macrostack

AI API price index · open-model host · read 17 Nov 2026

SambaNova Cloud API pricing

5 prices as SambaNova Cloud publishes them — 5 text models — read on its own pricing page on 17 Nov 2026. Its current text models cost $0.59 to $8.80 per million output tokens.

Free tier No free credit: the Free plan reads "Add a payment method and purchase credits to run your first requests." The Plans page adds: "Participate in the SambaNova Developer Community for the opportunity to earn credits!"

What to know before you build on SambaNova Cloud

  • SambaNova Cloud prices five models.
  • GLM-5.3 is $2.80 in and $8.80 out per million tokens, twice Z.ai's own $1.40 and $4.40; MiniMax-M3.1-Flash is $0.30 and $1.20, twice MiniMax's $0.15 and $0.60.
  • gpt-oss-120b is $0.22 in and $0.59 out.
  • There is no free credit: the Free plan needs a payment method and bought credits. Developer Community members can earn credits.
  • Enterprise is a subscription with production rate limits; no public price.

Against the other 31

Across the index, 390 current text models run from $0.03 to $50.00 per million output tokens — 1667×. SambaNova Cloud’s cheapest, gpt-oss-120b at $0.59, has 107 cheaper text models elsewhere; its dearest, GLM-5.3, costs $8.80. A cheaper model is a different model, not the same one for less — compare capability before price.

The same model elsewhere

Open-weight models SambaNova Cloud sells that other hosts price too — the only like-for-like comparison in the index.

  • gpt-oss-120b — Novita AI $0.05 / $0.25 · Google Vertex AI (Agent Platform) $0.09 / $0.36 · SambaNova Cloud $0.22 / $0.59 · Amazon Bedrock $0.15 / $0.60 · Fireworks AI $0.15 / $0.60 · Groq $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · Together AI $0.15 / $0.60 · Cerebras $0.35 / $0.75 · Cloudflare Workers AI $0.35 / $0.75 — 3.0× apart
  • Llama 3.3 70B — Novita AI $0.135 / $0.40 · Azure AI Foundry Models $0.71 / $0.71 · Amazon Bedrock $0.72 / $0.72 · Google Vertex AI (Agent Platform) $0.72 / $0.72 · SambaNova Cloud $0.60 / $1.20 — 3.0× apart
  • GLM 5.3 — DeepInfra $0.90 / $4.00 · Cloudflare Workers AI $1.40 / $4.40 · Fireworks AI $1.40 / $4.40 · Mistral AI $1.40 / $4.40 · Nebius Token Factory $1.40 / $4.40 · Novita AI $1.40 / $4.40 · Perplexity $1.40 / $4.40 · Together AI $1.40 / $4.40 · Z.ai $1.40 / $4.40 · SambaNova Cloud $2.80 / $8.80 — 2.2× apart
  • MiniMax M3.1 Flash — MiniMax $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · SambaNova Cloud $0.30 / $1.20 — 2.0× apart

Input / output per 1M tokens, standard tier.

Text models

ModelInputCached inputOutputNote
GLM-5.3$2.80$0.14$8.80—
MiniMax-M3.1-Flash$0.30$0.03$1.20—
gemma-4-31B-it$0.38—$1.15—
gpt-oss-120b$0.22—$0.59—
Meta-Llama-3.3-70B-Instruct$0.60—$1.20—

5 of these 5 prices are ranked in the index; the rest say why in their note. Text and embeddings per 1M tokens unless the row says otherwise.

Discounts and surcharges, as published

  • Enterprise: "Subscription based pricing for larger usage", production rate limits and on-request models; contact sales, no public price.
  • Developer is "Pay as you go for token usage", with standard rate limits and all Production and Preview models.

Where these numbers come from

Read on cloud.sambanova.ai/plans/pricing on 17 Nov 2026, checked against 1 more of SambaNova Cloud’s own pages. Macrostack measures nothing and is paid by no provider on this index. Prices change; the date is the claim.

The other providers in the index

Questions

How much does the SambaNova Cloud API cost?
On 17 Nov 2026, SambaNova Cloud's current text models cost $0.59 to $8.80 per million output tokens at the standard tier (gpt-oss-120b to GLM-5.3). The full list, with input and cached-input prices, is on this page.
Does SambaNova Cloud have a free tier?
What SambaNova Cloud's own pages say: No free credit: the Free plan reads "Add a payment method and purchase credits to run your first requests." The Plans page adds: "Participate in the SambaNova Developer Community for the opportunity to earn credits!"
Does SambaNova Cloud offer discounts?
Enterprise: "Subscription based pricing for larger usage", production rate limits and on-request models; contact sales, no public price. Developer is "Pay as you go for token usage", with standard rate limits and all Production and Preview models.
The Macrostack brief

New swaps, worth your inbox.

A short, occasional email when we add a high-intent alternative or ship a new head-to-head. No spam, no selling your address — unsubscribe in one click.