Skip to main content

Seed 1.8

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

Input / output price
$0.25 / $2.00 per 1M
Context
256K tokens
Released
Dec 18, 2025
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-1.8".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
DeepInfradeepinfra/ByteDance/Seed-1.8
$0.25/M$2.00/M

Pricing

USD per 1M tokens on DeepInfra, after gateway discounts.

Input
$0.25 per 1M
Output
$2.00 per 1M
Cache read
$0.05 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.25/MDeepInfra

Benchmarks

The Respan Index plus 16 published scores from 2 sources, each linked to where it was published.

27.8/ 100

Respan Index#98 of 175

175 ranked models. The shaded band is this model's 95% interval, 17.7 to 48.4. Hy3 preview and GLM-5 fall inside it, so the gap is within the margin of error.
Seed 1.8 by category: Coding 9.8, Agents 33.9, Reasoning 29.9 (estimated), Knowledge & language 20.5, Human preference 48.9 (estimated)
  1. 98Seed1.827.8
  2. 97Hy3 preview28.3
  3. 98GLM-527.8

Published scores

BenchmarkScore
LiveCodeBench(v6)github.com79.5%
SWE-Bench Verifiedgithub.com72.9%
Terminal Bench 2.0github.com45.2%
Multi-SWE-Benchgithub.com42%

Compare Seed 1.8: Seed1.8 vs Dola Seed 2.0 Pro

Apps

Use Seed 1.8 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 1.8 FAQ

Short answers, built from the data on this page.

Seed 1.8 is a model from ByteDance, released on Dec 18, 2025. Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

On the Respan gateway, Seed 1.8 costs $0.25 per 1M input tokens and $2.00 per 1M output tokens on DeepInfra, after gateway discounts.

Seed 1.8 is served by DeepInfra.

Seed 1.8 accepts up to 256K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "seed-1.8". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Seed 1.8 scores 27.8 out of 100 on the Respan Index v1.1, ranking #98 of 175 models. By category: Coding 9.8, Agents 33.9, Reasoning 29.9 (estimated), Knowledge & language 20.5, and Human preference 48.9 (estimated). The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Seed 1.8 has 16 published benchmark scores, including LiveCodeBench(v6) 79.5%, τ2-Bench 72%, and GPQA-Diamond 83.8%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.