14 models from 6 makers that you can call through Together AI — each one tested by us with fixed prompts, outputs kept, costs measured.
Makers: black-forest-labs · google · openai · qwen · rundiffusion · stabilityai
Docs Get an API key Their pricing page
Together AI isn't a model creator — it's a hosting and inference layer for open-weight models, serving 200+ of them (Llama, Qwen, DeepSeek, Mistral, Gemma, and more) behind one API.
Alongside pay-per-token serving, Together offers fine-tuning and dedicated endpoints for production workloads that need consistent throughput.
Affiliate program: No public affiliate/referral commission program found — Together offers a Startup Accelerator (credits), not a pay-per-referral program.
This is what Together AI itself charges for each model — not the cheapest price across every provider (that's what the cards above show). Prompt tokens range $0.0000–$0.0000 per 1M across 14 priced models.
| Model | Maker | Price via Together AI | Context |
|---|---|---|---|
| FLUX.1 Kontext [max] | black-forest-labs | $0.084/image | — |
| FLUX.1 Kontext [pro] | black-forest-labs | $0.042/image | — |
| FLUX1.1 [pro] | black-forest-labs | $0.042/image | — |
| FLUX.2 [dev] | black-forest-labs | $0.0154/image | — |
| FLUX.2 [flex] | black-forest-labs | $0.03/image | — |
| FLUX.2 [max] | black-forest-labs | $0.0735/image | — |
| gemini-3-pro-image | $0.134/image | — | |
| gemma-3-4b-it | free | 66K | |
| gpt-image-1.5 | openai | $0.034/image | — |
| gpt-image-2 | openai | $0.053/image | — |
| Qwen Image | qwen | $0.0058/image | — |
| Juggernaut Lightning Flux by RunDiffusion | rundiffusion | $0.0017/image | — |
| Juggernaut Pro Flux by RunDiffusion 1.0.0 | rundiffusion | $0.0049/image | — |
| SD XL | stabilityai | $0.0019/image | — |
Latency: Per-provider latency isn't independently measured yet — the probe rig currently tests one route per model, not one per provider (see PROBE_RIG.md ledger #10).