What is your AI inference actually costing?
Most real products do not buy from one vendor. They run a frontier text model, an image model, something for video or voice, and a cheap model for the boring half of the traffic — across three or four bills that never get compared. Build the whole basket here and see it in one number.
Build your basket
Your monthly AI spend
4 models- −25%
- −40%
- −40%
- −40%
Enter what you spend today at each provider's direct price. Savings are computed per model from the rates published on this page — models we price the same as the provider show no saving, and are left in rather than quietly dropped to flatter the total.
Your estimate
Current spend
$8,420
per month
Estimated with INFRO
$5,352
per month
Potential savings
$3,068
36% blended across your basket
Over twelve months
$36,816
same basket, same rates
36% of current spend
An estimate, not a quote. It prices your basket at the reference and INFRO rates published on this page — your real mix of prompt lengths, cached tokens, and image sizes will move it.
What moves this bill more than the vendor does.
A calculator prices a basket. These are the things that make a real invoice differ from one — worth knowing before you treat any estimate, including ours, as a number.
- Media usually dominates before anyone notices
- Text spend is visible because it is measured in familiar units. Video measured in seconds and speech measured in characters tend to overtake it quietly — a single feature that renders clips can outgrow an entire chat product's token bill in a quarter.
- The cheap half of your traffic is worth finding
- In most products a large share of calls are classification, extraction, routing, or moderation running on a frontier model because that was the default. Those are the calls where a tier change costs nothing in quality and a lot in spend.
- An estimate is a floor, not a quote
- Cached input, prompt length distribution, image sizes, retries, and failed generations all move a real bill. This tool prices a basket at published rates so you can see the shape; a cost audit reads your actual usage and prices the real thing.
The models in this calculator
Direct price beside ours, per unit. Rows priced at parity are left in rather than dropped.
| Model | Task | Direct | INFRO | Save |
|---|---|---|---|---|
| Claude Fable 5anthropic/claude-fable-5 | Frontier reasoning & agents | $20 | $16 /1M tok | −20% |
| GPT-5.6 Solopenai/gpt-5.6-sol | Frontier reasoning | $11 | $7.88 /1M tok | −30% |
| Gemini 3.1 Progoogle/gemini-3.1-pro | Multimodal reasoning | $4.50 | $3.38 /1M tok | −25% |
| Claude Opus 5anthropic/claude-opus-5 | Coding & complex work | $10 | $8.00 /1M tok | −20% |
| Grok 4.6xai/grok-4.6 | Agents & knowledge work | $3.00 | $1.80 /1M tok | −40% |
| Claude Sonnet 5anthropic/claude-sonnet-5 | Production workhorse | $6.00 | $4.50 /1M tok | −25% |
| GPT-5.6 Terraopenai/gpt-5.6-terra | Everyday reasoning | $4.50 | $2.92 /1M tok | −35% |
| Gemini 3.7 Flashgoogle/gemini-3.7-flash | Fast agents & coding | $1.50 | $0.90 /1M tok | −40% |
| GPT-5.6 Lunaopenai/gpt-5.6-luna | High-volume execution | $0.45 | $0.247 /1M tok | −45% |
| Claude Haiku 4.5anthropic/claude-haiku-4.5 | Fast, low-cost chat | $2.00 | $1.40 /1M tok | −30% |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | Budget reasoning | $0.313 | $0.175 /1M tok | −44% |
| Kimi K2.6moonshot/kimi-k2.6 | Long-context agents | $1.40 | $0.84 /1M tok | −40% |
| GLM-5.2zai/glm-5.2 | Open-weight flagship | $1.30 | $0.78 /1M tok | −40% |
| MiniMax M2.5minimax/minimax-m2.5 | Agentic coding | $0.875 | $0.525 /1M tok | −40% |
| Qwen3-Coderqwen/qwen3-coder | Code generation | $1.80 | $1.35 /1M tok | −25% |
| GPT Image 2openai/gpt-image-2 | Image generation & editing | $0.06 | $0.036 /image | −40% |
| Nano Banana Progoogle/nano-banana-pro | 2K–4K image generation | $0.18 | $0.09 /image | −50% |
| Seedream 5.0 Probytedance/seedream-5-pro | Image generation & editing | $0.05 | $0.03 /image | −40% |
| Nano Banana 2google/nano-banana-2 | Fast image generation | $0.045 | $0.027 /image | −40% |
| FLUX.2 [pro]bfl/flux-2-pro | Image generation | $0.05 | $0.03 /image | −40% |
| Grok Imagine 2.0xai/grok-imagine-image-2 | Image generation & editing | $0.06 | $0.03 /image | −50% |
| Imagen 4 Ultragoogle/imagen-4-ultra | Image generation | $0.06 | $0.046 /image | −23% |
| Qwen-Image 3.0qwen/qwen-image-3 | Image generation & typography | $0.02 | $0.011 /image | −45% |
| Topaz Image Upscaletopaz/image-upscale | Upscale & restoration | $0.10 | $0.05 /image | −50% |
USD, illustrative launch rates reconciled on 2026-08-24. Showing 24 of 48 — the full catalog has the rest. Live rates come from GET /v1/models once your key is active.
An estimate is a floor. Want the real number?
Send a usage export and we will price your actual traffic — with the arithmetic shown, and the caveats named.