AI Calculator Pro

Claude Sonnet 4

Anthropic · model · context window 983,040 tokens.

Pricing (per 1M tokens)

Input$2.60
Output$13.00
Cache read$0.2600
Cache write$3.20

Specifications

Context window983,040 tokens
Max output64,000 tokens
Modalitiestext
VisionNo
Tool useYes
ReasoningNo
Prompt cachingNo

Intelligence & value

Measured
Overall1338 · #111

Worth it? GPT OSS 120B matches or beats Claude Sonnet 4 on the overall Arena and costs about $10.85/month versus $1,040.00/month at 100,000 calls — roughly $1,029.15/month cheaper.

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 27 August 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

Where else you can run Claude Sonnet 4

The same model is resold by 11 providers we track. The typical one charges 1.2× what the cheapest does — $6.00 against $5.20 per 1M tokens, blended 3:1. Routing the same workload to a different host is often a bigger saving than switching model.

ProviderInput / 1MOutput / 1MBlended
Poe$2.60$13.00$5.20
Cortecs$2.90$14.49$5.80
Fastrouter$3.00$15.00$6.00
Github Copilot$3.00$15.00$6.00
Helicone$3.00$15.00$6.00
Kilo$3.00$15.00$6.00
Opencode$3.00$15.00$6.00
OpenRouter$3.00$15.00$6.00
Orcarouter$3.00$15.00$6.00
Vercel AI Gateway$3.00$15.00$6.00

Showing the 10 cheapest of 11. The full list for every model is in the open endpoint dataset.

Third-party listings via models.dev, not rates we verify with each host the way we do first-party pricing. Treat them as a shortlist to check, not a quote — and confirm quantisation, context limits and rate limits before switching, since a cheaper host is not always serving the same thing.

Estimate cost with Claude Sonnet 4

Claude Sonnet 4 is pre-selected below. Enter your token counts and volume to see the cost per request, per day and per month — then switch models to compare.

Results update automatically as you type.

Result
$0.00910 per request
~$273.00/month at 1,000 requests/day
Input cost
$0.00260
Output cost
$0.00650
Per request
$0.00910
Per day
$9.10
Per month
$273.00

Source: community-hosted (cheapest of 11 providers, poe via models.dev). Prices are re-checked daily against the provider’s official pricing; this rate was last changed on 27 August 2026. A recent date here just means the price is still current, not that it moved.