Seed 2.0 Pro

Seed 2.0 Pro is the flagship model of ByteDance's Seed 2.0 series, taking text, image and video input.

Input / output price: $0.50 / $3.00 per 1M
Context: 256K tokens
Released: Feb 14, 2026

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "seed-2.0-pro".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="seed-2.0-pro",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "seed-2.0-pro",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "seed-2.0-pro",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
DeepInfra`deepinfra/ByteDance/Seed-2.0-pro`	256K	$0.50/M	$3.00/M	$0.10/M
EmpirioLabs`empiriolabs/seed-2-0-pro`	229K	$0.63/M	$3.79/M	—

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.56 per 1M
Average output: $3.40 per 1M
Average cache read: $0.10 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.63/MEmpirioLabsLowest$0.50/MDeepInfra

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

8.6tokens/sacross providers

Faster than 25% of the other 560 models on the gateway

Response latency

Lower is better

10sacross providers

Faster than 17% of the other 650 models on the gateway

Benchmarks

The Respan Index plus 15 published scores from 2 sources, each linked to where it was published.

40.2/ 100

Respan Index#63 of 170

170 ranked models. The shaded band is this model's 95% interval, 25.5 to 58.6. Qwen3.6-Max-Preview and Gemini 3 Pro Preview fall inside it, so the gap is within the margin of error.

63Dola Seed 2.0 Pro40.2
62Qwen3.6-Max-Preview40.4
64Gemini 3 Pro Preview39.7

Published scores

Benchmark	Score	Source	Published
SWE-bench Verifiedlf3-static.bytednsdoc.com	76.5%	lf3-static.bytednsdoc.com	Feb 16, 2026
SWE-bench Multilinguallf3-static.bytednsdoc.com	71.7%	lf3-static.bytednsdoc.com	Feb 16, 2026
Terminal-Bench 2.0lf3-static.bytednsdoc.com	55.8%	lf3-static.bytednsdoc.com	Feb 16, 2026
SciCodelf3-static.bytednsdoc.com	48.5%	lf3-static.bytednsdoc.com	Feb 16, 2026
SWE-bench Prolf3-static.bytednsdoc.com	46.9%	lf3-static.bytednsdoc.com	Feb 16, 2026

Benchmark	Score	Source	Published
BrowseComplf3-static.bytednsdoc.com	77.3%	lf3-static.bytednsdoc.com	Feb 16, 2026
BFCL v4lf3-static.bytednsdoc.com	73.4%	lf3-static.bytednsdoc.com	Feb 16, 2026
DeepResearchBenchlf3-static.bytednsdoc.com	53.3%	lf3-static.bytednsdoc.com	Feb 16, 2026

Benchmark	Score	Source	Published
GPQA Diamondlf3-static.bytednsdoc.com	92.4%	lf3-static.bytednsdoc.com	Feb 16, 2026
HLE-Verifiedlf3-static.bytednsdoc.com	73.6%	lf3-static.bytednsdoc.com	Feb 16, 2026
Humanity's Last Exam (no tools)lf3-static.bytednsdoc.com	33.3%	lf3-static.bytednsdoc.com	Feb 16, 2026

Benchmark	Score	Source	Published
AIME 2025 (no tools)lf3-static.bytednsdoc.com	99%	lf3-static.bytednsdoc.com	Feb 16, 2026

Benchmark	Score	Source	Published
MMLU-Prolf3-static.bytednsdoc.com	90.1%	lf3-static.bytednsdoc.com	Feb 16, 2026

Benchmark	Score	Source	Published
LMArena EloLMArena	1457 Elo · #52 of 181	LMArena	Nov 11, 2026
LMArena VisionLMArena	1256 Elo · #38 of 89	LMArena	Nov 9, 2026

How the Respan Index works

Apps

Use Seed 2.0 Pro in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Seed 2.0 Pro FAQ

Short answers, built from the data on this page.

Seed 2.0 Pro is a model from ByteDance, released on Feb 14, 2026. Seed 2.0 Pro is the flagship model of ByteDance's Seed 2.0 series, taking text, image and video input.

On the Respan gateway, Seed 2.0 Pro costs from $0.50 per 1M input tokens and $3.00 per 1M output tokens on DeepInfra, after gateway discounts. Averaged across its 2 providers, it costs $0.56 per 1M input tokens and $3.40 per 1M output tokens.

Seed 2.0 Pro is available through 2 providers: DeepInfra and EmpirioLabs.

Seed 2.0 Pro accepts up to 256K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "seed-2.0-pro". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Seed 2.0 Pro scores 40.2 out of 100 on the Respan Index v1.1, ranking #63 of 170 models. By category: Coding 12.1, Agents 50.4, Reasoning 50.0, Knowledge & language 39.8, and Human preference 53.8. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Seed 2.0 Pro has 15 published benchmark scores, including SWE-bench Verified 76.5%, BrowseComp 77.3%, and GPQA Diamond 92.4%. Each score links to where it was published; the data is collected by Respan.