Upstage vs Voyage AI: Token Pricing, Speed & Intelligence
Full comparison of Upstage and Voyage AI — live token pricing, latency, throughput, context window, strengths, weaknesses, and best use cases. Rates sourced from public APIs — verify before use.
Upstage
Solar Pro 4, Solar Pro 3, Solar Pro 2 — Korean frontier models with strong multilingual performance
Upstage is a Korean AI company offering the Solar model family via API. Solar Pro 4 is the current flagship, with Solar Pro 3 and Solar Pro 2 available at lower price points. The Solar models are known for strong multilingual performance, particularly in Korean and English, and competitive pricing relative to their capability tier. Pricing is published at upstage.ai/pricing.
Voyage AI
Voyage 3.5 — strong MTEB retrieval quality for RAG and semantic search
Voyage AI specialises in embedding and reranking models for retrieval-augmented generation (RAG) and semantic search. Voyage 3.5 and its variants rank highly on the MTEB leaderboard for retrieval quality. The 2026 lineup adds Voyage 3.5 Lite (cost-efficient), Voyage Code 3 (code-optimised embeddings), and Voyage Multimodal 3 (image + text embeddings). Voyage AI is the default embedding provider for Anthropic's Claude documentation and many production RAG systems. Check voyageai.com for current rates.
Key metric comparison
—
—
—
—
—
—
—
—
—
—
—
—
Live token pricing
Strengths and weaknesses
Upstage
Voyage AI
Key differentiators
Korean-built Solar models with strong multilingual performance and competitive frontier-tier pricing — Solar Pro 4 at $0.30/$1.20 per 1M tokens.
Voyage 3.5 Lite delivers strong MTEB retrieval quality at cost-efficient pricing — with specialised variants for code and multimodal content.
Frequently asked questions
Upstage FAQs
What is Upstage Solar?
Upstage Solar is a family of LLMs from Korean AI company Upstage. Solar Pro 4 is the current flagship, with Solar Pro 3 and Solar Pro 2 at lower price points. See upstage.ai/pricing for current rates.
How much does Upstage Solar cost?
As of October 2026: Solar Pro 4 $0.30/$1.20 per 1M tokens, Solar Pro 3 $0.15/$0.60, Solar Pro 2 $0.15/$0.60. See upstage.ai/pricing for current rates.
Is Upstage good for Korean language tasks?
Yes. The Solar model family is developed by a Korean AI company and shows strong performance on Korean-language benchmarks, making it a top choice for Korean NLP workloads.
Voyage AI FAQs
What is Voyage AI used for?
Voyage AI provides embedding and reranking models for RAG pipelines, semantic search, and document retrieval. It does not offer chat or text generation models — it is purpose-built for the retrieval layer of AI applications.
How does Voyage AI compare to OpenAI embeddings?
Voyage 3.5 consistently scores well on MTEB benchmarks relative to OpenAI text-embedding-3-large, often at lower per-token cost. Check voyageai.com and openai.com/api/pricing for current rates to compare.
What is Voyage Code 3?
Voyage Code 3 is a code-optimised embedding model designed for code search and retrieval. It outperforms general-purpose embeddings on code-related retrieval tasks, making it the preferred choice for code search applications.
Provider resources
Upstage — Solar Pro 4, Solar Pro 3, Solar Pro 2 — Korean frontier models with strong multilingual performance
Upstage is a Korean AI company offering the Solar model family via API. Solar Pro 4 is the current flagship, with Solar Pro 3 and Solar Pro 2 available at lower price points. The Solar models are known for strong multilingual performance, particularly in Korean and English, and competitive pricing relative to their capability tier. Pricing is published at upstage.ai/pricing.
Korean-built Solar models with strong multilingual performance and competitive frontier-tier pricing — Solar Pro 4 at $0.30/$1.20 per 1M tokens.
Voyage AI — Voyage 3.5 — strong MTEB retrieval quality for RAG and semantic search
Voyage AI specialises in embedding and reranking models for retrieval-augmented generation (RAG) and semantic search. Voyage 3.5 and its variants rank highly on the MTEB leaderboard for retrieval quality. The 2026 lineup adds Voyage 3.5 Lite (cost-efficient), Voyage Code 3 (code-optimised embeddings), and Voyage Multimodal 3 (image + text embeddings). Voyage AI is the default embedding provider for Anthropic's Claude documentation and many production RAG systems. Check voyageai.com for current rates.
Voyage 3.5 Lite delivers strong MTEB retrieval quality at cost-efficient pricing — with specialised variants for code and multimodal content.
Key strengths compared
Upstage
- Solar Pro 4: competitive frontier-tier pricing at $0.30/$1.20 per 1M tokens
- Strong multilingual performance — Korean and English
- Three-tier model family: Solar Pro 4, 3, and 2 for different cost/quality trade-offs
- Smaller global ecosystem than OpenAI or Anthropic
- Limited model variety beyond the Solar family
Voyage AI
- Voyage 3.5 ranks highly on MTEB retrieval benchmarks
- Voyage 3.5 Lite: cost-efficient embedding option
- Voyage Code 3 for code-optimised embeddings
- Embeddings and reranking only — no chat or generation models
- Smaller ecosystem than OpenAI
Key weaknesses compared
Upstage
- Smaller global ecosystem than OpenAI or Anthropic
- Limited model variety beyond the Solar family
- Less documentation in English than major US providers
Voyage AI
- Embeddings and reranking only — no chat or generation models
- Smaller ecosystem than OpenAI
- No open-weight models
Provider category context
Upstage is a frontier lab, founded in 2020. Voyage AI is a inference api, founded in 2023. Upstage as a frontier lab trains and serves its own proprietary models. Voyage AI as an inference API provider hosts open-weight models — typically offering lower prices for equivalent capability tiers but without access to proprietary frontier models.
How to choose between them
Choose Upstage if you need solar pro 4: competitive frontier-tier pricing at $0.30/$1.20 per 1m tokens. Choose Voyage AI if you need voyage 3.5 ranks highly on mteb retrieval benchmarks. For high-volume production workloads, run a cost comparison using the token pricing table above with your actual prompt/completion token ratio — the cheapest provider depends heavily on your input-to-output token ratio.