Models and per-token pricing

Each request is charged per token at its model's list price.

Prices in USD per 1,000,000 tokens.

ModelInputCached inputOutputCache write
(5 min)
Cache write
(1 hour)
GLM-5.3
momento/zai-org/GLM-5.3Try
$1.40$0.14$4.40——
DeepSeek V4 Pro
momento/deepseek-ai/DeepSeek-V4-ProTry
$1.32$0.132$3.96——
Kimi K3
momento/moonshotai/Kimi-K3Try
$3.00$0.30$15.00——
Gemma 4 Tailwind
momento/gemma4-tailwindTry
$0.12$0.12$0.35——
Claude Fable 5.1
anthropic/claude-fable-5-1
$10.00$0.25$50.00$12.50$20.00
Claude Opus 5.5
anthropic/claude-opus-5-5
$4.00$0.20$20.00$5.00$8.00
Claude Fable 5
anthropic/claude-fable-5
$10.00$1.00$50.00$12.50$20.00
Claude Opus 5
anthropic/claude-opus-5
$5.00$0.50$25.00$6.25$10.00
Claude Opus 4.8
anthropic/claude-opus-4-8
$5.00$0.50$25.00$6.25$10.00
Claude Sonnet 5
anthropic/claude-sonnet-5
$2.00$0.20$10.00$2.50$4.00
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
$3.00$0.30$15.00$3.75$6.00
Claude Haiku 4.5
anthropic/claude-haiku-4-5
$1.00$0.10$5.00$1.25$2.00

* GLM-5.3 Flash Fast uses 4-bit MXFP4 quantization with a 1M-token context window. When Momento capacity is full, requests overflow to partner inference providers at the same price. Approximately 735 tokens per second in a single session, measured November 17, 2026.

How credits work

  • Credits are prepaid: buy them first, and requests draw from your balance.
  • Every request is drawn at the prices above, whichever backend serves it.
  • Cache writes are charged at the model's cache-write price (Anthropic's own rates for Claude); a model without one (—) charges them at its input price.
  • Credits don't expire.