SambaNova models & pricing

SambaNova hosts 17 models (17 with public pricing) covering 1 modalities. Reconfigurable Dataflow Unit inference for Llama, DeepSeek, Qwen. Cheapest input starts at $0.0400/M tokens; the most premium goes up to $5.00/M. Use Future AGI's Agent Command Center to route any SambaNova model with cost-optimized fallback and unified observability.

Homepage ↗ Docs ↗

chat 17

Model Input / 1M Output / 1M Context Caps
Meta Llama 3.2 1B Instruct $0.0400/M $0.0800/M 16,384
Meta Llama 3.2 3B Instruct $0.0800/M $0.160/M 4,096
Meta Llama 3.1 8B Instruct $0.1000/M $0.200/M 16,384 tools
Meta Llama Guard 3.8B $0.300/M $0.300/M 16,384
Minimax M2.7 $0.300/M $1.20/M 204,800 tools · reasoning
Llama 4 Scout 17B 16e Instruct $0.400/M $0.700/M 8,192 tools
Qwen3.32b $0.400/M $0.800/M 8,192 tools · reasoning
Qwen2 Audio 7B Instruct $0.500/M $100/M 4,096 audio
Qwq 32B $0.500/M $1.00/M 16,384
Meta Llama 3.3 70B Instruct $0.600/M $1.20/M 131,072 tools
Llama 4 Maverick 17B 128e Instruct $0.630/M $1.80/M 131,072 tools · vision
DeepSeek R1 Distill Llama 70B $0.700/M $1.40/M 131,072
DeepSeek v3.0324 $3.00/M $4.50/M 32,768 tools · reasoning
DeepSeek v3.1 $3.00/M $4.50/M 32,768 tools · reasoning
GPT Oss 120B $3.00/M $4.50/M 131,072 tools · reasoning
DeepSeek R1 $5.00/M $7.00/M 32,768
Meta Llama 3.1 405B Instruct $5.00/M $10.00/M 16,384 tools

FAQ

How many SambaNova models are there?

17 SambaNova models are listed across 1 modality on this page. 17 have public per-token pricing.

How is SambaNova pricing verified?

Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.

Which SambaNova model is cheapest?

Input pricing on SambaNova starts at $0.0400 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.

Can I route to SambaNova via an OpenAI-compatible API?

Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a SambaNova target, and call SambaNova models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.

Route any SambaNova model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.