OmniRouteby Cheaper Inference

OmniRoute / Cheaper Inference catalog

Every model, at the price you actually pay.

The hosted Cheaper Inference catalog OmniRoute can route to, with the direct list price beside the price you pay.

Browse the catalog Try Cheaper Inference Back to overview

Live catalog

Compare the list price with the price you pay.

Prices checked Sep 5, 2026. Rates move when upstream pricing or the available routes change.

64 modelsDirect list price compared with the Cheaper Inference price
Direct list prices compared with Cheaper Inference prices by model
ModelInput priceOutput priceSavingsContextDetails
gpt-5.6-lunaOpenAI · text$0.20$0.08/ 1M tokens$1.20$0.48/ 1M tokens60% off1.1M
gpt-oss-120bOpenAI · text$0.10$0.04/ 1M tokens$0.50$0.20/ 1M tokens60% off—
glm-5.3-flashZ.ai · text$0.15$0.0705/ 1M tokens$0.50$0.235/ 1M tokens53% off1.0M
qwen3.6-27bAlibaba · text$0.60$0.267298/ 1M tokens$3.60$1.78199/ 1M tokens50.5% off256K
gpt-5.6-solOpenAI · text$2.00$1.00/ 1M tokens$10.00$5.00/ 1M tokens50% off1.1M
glm-5Z.ai · text$1.00$0.534597/ 1M tokens$3.20$1.71071/ 1M tokens46.54% off198K
glm-4.5Z.ai · text$0.60$0.33/ 1M tokens$2.20$1.21/ 1M tokens45% off128K
glm-4.5-airZ.ai · text$0.20$0.11/ 1M tokens$1.10$0.605/ 1M tokens45% off128K
glm-4.6Z.ai · text$0.60$0.33/ 1M tokens$2.20$1.21/ 1M tokens45% off198K
glm-4.7Z.ai · text$0.60$0.33/ 1M tokens$2.20$1.21/ 1M tokens45% off128K
glm-5.1Z.ai · text$1.40$0.77/ 1M tokens$4.40$2.42/ 1M tokens45% off200K
glm-5.2Z.ai · text$0.80$0.44/ 1M tokens$2.55$1.4025/ 1M tokens45% off1.0M
glm-5.3Z.ai · text$0.70$0.385/ 1M tokens$2.20$1.21/ 1M tokens45% off1M
deepseek-v4-flashDeepSeek · text$0.13$0.075966/ 1M tokens$0.26$0.151932/ 1M tokens41.56% off1M
deepseek-v4-flash-0731DeepSeek · text$0.076$0.050545/ 1M tokens$0.153$0.101755/ 1M tokens33.49% off1.0M
claude-fable-5Anthropic · text$10.00$7.00/ 1M tokens$50.00$35.00/ 1M tokens30% off1M
claude-fable-5.1Anthropic · text$10.00$7.00/ 1M tokens$50.00$35.00/ 1M tokens30% off1M
claude-haiku-4.5Anthropic · text$1.00$0.70/ 1M tokens$5.00$3.50/ 1M tokens30% off200K
claude-opus-4-8-fastAnthropic · text$12.00$8.40/ 1M tokens$60.00$42.00/ 1M tokens30% off1M
claude-opus-4.5Anthropic · text$5.00$3.50/ 1M tokens$25.00$17.50/ 1M tokens30% off198K
Showing 20 of 64 models

Cheaper Inference is the hosted gateway. Self-hosted OmniRoute routes to the providers you connect yourself, at whatever those providers charge you.

OmniRoute by Cheaper Inference

Choose how you run OmniRoute.

Self-host OmniRoute, or use Cheaper Inference for a hosted cost-ranked gateway.

Try Cheaper Inference Self-host OmniRoute (opens in a new tab) View on GitHub (opens in a new tab)