Seed 2.0 Pro API

Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.

Model IDbytedance/seed-2-0-pro-260328
Input pricing
$0.500 / 1M tokens
Output pricing
$2.000 / 1M tokens
Context
256,000 tokens
Regions
US / LK
United States and apac-lk-colombo
Data handling
Retention not verified
Prompts and outputs are not used for training
API
OpenAI-compatible
Last verified:

Verification checks the published Geodd catalogs, not a live inference request. Prices and availability come from the backend.

Endpoint support

Seed 2.0 Pro capabilities on Geodd

These values describe Geodd's published endpoint capabilities, not capabilities inherited from the base model. An unreported feature is marked Not verified, not assumed unsupported. Independent test results are not supplied by the catalog.

Streaming
Not verified
Tool calling
Yes
Structured outputs
Not verified
Reasoning
Yes
OpenAI-compatible chat completions
Yes
JSON responses
Yes
Batch API
Not verified
Fine-tuning
Not verified
Dedicated deployment
Not verified

Catalog precision: bf16. Maximum output: 128,000 tokens.

From model ID to request

Use Seed 2.0 Pro with the OpenAI SDK

Install the SDK with npm install openai or pip install openai. Set GEODD_API_KEY in your server environment or secret manager. Never put it in browser code or a public environment variable.

TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.GEODD_API_KEY,
  baseURL: "https://api.geodd.io/inference/v1",
});

const response = await client.chat.completions.create({
  model: "bytedance/seed-2-0-pro-260328",
  messages: [
    { role: "user", content: "Explain speculative decoding." }
  ],
});

console.log(response.choices[0].message.content);
Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["GEODD_API_KEY"],
    base_url="https://api.geodd.io/inference/v1",
)

response = client.chat.completions.create(
    model="bytedance/seed-2-0-pro-260328",
    messages=[
        {"role": "user", "content": "Explain speculative decoding."}
    ],
)

print(response.choices[0].message.content)
cURL
curl --fail-with-body "https://api.geodd.io/inference/v1/chat/completions" \
  --header "Authorization: Bearer $GEODD_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "bytedance/seed-2-0-pro-260328",
    "messages": [
      { "role": "user", "content": "Explain speculative decoding." }
    ]
  }'

All examples use bytedance/seed-2-0-pro-260328. To select another available region, replace baseURL, base_url, or the cURL URL with its base URL below. A real request consumes billable usage.

OpenAI-compatible API quick start

Usage-based billing / USD

Seed 2.0 Pro pricing

Seed 2.0 Pro serverless token pricing in USD
UsagePrice
Input tokens$0.500 / 1M tokens
Output tokens$2.000 / 1M tokens
Cached input reads$0.100 / 1M tokens
Cache writes$0.000 / 1M tokens
Serverless billing unit
Per token; prices shown per 1 million tokens
Per-request fee
No per-request fee listed ($0)
Reasoning-token billing
Not specified by the model catalog
Additional platform fees
Not specified by the model catalog
Minimum spend
Not specified by the model catalog

Cache rates are catalog fields; a zero rate does not establish that caching is available. Cache support and reasoning-token accounting have not been verified. Confirm unlisted billing conditions before production use.

View all inference pricing

Model-specific availability

Available regions

United States

Available

United States

Base URL
https://api.geodd.io/inference/v1

apac-lk-colombo

Available

apac-lk-colombo

Base URL

Not published

Use the selected serving region for inference processing. Residency commitments and administrative or support access remain subject to Geodd's data handling policy and your agreement.

Payloads and operational metadata

Data handling

  • A model-specific zero-retention flag is not available in the current catalog. Confirm applicability before sending sensitive data.
  • Geodd does not use customer prompts or model outputs to train models.
  • Limited operational metadata, such as usage, billing, and security events, may be retained. Zero payload retention does not mean zero metadata.
  • Requests use the selected serving region where applicable. API credentials should only be used server-side.

Integrate in your existing stack

Add Seed 2.0 Pro with your coding agent

Using Claude Code, Codex, Cursor, Windsurf, or another terminal-based coding agent? Give it the prompt below to configure Geodd in your application.

Geodd CLIComing soon

No install or setup command is published here until the CLI is available. Today, use an authorized server-side credential from the Geodd console and the SDK examples above.

Planned authorization workflow

The intended CLI flow is to authenticate with Geodd, create or select a project, select an inference region, create a scoped credential, safely configure the environment, detect the project's language and framework, install the appropriate SDK, and test an actual request.

The goal is human approval only for authentication, billing authorization, and spending limits, without manually copying credentials when an authorization flow is available. This is a planned workflow, not a currently available feature.

Coding-agent prompt
Add Seed 2.0 Pro to this application using Geodd.

Use model: bytedance/seed-2-0-pro-260328
Use Geodd's OpenAI-compatible API.

Requirements:
- Inspect the existing application first and use its existing integration patterns.
- Keep Geodd credentials server-side and use environment variables.
- Never expose the API credential to browser code, logs, or source control.
- Use GEODD_API_KEY; do not ask me to paste a credential into the conversation.
- Implement streaming where supported and appropriate.
- Preserve conversation history if the application includes chat.
- Add error handling for authentication, rate limits, and upstream failures.
- Install the required SDK using the project's package manager.
- Run a real test request when authorized credentials and billing are available.
- Ask for approval before incurring charges or changing a spending limit.
- If credentials are unavailable, explain the blocker; do not claim the test passed.
- Do not rewrite the application architecture when the existing stack supports this integration.

Geodd API base URL: https://api.geodd.io/inference/v1
Geodd documentation: https://geodd.io/docs/llm-api/getting-started
Model facts: https://geodd.io/models/bytedance/seed-2-0-pro-260328.json

Traceable facts

Model data and sources

This page and its JSON representation use the same backend snapshot. Unknown values remain null in JSON; they are not interpreted as supported or unsupported. The availability date uses the backend's model creation timestamp.

Model name
Seed 2.0 Pro
Model ID
bytedance/seed-2-0-pro-260328
Model developer
bytedance
API provider
Geodd
Last verified (catalog)
Page data updated
Model released
Not supplied by the Geodd catalog
Available on Geodd since

Direct answers

Frequently asked questions

Does Geodd offer Seed 2.0 Pro?

Yes. Use the Geodd model ID bytedance/seed-2-0-pro-260328. The model developer is bytedance; the API provider is Geodd.

Is Geodd's Seed 2.0 Pro API OpenAI compatible?

Yes. Use the supported OpenAI SDK chat completions interface with a Geodd API base URL and model ID bytedance/seed-2-0-pro-260328.

How much does Seed 2.0 Pro cost on Geodd?

Input: $0.500 / 1M tokens. Output: $2.000 / 1M tokens. Prices are in USD. See the pricing section for published fees and unverified billing details.

Where is Seed 2.0 Pro hosted?

Currently listed serving regions: United States and apac-lk-colombo. Use the regional base URLs above.

Does Geodd retain Seed 2.0 Pro prompts?

A model-specific zero-retention flag has not been verified. Geodd publishes its default payload and operational-metadata handling in the data handling policy linked above.

Can I use Seed 2.0 Pro for tool calling?

Yes, tool calling is listed in Geodd's model capability catalog. This page does not represent an independent live capability test.

Can my coding agent add Seed 2.0 Pro automatically?

The Geodd CLI workflow is coming soon. Today, copy the integration prompt above into Claude Code, Codex, Cursor, Windsurf, or another coding agent. An authorized server-side credential and billing approval are needed for a real test request.