SambaCloud by SambaNova
OpenAI- and Anthropic-compatible API for LLM inference on SambaNova RDU hardware.
Price
Free plan
then from $0.22/M input
Free tier
Yes
Free Tier without payment method: 20 RPM, 20...
SDK downloads
—
npm sambanova · PyPI sambanova
Pricing
| Free tier | Free Tier without payment method: 20 RPM, 20 requests/day and 200,000 tokens/day per model |
|---|---|
| Cheapest paid plan | — |
| Usage price | $0.22/M input, $0.59/M output (gpt-oss-120b); $0.60/M input, $2.40/M output (MiniMax-M3); $0.60/$1.20 (Llama-3.3-70B) |
| Good to know | Developer Tier applies once a payment method is linked and is limited to 20M tokens per day across all models. |
From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.
Use it from an agent
| MCP server | None found |
|---|---|
| npm | npm install sambanova |
| PyPI | pip install sambanova |
Alternatives to SambaCloud
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| Fireworks Serverless inference API with per-token pricing for running open and proprietary models. |
— | per token for inference; per GPU second for on-demand deployments | — | — | |
| Replicate Run and deploy machine learning models with pay-per-use pricing for inference. |
— | Varies by model and hardware; examples: $0.04/output image,... | — | — | |
| AI21 API access to foundation models for text generation and chat tasks. |
$10 credits for 7 days | Free plan then $0.2 per 1M input tokens, $0.4 per 1M output tokens... |
— | — | |
| Baseten Deploy and run custom, fine-tuned, and open-source AI models with GPU compute. |
Free credits for new accounts | Free plan then Price per 1M tokens for Model APIs; price per minute for... |
— | — | |
| DeepInfra API for running various AI models including text generation, embeddings, image generation, and speech recognition. |
— | Per token pricing varies by model; e.g., $0.06 per 1M input tokens... | — | — | |
| Together AI API for inference on open-source and third-party language models, vision, audio, video, and embeddings. |
— | varies by model and task; e.g., $0.30 per 1M input tokens (MiniMax... | — | — |