LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Providers

Inference

inference·Gateway·9 models·Official docs ↗

Inference is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.

It lists 9 models on this page. Coverage spans text and chat (8) and embeddings (1). The lowest-priced model hosted here is Qwen 3 Embedding 4B.

Inference is the lowest paid channel for 4 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.

Coverage & pricing
Models hosted9With public price 9
Cheapest anywhere4
Model typesText / Chat 8Embedding 1
Cheapest model hereQwen 3 Embedding 4B
SDK package@ai-sdk/openai-compatible
APIhttps://inference.net/v1

Hosted models by blended price asc

⌕
9 of 9
Cheapest here?
Qwen 3 Embedding 4BEmbeddingqwen/qwen3-embedding-4bLowest anywhere$0.01$0—32,000Lowest anywhere
Llama 3.2 1B Instructmeta/llama-3.2-1b-instructLowest anywhere$0.01$0.01—16,000Lowest anywhere
Llama 3.2 3B Instructmeta/llama-3.2-3b-instructLowest anywhere$0.02$0.02—16,000Lowest anywhere
Llama-3.1-8B-Instructmeta/llama-3.1-8b-instruct1.1× pricier$0.025$0.025—16,0001.1× pricier
Mistral Nemomistral/mistral-nemo-12b-instruct2.1× pricier$0.038$0.10—16,0002.1× pricier
Llama-3.2-11B-Vision-Instructmeta/llama-3.2-11b-vision-instructLowest anywhere$0.055$0.055—16,000Lowest anywhere
Google Gemma 3google/gemma-3Only channel$0.15$0.30—125,000Only channel
osOsmosis Structure 0.6Bosmosis/osmosis-structure-0.6bOnly channel$0.10$0.50—4,000Only channel
Qwen 2.5 7B Vision Instructqwen/qwen-2.5-7b-vision-instructOnly channel$0.20$0.20—125,000Only channel