Pay for real tokens. No hidden fees.
Subscriptions unlock features (agents, KB, workflow). Token usage is billed at provider rates plus a transparent 30/50% markup.
$0
Enough for real testing. No card required.
- · 500 credits / month (~$5)
- · 2 API keys
- · 3 agents
- · 20 RPM
- · Fast-tier models: gpt-4o-mini, haiku, flash, mistral-small
$29
For small teams shipping their first AI product.
- · 3,500 credits / month (~$35 token usage)
- · 10 API keys
- · 20 agents
- · 100 RPM
- · All 14 models — including Opus 4.7, Sonnet 4.6, GPT-4o
$99
For production teams with heavier traffic.
- · 13,000 credits / month (~$130 token usage)
- · 100 API keys
- · Unlimited agents
- · 500 RPM
- · SSO + audit log + custom models
Custom
For organizations needing custom models and deployment controls.
- · Custom credits
- · Custom rate limits
- · Dedicated support
- · On-prem options
- · SLA review
Estimate your bill before you commit.
Drag the slider to estimate monthly credits for your usage. Swap models to compare side by side.
Estimated / month
$8.58
USD / month
Credits needed
858
credits / month
Recommended plan
Starter
Every rate is public. Compare with OpenAI/Anthropic direct, right here.
30% markup on top-tier models, 50% on the cheap tier (covers routing, observability, audit log, KB, and agents).
| Model | Input / 1M | Output / 1M | Context | Markup |
|---|---|---|---|---|
Claude Opus 4.7 claude-opus-4-7 | $6.50 | $32.50 | 1M | +30% |
DeepSeek V4 Pro deepseek-v4-pro | $0.570 | $1.13 | 1M | +30% |
Claude Sonnet 4.6 claude-sonnet-4-6 | $3.90 | $19.50 | 1M | +30% |
GPT-4o gpt-4o-2024-08-06 | $3.25 | $13.00 | 128K | +30% |
Mistral Large 2 mistral-large-2411 | $2.60 | $7.80 | 131.072K | +30% |
Gemini 2.5 Pro gemini-2.5-pro | $1.63 | $13.00 | 1M | +30% |
Kimi K2.6 kimi-k2.6 | $1.23 | $5.20 | 262.144K | +30% |
Llama 3.1 70B llama-3.1-70b-instruct | $0.940 | $0.940 | 128K | +30% |
GLM-4.6 glm-4.6 | $0.590 | $1.95 | 200K | +30% |
Qwen 2.5 72B qwen2.5-72b-instruct | $0.450 | $0.520 | 128K | +30% |
o3 mini o3-mini-2025-01-31 | $1.43 | $5.72 | 200K | +30% |
Claude Haiku 4.5 claude-haiku-4-5 | $1.50 | $7.50 | 200K | +50% |
Gemini 2.5 Flash gemini-2.5-flash | $0.450 | $3.75 | 1M | +50% |
GPT-4o mini gpt-4o-mini-2024-07-18 | $0.220 | $0.900 | 128K | +50% |
Mistral Small 3 mistral-small-latest | $0.220 | $0.900 | 128K | +50% |
DeepSeek V4 Flash deepseek-v4-flash | $0.210 | $0.420 | 1M | +50% |
Prices auto-sync from models.dev monthly. When providers cut prices, VeloxAI passes them on at the next sync.
Production guardrails are not add-ons.
API keys
Live/test keys, SHA-256 hashes, one-time reveal, rotation, and scopes.
Usage controls
Credits, RPM, resource limits, model allowlists, and alerting.
Observability
Request logs, latency, model breakdowns, webhooks, and OpenTelemetry-ready exports.
Workers
Queue-backed KB indexing, images, workflows, analytics, billing, alerts, and webhooks.