SambaNova Cloud vs Voyage AI: Token Pricing, Speed & Intelligence
Full comparison of SambaNova Cloud and Voyage AI — live token pricing, latency, throughput, context window, strengths, weaknesses, and best use cases. Rates sourced from public APIs — verify before use.
SambaNova Cloud
High-throughput inference on SambaNova RDU chips — gpt-oss-120b, GLM-5.3, Llama
SambaNova Cloud runs inference on SambaNova's proprietary Reconfigurable Dataflow Unit (RDU) chips, delivering very high throughput (800+ tokens/sec on gpt-oss-120b). The catalog covers gpt-oss-120b, GLM-5.3, MiniMax-M3, DeepSeek-V3.2, Meta-Llama-3.3-70B, and Gemma 4 31B. Pricing is PAYG with prompt caching on select models.
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
SambaNova Cloud
Voyage AI
Key differentiators
Proprietary RDU chips deliver industry-leading throughput on open-weight models at competitive per-token rates.
Voyage 3.5 Lite delivers strong MTEB retrieval quality at cost-efficient pricing — with specialised variants for code and multimodal content.
Frequently asked questions
SambaNova Cloud FAQs
What makes SambaNova Cloud different?
SambaNova runs inference on its own Reconfigurable Dataflow Unit (RDU) chips rather than NVIDIA GPUs. This delivers very high throughput — over 800 tokens/sec on gpt-oss-120b — at competitive per-token rates.
What models does SambaNova Cloud offer?
As of October 2026: gpt-oss-120b ($0.22/$0.59), GLM-5.3 ($1.40/$4.40, cached $0.14), MiniMax-M3 ($0.60/$2.40, cached $0.06), DeepSeek-V3.2 ($3.00/$4.50), Meta-Llama-3.3-70B ($0.60/$1.20), and Gemma 4 31B ($0.38/$1.15). See cloud.sambanova.ai/plans/pricing for current rates.
Does SambaNova offer prompt caching?
Yes, on GLM-5.3 (cached input $0.14/1M vs $1.40/1M standard) and MiniMax-M3 (cached input $0.06/1M vs $0.60/1M standard).
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
SambaNova Cloud — High-throughput inference on SambaNova RDU chips — gpt-oss-120b, GLM-5.3, Llama
SambaNova Cloud runs inference on SambaNova's proprietary Reconfigurable Dataflow Unit (RDU) chips, delivering very high throughput (800+ tokens/sec on gpt-oss-120b). The catalog covers gpt-oss-120b, GLM-5.3, MiniMax-M3, DeepSeek-V3.2, Meta-Llama-3.3-70B, and Gemma 4 31B. Pricing is PAYG with prompt caching on select models.
Proprietary RDU chips deliver industry-leading throughput on open-weight models at competitive per-token rates.
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
SambaNova Cloud
- Proprietary RDU chips deliver very high throughput — 800+ tokens/sec on gpt-oss-120b
- Competitive pricing on gpt-oss-120b ($0.22/$0.59 per 1M)
- Prompt caching on GLM-5.3 (cached input at $0.14/1M)
- Smaller model catalog vs OpenRouter or Together AI
- No proprietary frontier models — inference-only platform
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
SambaNova Cloud
- Smaller model catalog vs OpenRouter or Together AI
- No proprietary frontier models — inference-only platform
- RDU architecture may behave differently from GPU inference for some workloads
Voyage AI
- Embeddings and reranking only — no chat or generation models
- Smaller ecosystem than OpenAI
- No open-weight models
Provider category context
SambaNova Cloud is a inference api, founded in 2017. Voyage AI is a inference api, founded in 2023. Both are inference api providers — the comparison is primarily about pricing, model selection, and feature differentiation within the same tier.
How to choose between them
Both SambaNova Cloud and Voyage AI host open-weight models. The key differentiators are latency, throughput, and which specific model versions each provider offers. Check the speed metrics above — inference API providers often differ significantly on tokens-per-second for the same model. Pricing is typically competitive between them; availability of specific model versions (e.g., Llama 3.1 405B, DeepSeek V3) may be the deciding factor.