Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Seed-1.8, Seed-2.0-code, Perplexity: Decider V1.2
3 modelsByteDanceSeed-1.8Remove ×ByteDanceSeed-2.0-codeRemove ×perplexityPerplexity: Decider V1.2Remove ×
What’s differentOptimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.Decider V1.2 is a new 27B checkpoint of Perplexity's decision model, succeeding Decider V1.1 27B with the same API contract. Instead of generating text, it reads content passed as state...
DateFeb 17, 2026ListedApr 29, 2026ListedOct 16, 2026Listed
Listed rate$0.25 in / $2.00 out/ 1M tokensDeepInfra · all routes ↗$0.50 in / $3.00 out/ 1M tokensDeepInfra · all routes ↗$0.02 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗
Provider endpoints1 endpoint →1 endpoint →1 endpoint →
Context window256K256K262.1K
Max output——235.9K
Parameters———
Image inputNot reportedNot reportedSupported

Add another model

Search all models →