> Snowflake Cortex
Snowflake Cortex AI runs LLMs, agents and search inside the Snowflake governance perimeter, exposed through SQL AI functions, Cortex Agents, Cortex Analyst and Cortex Search. It bills on a second credit type: AI Credits, priced at $2.00 per credit on demand globally and $2.20 regionally (Snowflake Service Consumption Table, effective 2026-09-09), on top of Platform Credits for warehouses. Published AI Credit rates per 1M tokens include llama3.1-8b at 0.11 in / 0.11 out, llama3.3-70b at 0.36 / 0.36, mistral-large2 at 1.00 / 3.00, and claude-sonnet-5 at 1.30 / 6.50 when invoked via Snowflake CoWork or Cortex Agents; Cortex Search is 6.3 AI Credits per GB per month of indexed data and Cortex Analyst is 67 Platform Credits per 1,000 messages.
// pros
- Token-level rates are published in an official PDF with an effective date, and the same table lists separate cache-write and cache-read rates for cached models such as openai-gpt-5.6-luna (0.125 / 0.01)
- Provisioned Throughput is available for reserved AI capacity at 0.08 Platform Credits per PTU-hour on AWS and 0.10 on Azure, useful for flattening spiky inference spend
- Edition ladder is explicit on the official pricing page: Business Critical adds Tri-Secret Secure, private connectivity and failover, and VPS runs in a fully isolated Snowflake environment
- Non-token AI units are also published, e.g. AI_PARSE_DOCUMENT at 3.66 AI Credits per 1,000 pages for layout and 0.68 for OCR, which makes document pipelines modelable
- AI Credit pricing steps down with annual contract value, from $2.00 on demand to $1.88 at the $40M+ tier, so large buyers can see the discount curve without a quote
// cons
- Two meters apply at once: Platform Credits for compute and AI Credits for AI features, and the consumption table states Cortex Inference may not be eligible for discounted Capacity AI Credit Pricing
- Provisioned Throughput is non-cancellable, non-transferable, non-refundable, non-renewable and does not renew automatically, so reserved PTUs are a hard commitment
- The published discount tiers only begin at $1.2M annual contract value, meaning mid-market accounts pay full on-demand AI Credit rates
- The marketing pricing page renders no dollar values in page text, so the official PDF consumption table is the only place to read rates
Best fit when the prompts must touch governed enterprise data without extraction, since inference and guardrails stay inside the existing role-based access model. Pair Cortex AI with Business Critical or VPS when residency and key control matter, and reserve Provisioned Throughput only for steady, forecastable agent traffic.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
No free tier
This provider does not offer a free tier as of our last verification (Sep 16, 2026). The cheapest way to try it is pay-as-you-go — input from Free per 1M tokens. If the provider adds a free tier, submit a correction and we’ll re-verify.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Pay-as-you-go | payg | — | Free | Free | Cheapest tracked model rate (OpenRouter-normalized). |
| AI Credit Consumption | payg | — | — | — | Billed in AI Credits per million tokens. Rates vary by model and are flat across regions. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Meta-Llama-3.1-70B-Instruct | Free | Free | 131k |
| Llama-3.1-8B-Instruct | Free | Free | 131k |
| Gemma 2 27B | $0.0000 | $0.0000 | 8k |
| Mistral Large | $0.0000 | $0.0000 | 128k |
$ Does Snowflake Cortex have a free tier?
No. Snowflake Cortex does not offer a meaningful free tier — entry requires payment (pay-as-you-go or a plan). We mark this explicitly rather than showing a misleading zero.
$ How much does Snowflake Cortex cost per 1M tokens?
The cheapest model we track at Snowflake Cortex is Free per 1M input tokens and Free per 1M output tokens. This is normalized from Snowflake Cortex's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is Snowflake Cortex safe to use?
Uprouter rates Snowflake Cortex as low risk. Risk level: moderate to elevated. The credit and per-token rates are published, but the model is consumption-based across two credit pools and reserved capacity is contractually non-cancellable and non-refundable. Data handling is comparatively strong, with inference inside Snowflake's perimeter, role-based access, automatic encryption, Tri-Secret Secure and private connectivity at Business Critical, plus a fully isolated VPS option for regulated workloads. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: unknownNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Risk level: moderate to elevated. The credit and per-token rates are published, but the model is consumption-based across two credit pools and reserved capacity is contractually non-cancellable and non-refundable. Data handling is comparatively strong, with inference inside Snowflake's perimeter, role-based access, automatic encryption, Tri-Secret Secure and private connectivity at Business Critical, plus a fully isolated VPS option for regulated workloads.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Snowflake Cortex's own API — get a key from their dashboard
curl https://www.snowflake.com/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama-3-1-70b-instruct",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.