GPT-5.6 Sol API price — 3 gateways compared
Cheapest right now: OpenRouter at $2.00/MTok in — 2.0× cheaper than the priciest gateway.
OpenAI · from $2.00 per
million input tokens · 2.0× spread between gateways
· updated continually
Gateway $ in /MTok $ out /MTok
Context Input price history Model ID
OpenRouter fees $2.00 $10.00 1,050,000 openai/gpt-5.6-sol use Glama $2.50 $15.00 1,050,000 openai/gpt-5.6-sol use Requesty $4.00 $20.00 1,050,000 azure/gpt-5.6-sol@eastus2 use
Fees beyond the token price OpenRouter : No markup on token prices (provider pass-through), but credit purchases cost 5.5% via card ($0.80 minimum) or 5% via crypto; BYOK usage above the monthly allowance is charged 5%. source
Changelog for GPT-5.6 Sol
2026-08-27 requesty raised gpt-5.6-sol-output 11.1%: 18.0 → 20.0 usd_per_mtok
2026-08-27 requesty raised gpt-5.6-sol-input 11.1%: 3.6 → 4.0 usd_per_mtok
2026-08-23 requesty cut gpt-5.6-sol-output 33.3%: 27.0 → 18.0 usd_per_mtok
2026-08-23 requesty cut gpt-5.6-sol-input 20.0%: 4.5 → 3.6 usd_per_mtok
2026-08-21 openrouter cut openai-gpt-5.6-sol-output 33.3%: 15.0 → 10.0 usd_per_mtok
2026-08-21 openrouter cut openai-gpt-5.6-sol-input 20.0%: 2.5 → 2.0 usd_per_mtok
2026-08-18 openrouter listed openai-gpt-5.6-sol-output at 15.0 usd_per_mtok
2026-08-18 openrouter listed openai-gpt-5.6-sol-input at 2.5 usd_per_mtok
2026-08-17 openrouter delisted openai-gpt-5.6-sol-output
2026-08-17 openrouter delisted openai-gpt-5.6-sol-input
GPT-5.6 Sol pricing FAQ
How much does GPT-5.6 Sol cost per million tokens? The cheapest tracked gateway charges $2.00 per million input tokens and $10.00 per million output tokens (OpenRouter). Prices refresh continually.
Which gateway is cheapest for GPT-5.6 Sol? OpenRouter for input tokens and OpenRouter for output tokens, among the 3 gateways we track.
Do GPT-5.6 Sol prices differ between gateways? Yes — the most expensive tracked gateway charges 2.0× the cheapest for input tokens. Identical model, identical tokens, different bill.
← All LLM prices · API
Every datum links its source and is versioned in
public git history .
Data: CC BY 4.0 — cite gpudiff.com. Nameplate specs are vendor claims, not measured
throughput. Vast prices are the 25th percentile of verified marketplace listings
(what a careful buyer actually gets); RunPod prices are list. Outbound provider
links may carry referral codes and sponsored units are labelled; neither ever
affects the numbers. Sponsor this site .