What they do
Inference provides managed AI infrastructure and model APIs for structured output, video understanding, and related production inference workflows.
$10 off the fastest Kimi K3 and GLM 5.2 from Synthetic
Provider details
Inference
Learn more about this provider, then browse the models currently listed under it.
inferenceinference
Latest news about Inference
No articles yet. Fetch the latest news to show it here.
About Inference
How they were founded
Public sources identify Sam Hogan and Abe (Ibrahim) Ahmed among Inference's founders, while Founders, Inc. also lists Ryan McNutt and Chris Ries; public sources conflict on whether the company was founded in 2022 or 2023.
Quick Info
- Organization
- Inference
- Headquarters
- San Francisco, California, United States
- SDK package
- @ai-sdk/openai-compatible
- Synced at
- Jul 11, 2026
Models served
9 models available through Inference
These model results are sorted newest first so you can quickly see the latest options from this provider.
Inferenceqwen
Qwen 3 Embedding 4B
qwen/qwen3-embedding-4bInferenceReleased Jan 1, 202532,000 token context windowSubscription plan pricing
Input
Output
Inferenceqwen
Qwen 2.5 7B Vision Instruct
qwen/qwen-2.5-7b-vision-instructInferenceReleased Jan 1, 2025125,000 token context windowIn $0.20 · Out $0.20
Input
Output
Inferenceosmosis
Osmosis Structure 0.6B
osmosis/osmosis-structure-0.6bInferenceReleased Jan 1, 20254,000 token context windowIn $0.10 · Out $0.50
Input
Output
Inferencemistral-nemo
Mistral Nemo 12B Instruct
mistral/mistral-nemo-12b-instructInferenceReleased Jan 1, 202516,000 token context windowIn $0.038 · Out $0.10
Input
Output
Inferencellama
Llama 3.2 3B Instruct
meta/llama-3.2-3b-instructInferenceReleased Jan 1, 202516,000 token context windowIn $0.02 · Out $0.02
Input
Output
Inferencellama
Llama 3.2 1B Instruct
meta/llama-3.2-1b-instructInferenceReleased Jan 1, 202516,000 token context windowIn $0.01 · Out $0.01
Input
Output
Inferencellama
Llama 3.2 11B Vision Instruct
meta/llama-3.2-11b-vision-instructInferenceReleased Jan 1, 202516,000 token context windowIn $0.055 · Out $0.055
Input
Output
Inferencellama
Llama 3.1 8B Instruct
meta/llama-3.1-8b-instructInferenceReleased Jan 1, 202516,000 token context windowIn $0.025 · Out $0.025
Input
Output
Inferencegemma
Input
Output