FlexAI Models — Pricing & Benchmarks
32 models available · FlexAI Systems Inc
Last refreshed 2026-11-18. Next refresh: weekly.
FlexAI hosts 32 AI models in this catalog. The lowest listed input price is BGE M3 at $0.01/1M input tokens. LLM Reference compares these models across all 137 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| BGE M3 | $0.01 | — | 8K | |
| gpt-oss-20b | $0.018 | $0.09 | 128K | |
| Mistral NeMo Instruct (2407) | $0.023 | $0.03 | 128K | |
| gpt-oss-120b | $0.03 | $0.15 | 128K | |
| Llama 3.1 8B Instruct | $0.05 | $0.08 | 128K | |
| Qwen3 Reranker 8B | $0.05 | — | 40K | |
| Nemotron 3.5 Lightning | $0.06 | $0.16 | 1M | |
| Gemma 4 26B A4B IT | $0.067 | $0.29 | 256K | |
| Qwen3-Coder-30B-A3B-Instruct | $0.07 | $0.28 | 256K | |
| DeepSeek V4.1 Flash 1017 | $0.08 | $0.605 | 1M | |
| GLM-5.3-Flash | $0.088 | $0.25 | 1M | |
| Qwen3.5-9B | $0.1 | $0.15 | 256K | |
| Qwen3.6-35B-A3B | $0.1 | $0.95 | 256K | |
| DeepSeek V4 Flash 0731 | $0.13 | $0.26 | 1M | |
| Gemma 4 31B IT | $0.14 | $0.4 | 256K | |
| GLM-4.5-Air | $0.14 | $0.86 | 128K | |
| MiMo-V2.6-Flash | $0.14 | $0.28 | 1M | |
| PaddleOCR VL | $0.14 | $0.8 | 128K | |
| MiniMax M3.1 Flash | $0.15 | $0.6 | 1M | |
| Qwen3.8-Flash-Next | $0.15 | $0.47 | 256K | |
| Llama Guard 4 12B | $0.18 | $0.18 | 16K | |
| Qwen3-30B-A3B-Thinking-2507 | $0.2 | $2.40 | 256K | |
| Qwen3.8-27B | $0.2 | $2.50 | 256K | |
| Llama 3.3 70B Instruct | $0.22 | $0.5 | 128K | |
| Qwen3.6-27B | $0.25 | $2.00 | 256K | |
| Muse Glimmer | $0.35 | $1.50 | 128K | |
| GLM-5.2 | $0.6 | $2.00 | 1M | |
| FLUX.1 [schnell] | — | — | — | |
| Kokoro-82M | $0.99/1M chars | — | — | |
| MiniMax H3 | — | — | — | |
| NVIDIA Parakeet TDT 0.6B v3 | — | — | — | |
| Whisper large-v3-turbo | — | — | — |
Where else to run this
Pricing Overview
Cheapest$0.01/1M
Most expensive$0.60/1M
About FlexAI
Token Factory is an OpenAI-compatible API at api.flex.ai/v1. Serverless models are usage-priced; dedicated GPUs are priced per GPU-hour.
Full provider profile →