Token cost estimator
Quick AI cost calculator
Drag the sliders to set your usage volume and see estimated monthly costs update live across 18 models.
Usage volume ✓ drag to adjust
Model selection ✓ toggle to compare
Recommended model
Claude Haiku 5.5Low-cost
$4–$5/moLowest estimated monthly cost for this usage volume. $0.10 input / $0.50 output per million tokens.
Anthropic
Recommended
Anthropic
Claude Haiku 5.5*
$4estimated / month
Anthropic
Claude Sonnet 5.5
$89estimated / month
Anthropic
Claude Opus 5.5
$177estimated / month
Anthropic
Claude Fable 5.1
$443estimated / month
OpenAI
OpenAI
GPT-6 Luna
$4estimated / month
OpenAI
GPT-6.1 Sol
$89estimated / month
OpenAI
GPT-6 Astra
$443estimated / month
Google
Google
Gemini 3.5 Flash-Lite
$19estimated / month
Google
Gemini 3.8 Flash*
$33estimated / month
Google
Gemini 4 Argon*
$89estimated / month
xAI
xAI
Grok 4.7*
$68estimated / month
Open-weight
Open-weight
Llama 3.3 70B*
$24estimated / month
Open-weight
Mistral Large 3*
$17estimated / month
Open-weight
Muse Spark Open*
$45estimated / month
Other API
Other API
DeepSeek V4.1 Flash*
$12estimated / month
Other API
DeepSeek V4 Pro*
$45estimated / month
Other API
Qwen3.8 Flash*
$5estimated / month
Other API
Qwen3.8 Max*
$68estimated / month
Price notes. These prices can change or depend on how you use the model. Confirm current pricing with the provider before you build.
- Claude Haiku 5.5: Price rises to $0.50 in / $2.50 out per 1M tokens for prompts over 100,000 tokens.
- Gemini 3.8 Flash: Promotional price through Dec 31, 2026. From Jan 1, 2027 it is $1.50 in / $7.50 out per 1M tokens.
- Gemini 4 Argon: Promotional price through Nov 30, 2026. From Dec 1, 2026 it is $4.00 in / $20.00 out per 1M tokens.
- Grok 4.7: Prompts of 200k tokens or more are billed at $4.00 in / $12.00 out per 1M tokens, for the whole request.
- Llama 3.3 70B: Open-weight model: priced at Together AI's serverless rate. Other hosts charge differently, and self-hosting costs depend on your hardware.
- DeepSeek V4.1 Flash: Peak-hours rate shown. Off-peak is half price, and DeepSeek sets the peak windows.
- DeepSeek V4 Pro: Peak-hours rate shown. Off-peak is half price, and DeepSeek sets the peak windows.
- Qwen3.8 Flash: International (Singapore) pricing; other regions are priced differently.
- Qwen3.8 Max: International (Singapore) pricing; other regions are priced differently.
- Mistral Large 3: Open-weight model: what you pay depends on where you run it. This is a hosted-API estimate; other hosts charge differently, and self-hosting costs depend on your hardware.
- Muse Spark Open: Open-weight model: priced at Together AI's serverless rate. Other hosts charge differently, and self-hosting costs depend on your hardware.
Estimates only. Based on published API rates. Real costs vary with caching, context growth, retries, and provider rate changes. Confirm current prices with each provider, and validate against your own usage data, before you build or make budget decisions.
Built by XYZAgents.ai. Questions? info@xyzagents.ai