Preview build — figures marked “✓” or in green are sourced (benchmarks by Artificial Analysis); treat everything else (value scores, “Est.” figures, unmarked prices and changes) as illustrative. Methodology

Cost per task

What a finished task actually costs.

Per-token, per-second, per-character and per-image prices can't be compared directly — finished tasks can. Each category below defines one standard task with its conversion published. Quality is shown per model but never compared across categories — a video Elo and a language-model index measure different things.

$1 buys

757×

summarize a report · Gemini 2.5 Flash-Lite

$1 buys

1.9×

a 10-second clip · Seedance 1.5

$1 buys

277×

one minute of narration · Cloud TTS WaveNet

$1 buys

333×

one image · FLUX Schnell

Summarize a report

LLM

A 1,000-word summary of a ~6,000-word document in one request. Conversion: ≈8,000 input + 1,300 output tokens (1.33 tokens per English word).

ModelProviderCost / taskTasks / $1Intelligence index
OpenAI$0.0013757
Google$0.00137576.9
Qwen 3 235Bfrontier
Together$0.002442018.2
OpenAI$0.0053189
Google$0.0056176
Mistral$0.006016815.9
Anthropic$0.01568
OpenAI$0.01568
Google$0.0234325.8
OpenAI$0.0263719.4
o3frontier
OpenAI$0.0263730.4
Anthropic$0.0293453.4
Google$0.03231
OpenAI$0.0323142.2
Anthropic$0.0721334.7

A 10-second clip

Video

Ten seconds of generated video at each model's priced tier. Conversion: 10 × the per-second list price (tier caveats per row on the pricing page).

ModelProviderCost / taskTasks / $1Arena Elo
Seedance 1.5frontier
fal.ai$0.5201.91172 ±8
Kling 2.5frontier
fal.ai$0.7001.41200 ±7
Wan 2.7frontier
fal.ai$1.001.01216 ±9
fal.ai$1.001.01186 ±8
Google$1.001.01201 ±8
Replicate$1.680.61212 ±8
Replicate$2.240.41240 ±8
Seedance 2.0frontier
fal.ai$3.030.31266 ±8
Google$4.000.31201 ±8

One minute of narration

TTS

Sixty seconds of spoken audio at a typical narration pace. Conversion: ≈150 words/min ≈ 900 characters, so 0.9 × the per-1K-chars price.

ModelProviderCost / taskTasks / $1Arena Elo
Google$0.0036277
Google$0.0036277902 ±12
tts-1frontier
OpenAI$0.013741083 ±11
Amazon$0.01469879 ±14
tts-1-hdfrontier
OpenAI$0.027371102 ±12
ElevenLabs$0.045221098 ±11

One image

Image

A single generated image at the model's priced resolution. Conversion: 1 × the per-image list price.

ModelProviderCost / taskTasks / $1Arena Elo
FLUX Schnellfrontier
fal.ai$0.00303331000 ±0
OpenAI$0.04025950 ±8
Imagen 4.0frontier
Google$0.040251101 ±8
fal.ai$0.040251088 ±7
GPT Image 2frontier
OpenAI$0.053181339 ±7
Google$0.067141262 ±7
fal.ai$0.068141240 ±9
Google$0.1347.51225 ±7

Costs are computed from the sourced list prices shown on the pricing pages (excluding caching, batch discounts, volume and context-length tiers). Conversion constants are editorial and versioned with the methodology. Benchmarks by Artificial Analysis; “—” means no sourced measurement exists. See methodology.