KI‑Modell‑Intelligenz

Anbieter · 2026-05-12

cloudflare-ai-gateway

15 kanonische Modelle19 Einträge insgesamt (inkl. Derivate)
ModellEingabe / 1MAusgabe / 1MKontextHosterTags
BGE Reranker Base$0.003Unknown128K1
BGE M3$0.012Unknown128K1
PLaMo Embedding 1B$0.019Unknown128K1
BGE Small EN v1.5$0.020Unknown128K1
DistilBERT SST-2 INT8$0.026Unknown128K1
BGE Base EN v1.5$0.067Unknown128K1
IBM Granite 4.0 H Micro$0.017$0.110128K1
BGE Large EN v1.5$0.200Unknown128K1
IndicTrans2 EN-Indic 1B$0.340$0.340128K1
BART Large CNNUnbekanntUnbekannt128K1
Deepgram Aura 2 (EN)UnbekanntUnbekannt128K1
Deepgram Aura 2 (ES)UnbekanntUnbekannt128K1
Deepgram Nova 3UnbekanntUnbekannt128K1
MyShell MeloTTSUnbekanntUnbekannt128K1
Pipecat Smart Turn v2UnbekanntUnbekannt128K1
Mistral 7B Instruct v0.1Derivat$0.110$0.190128K1
Gemma SEA-LION v4 27B ITDerivat$0.350$0.560128K1
Nemotron 3 Super 120BDerivat$0.500$1.50256K1tools · reasoning · open-weights
Claude Sonnet 3Derivat$3.00$15.00200K1tools · vision

Frequently asked questions

How many AI models does cloudflare-ai-gateway offer?

We track 15 canonical cloudflare-ai-gateway models plus 4 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which cloudflare-ai-gateway model is the cheapest?

BGE Reranker Base is currently the lowest-priced cloudflare-ai-gateway model, at $0.003 per 1M input tokens and Unknown per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which cloudflare-ai-gateway model has the largest context window?

BGE Reranker Base leads at 128K tokens. This is the total of prompt + completion.

What are the best alternatives to cloudflare-ai-gateway?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this cloudflare-ai-gateway pricing data?

Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

Zuletzt aktualisiert:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.