FlexAI
Researched todayInference PlatformTier 3FlexAI Systems Inc
FlexAI offers 32 tracked models (25 with output token pricing). This catalog covers coding, rag, and agents; open any model detail page for benchmarks, batch tiers, and migration prompts.
Covers 7 workload areas across 32 tracked models; last verified 2026-11-18.
Use it for
- Teams comparing token and batch pricing across this provider's models
- Operators routing coding, rag, and agents workloads through this API
Do not use it for
- Final benchmark picks without opening the relevant model detail page
Tracked models
32
Models available through this provider
Priced output routes
25
Models with output token pricing tracked
Cheapest output
$0.030
Mistral NeMo Instruct (2407) on this route
Batch-ready models
0
No batch pricing tracked
Latest model release
2026-10-19
30d since newest release
Freshness
2026-11-18
Researched today
Information
FlexAI operates Token Factory, an OpenAI-compatible inference API for open models, plus dedicated GPU endpoints, fine-tuning, training, and private-cloud AI Factory deployments.
Where this host wins
- Coding: 13 tracked models with SWE-bench / HumanEval-style scores.
- RAG: 21 tracked models with ruler / needle retrieval benchmarks.
- Agentic: 17 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 23 tracked models with context-token or InfiniteBench-class signal.
Getting started
Platform Overview
Token Factory is an OpenAI-compatible API at api.flex.ai/v1. Serverless models are usage-priced; dedicated GPUs are priced per GPU-hour.
Available Models(32)
View all →All models available as Serverless