Inference host prices: sambanova
Open-weight models served by inference hosts, with each host's price per 1M tokens (input, output). One row per model, host and quantization.
Sources for this list
- Last verified 2026-10-24T06:58:16+00:00 · https://api.sambanova.ai/v1/models (first-party,
sambanova-models)
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| deepseek/deepseek-chat-v3.1/sambanova/unknown | deepseek/deepseek-chat-v3.1 via SambaNova | USD 3.00 | USD 4.50 | – | 131,072 | 2026-10-24 06:58 UTC | source |
| deepseek/deepseek-v3.2/sambanova/unknown | deepseek/deepseek-v3.2 via SambaNova | USD 3.00 | USD 4.50 | – | 32,768 | 2026-10-24 06:58 UTC | source |
| google/gemma-4-31b-it/sambanova/unknown | google/gemma-4-31b-it via SambaNova | USD 0.38 | USD 1.15 | – | 131,072 | 2026-10-24 06:58 UTC | source |
| meta-llama/llama-3.3-70b-instruct/sambanova/unknown | meta-llama/llama-3.3-70b-instruct via SambaNova | USD 0.60 | USD 1.20 | – | 131,072 | 2026-10-24 06:58 UTC | source |
| minimax/minimax-m3.1-flash/sambanova/unknown | minimax/minimax-m3.1-flash via SambaNova | USD 0.30 | USD 1.20 | – | 1,048,576 | 2026-10-24 06:58 UTC | source |
| openai/gpt-oss-120b/sambanova/unknown | openai/gpt-oss-120b via SambaNova | USD 0.22 | USD 0.59 | – | 131,072 | 2026-10-24 06:58 UTC | source |