Abacus

Access 55 Abacus models through Mastra's model router. Authentication is handled automatically using the ABACUS_API_KEY environment variable.

Learn more in the Abacus documentation.

ABACUS_API_KEY=your-api-key

import { Agent } from "@mastra/core";

const agent = new Agent({
  name: "my-agent",
  instructions: "You are a helpful assistant",
  model: "abacus/Qwen/QwQ-32B"
});

// Generate a response
const response = await agent.generate("Hello!");

// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
  console.log(chunk);
}

info

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Abacus documentation for details.

Models

55 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
abacus/claude-3-7-sonnet-20250219	200K						$3	$15
abacus/claude-haiku-4-5-20251001	200K						$1	$5
abacus/claude-opus-4-1-20250805	200K						$15	$75
abacus/claude-opus-4-20250514	200K						$15	$75
abacus/claude-opus-4-5-20251101	200K						$5	$25
abacus/claude-sonnet-4-20250514	200K						$3	$15
abacus/claude-sonnet-4-5-20250929	200K						$3	$15
abacus/deepseek-ai/DeepSeek-R1	128K						$3	$7
abacus/deepseek-ai/DeepSeek-V3.1-Terminus	128K						$0.27	$1
abacus/deepseek-ai/DeepSeek-V3.2	128K						$0.27	$0.40
abacus/deepseek/deepseek-v3.1	128K						$0.14	$0.28
abacus/gemini-2.0-flash-001	1.0M						$0.10	$0.40
abacus/gemini-2.0-pro-exp-02-05	2.0M						—	—
abacus/gemini-2.5-flash	1.0M						$0.30	$3
abacus/gemini-2.5-pro	1.0M						$1	$10
abacus/gemini-3-flash-preview	1.0M						$0.50	$3
abacus/gemini-3-pro-preview	1.0M						$2	$12
abacus/gpt-4.1	1.0M						$2	$8
abacus/gpt-4.1-mini	1.0M						$0.40	$2
abacus/gpt-4.1-nano	1.0M						$0.10	$0.40
abacus/gpt-4o-2024-11-20	128K						$3	$10
abacus/gpt-4o-mini	128K						$0.15	$0.60
abacus/gpt-5	400K						$1	$10
abacus/gpt-5-mini	400K						$0.25	$2
abacus/gpt-5-nano	400K						$0.05	$0.40
abacus/gpt-5.1	400K						$1	$10
abacus/gpt-5.1-chat-latest	400K						$1	$10
abacus/gpt-5.2	400K						$2	$14
abacus/gpt-5.2-chat-latest	400K						$2	$12
abacus/grok-4-0709	256K						$3	$15
abacus/grok-4-1-fast-non-reasoning	2.0M						$0.20	$0.50
abacus/grok-4-fast-non-reasoning	2.0M						$0.20	$0.50
abacus/grok-code-fast-1	256K						$0.20	$2
abacus/kimi-k2-turbo-preview	256K						$0.15	$8
abacus/llama-3.3-70b-versatile	128K						$0.59	$0.79
abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8	1.0M						$0.14	$0.59
abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo	128K						$4	$4
abacus/meta-llama/Meta-Llama-3.1-70B-Instruct	128K						$0.40	$0.40
abacus/meta-llama/Meta-Llama-3.1-8B-Instruct	128K						$0.02	$0.05
abacus/o3	200K						$2	$8
abacus/o3-mini	200K						$1	$4
abacus/o3-pro	200K						$20	$80
abacus/o4-mini	200K						$1	$4
abacus/openai/gpt-oss-120b	128K						$0.08	$0.44
abacus/qwen-2.5-coder-32b	128K						$0.79	$0.79
abacus/Qwen/Qwen2.5-72B-Instruct	128K						$0.11	$0.38
abacus/Qwen/Qwen3-235B-A22B-Instruct-2507	262K						$0.13	$0.60
abacus/Qwen/Qwen3-32B	128K						$0.09	$0.29
abacus/Qwen/qwen3-coder-480b-a35b-instruct	262K						$0.29	$1
abacus/Qwen/QwQ-32B	33K						$0.40	$0.40
abacus/qwen3-max	131K						$1	$6
abacus/route-llm	128K						$0.50	$2
abacus/zai-org/glm-4.5	128K						$0.60	$2
abacus/zai-org/glm-4.6	128K						$0.60	$2
abacus/zai-org/glm-4.7	128K						$0.70	$3

Advanced Configuration

Custom Headers

const agent = new Agent({
  name: "custom-agent",
  model: {
    url: "https://routellm.abacus.ai/v1",
    id: "abacus/Qwen/QwQ-32B",
    apiKey: process.env.ABACUS_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic Model Selection

const agent = new Agent({
  name: "dynamic-agent",
  model: ({ runtimeContext }) => {
    const useAdvanced = runtimeContext.task === "complex";
    return useAdvanced
      ? "abacus/zai-org/glm-4.7"
      : "abacus/Qwen/QwQ-32B";
  }
});