LLM evaluation and observability pricing calculator
Rates checked 2026-10-17 on each vendor's own pricing page. Only published rates are used; anything else is marked “not estimated”.
Short answer: Every tool here has a free tier or free self-hosted version. Published entry plans checked 2026-10-17 run from $19/month (Comet Opik Pro Cloud) to $249/month (Braintrust Pro), and per-seat plans grow with team size. What you actually pay depends on your volume of traces, spans, scores or GB, which each vendor meters differently.
Estimate your monthly cost
| Tool | Plan used | Estimate / month | How |
|---|---|---|---|
| Braintrust | Starter | $0 | $0 base; 1 GB and 10k scores included, then $4/GB and $2.50 per 1k scores Excludes model credits used at token rates. [rates] |
| W&B Weave | Free | $0 | 1 GB/month Weave ingestion [rates] |
| Comet Opik | Pro Cloud | $19 | $19 base; 100k spans included, then $5 per 100k spans [rates] |
| Langfuse | Core | $29 | $29 base; 70,000 units (traces + observations + scores), 100k included, then $8 per 100k (graduated) [rates] |
| Arize AX | AX Pro | $50 | $50 base; 50k spans and 10 GB included [rates] |
| Maxim AI | Professional | $87 | $29 x 3 seat(s); 100k logs included, then $1 per 10k logs We count one log per LLM request; check how Maxim counts your logs. [rates] |
| LangSmith | Plus | $117 | $39 x 3 seat(s); 10k base traces included [rates] |
| Confident AI | Starter | $200 | $200 per organization; 5 GB-months included, then $1 per GB-month [rates] |
| Helicone | Pro | not estimated | $79 base; 10k requests and 1 GB free, then usage-based Usage above 10k requests or 1 GB is billed at rates shown only in Helicone's calculator, which we could not verify. [rates] |
Assumptions
- Usage above an allowance is treated as billed pro rata, and taxes, discounts, annual terms and add-ons are left out.
- Each estimate uses the cheapest self-serve plan that fits your inputs, or the entry paid plan if you exceed the free tier.
- Vendors define units differently: Langfuse counts traces, observations and scores; Arize and Opik count spans; Maxim counts logs; Helicone counts requests; Braintrust, Confident AI and Weave count GB. Map your own numbers to each definition.
Not included
- Braintrust model credits: Billed at token rates that vary by model.
- Galileo (Splunk Agent Observability): Listed from $100/month per 1.2 million spans, billed annually; we do not model annual contracts.
- Promptfoo and Ragas: Open-source tools with no usage-metered cloud plan to estimate (Promptfoo Enterprise is custom).
- Enterprise plans: Custom pricing on every vendor.
- Self-hosting: Langfuse, Phoenix, Opik and Helicone are free to self-host; your infrastructure cost is not included.
Published plans and rates
| Tool | Free tier | Entry paid plan |
|---|---|---|
| Arize AX and Phoenix | AX Free: 25k spans/month, 1 GB ingestion, 15-day retention, unlimited users [source, checked 2026-10-17] | AX Pro $50/month: 50k spans, 10 GB, 30-day retention (overage rates not stated on the pricing page) [source, checked 2026-10-17] |
| Braintrust | Starter $0: 1 GB processed data, 10k scores, 14-day retention, unlimited users; then $4/GB and $2.50 per 1k scores [source, checked 2026-10-17] | Pro $249/month: 5 GB and 50k scores included, then $3/GB and $1.50 per 1k scores; 30-day retention [source, checked 2026-10-17] |
| Comet Opik | Free Cloud: 25k spans/month, up to 10 team members, 60-day retention; open source self-hosted is free [source, checked 2026-10-17] | Pro Cloud $19/month: 100k spans, up to 50 members, then $5 per 100k spans [source, checked 2026-10-17] |
| DeepEval and Confident AI | Free: 2 seats, 1 project, 5 test runs/week, 1 GB-month of trace spans [source, checked 2026-10-17] | Starter $200/month per organization: unlimited seats, 5 projects, 5 GB-months, then $1 per GB-month [source, checked 2026-10-17] |
| Galileo (Splunk Agent Observability) | not verified | From $100/month per 1.2 million spans, billed annually; includes 500 million Luna tokens and 5 Luna fine-tuning runs per year [source, checked 2026-10-17] |
| Helicone | Hobby: 10,000 requests/month, 1 GB storage, 1 seat, 7-day retention [source, checked 2026-10-17] | Pro $79/month plus usage-based pricing (usage rates are shown only via a calculator, not verified) [source, checked 2026-10-17] |
| Langfuse | Hobby: 50k units/month, 30 days data access, 2 users [source, checked 2026-10-17] | Core $29/month: 100k units included, then $8 per 100k units (graduated down to $6 per 100k above 50M) [source, checked 2026-10-17] |
| LangSmith | Developer $0: 1 seat, up to 5k base traces/month, then pay as you go [source, checked 2026-10-17] | Plus $39/seat/month: up to 10k base traces/month, then pay as you go (per-trace rate not stated on the pricing page) [source, checked 2026-10-17] |
| Maxim AI | Developer: free for up to 3 seats, 1 workspace, 10k logs/month, 3-day retention, no overages [source, checked 2026-10-17] | Professional $29/seat/month: 100k logs/month, 7-day retention, $1 per 10k extra logs [source, checked 2026-10-17] |
| Promptfoo | Community: free, all LLM evaluation features, red teaming up to 10k probes/month [source, checked 2026-10-17] | Enterprise: custom pricing (no public price) [source, checked 2026-10-17] |
| Ragas | Free, open source [source, checked 2026-10-17] | No paid plan published [source, checked 2026-10-17] |
| W&B Weave | Free $0: 1 GB/month Weave data ingestion [source, checked 2026-10-17] | Pro from $60/month: 1.5 GB/month ingestion, then $0.10 per MB; for teams under 50 employees [source, checked 2026-10-17] |
FAQ
What does the default example cost?
For 10,000 traces, 50,000 spans, 10,000 scores, 50,000 LLM requests, 1 GB and 3 seats a month: Braintrust Starter $0; W&B Weave Free $0; Comet Opik Pro Cloud $19; Langfuse Core $29; Arize AX AX Pro $50; Maxim AI Professional $87; LangSmith Plus $117; Confident AI Starter $200. Some tools are left out of this list because their rates above the allowance are not published.
Why are some estimates 'not estimated'?
When your usage goes past a plan's allowance and the vendor does not print the overage rate on its pricing page (LangSmith traces, Arize AX spans, Helicone usage), we show the known part and stop rather than guess.
Are these prices exact?
No. They are list-price estimates from rates on vendor pages checked 2026-10-17. Usage above an allowance is treated as billed pro rata, and taxes, discounts, annual terms and add-ons are left out. Confirm with each vendor's own calculator before you buy.