LLM API

Text models
through one API

Claude, GPT, Gemini, Grok, Kimi, GLM, DeepSeek and more through the OpenAI-compatible MegaBrain API. The same key and balance also run image and video generation.

115 models20 labs14 free

Get started free Try in chat

Frontier models

The flagships of Claude, GPT, Gemini, Grok and other families that are available right now. Prices per 1M tokens.

Claude Fable 5.2

Anthropic

sees images

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

input $9.2output $46context 1M

anthropic/claude-fable-5.2

Claude Opus 5.5

Anthropic

sees images

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, code...

input $4.6output $23context 1M

anthropic/claude-opus-5.5

GPT-6.1 Sol

OpenAI

sees images

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

input $1.15output $5.75context 1.1M

openai/gpt-6.1-sol

GPT-6 Astra

OpenAI

sees images

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...

input $5.75output $29context 1.1M

openai/gpt-6-astra

Grok 4.7

SpaceXAI

sees images

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

input $2.3output $6.9context 500K

x-ai/grok-4.7

Gemini 3.8 Flash

Google

sees images

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

input $0.86output $4.31context 1M

google/gemini-3.8-flash

Claude Sonnet 5.5

Anthropic

sees images

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

input $2.3output $12context 1M

anthropic/claude-sonnet-5.5

Kimi K3.1 Pro

Moonshot AI

sees images

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

input $2.3output $12context 1M

moonshotai/kimi-k3.1-pro

GPT-6.1 Terra

OpenAI

sees images

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...

input $0.57output $2.88context 1.1M

openai/gpt-6.1-terra

GLM 5.3

Z.ai

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

input $1.61output $5.06context 1M

z-ai/glm-5.3

DeepSeek V4 Pro 0423

DeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

input $1.63output $3.26context 1M

deepseek/deepseek-v4-pro

Qwen3.8 Max (0902)

Qwen

sees images

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

input $2.3output $6.9context 1M

qwen/qwen3.8-max-0902

Questions and answers

How do I connect?

Create a free account, make an API key in your dashboard and set the base URL to https://getmegabrain.com/api/gateway/v1 in any OpenAI client: the official SDKs, LangChain, Cursor, Continue. Pass the model id from its page in the model field, for example anthropic/claude-opus-5.5.

How does billing work?

You pay as you go from a prepaid USD balance. Each request is charged for the tokens it actually used: input and output separately, at the per-1M-token price shown on the model page. No subscription is needed.

Are there free models?

Yes. Models marked "free" cost nothing. They are offered by the labs themselves, so availability can change. The mb-auto/free route picks an available free model for you.

Is it the same key for images and video?

Yes. One key and one balance cover text models, image generation and video generation.

Every model, one key

Switch between models by changing one line of code. Pay as you go from a prepaid USD balance.

Get started free

Text modelsthrough one API

Frontier models

Questions and answers

Every model, one key

All text models

Text models
through one API