's original list rates; upstream availability may differ.

Get API Key ↗

gemini-2.5-flash-lite

Google

VisionLong contextFastChat

Gemini 2.5 Flash-Lite is a lightweight reasoning model optimized for low latency and cost efficiency. It is designed for high throughput and fast token generation, with multimodal inputs and a one-million-token context window.

Pricing Save 90%

Input / output: $0.01 / $0.04 / 1M ~~$0.10 / $0.40~~
Cache read / write: $0.001 / $0.01 / 1M ~~$0.01 / $0.10~~

Crossed-out prices reflect the providers' official API rates. Our prices are 90% lower.

Specs

Context window: 1M tokens
Max output: 66K tokens
Input: Text, image, file, audio, video

Get API Key ↗