Input
- Official OpenAI
- $2
- Here (−50%)
- $1
gpt-6.1-sol
GPT-6.1 Sol API — price per token
GPT-6.1 Sol is the newest GPT model: near-Astra quality for complex coding, computer use and professional work at a fraction of the Astra price, on the OpenAI-compatible endpoint. Choose reasoning effort from low to max, send images, and use structured outputs or function tools.
Pricing per 1M tokens
| Rate | Official OpenAI | Here (−50%) |
|---|---|---|
| Input | $2 | $1 |
| Cached input | $0.1 | $0.05 |
| Cache write | $2.5 | $1.25 |
| Output | $10 | $5 |
Cached input
- Official OpenAI
- $0.1
- Here (−50%)
- $0.05
Cache write
- Official OpenAI
- $2.5
- Here (−50%)
- $1.25
Output
- Official OpenAI
- $10
- Here (−50%)
- $5
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 872K tokens. Max output: 128K tokens. Reasoning efforts: low, medium, high, xhigh, max.
Best for
- Complex coding and agentic work close to Astra quality at a lower price.
- Long sessions with repeated context: cached input is $0.10 per 1M.
- Tool calls, image understanding and structured JSON output.
Good to know
- This service uses GPT-6.1 Sol's Codex subscription limits: 872K maximum context. The larger direct OpenAI API window does not apply here.
- Discovery reports 872K total context, 128K output and 744K conservative input.
- Cached input bills at 5% of input, half the GPT-6 Sol rate.
- Above 272K input tokens, the whole request uses 2× input/cache rates and 1.5× output rates. Fast (priority) uses 2× the applicable API rates.
- Reasoning none and Codex-specific ultra delegation are not advertised.
How to use GPT-6.1 Sol
Create a free account, generate one key, and point any OpenAI-compatible tool at https://router.apitoken.sale/v1 with model ID gpt-6.1-sol — Responses and Chat Completions both work, authenticated with Authorization: Bearer. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://openai.api.apitoken.sale/v1 keep working.
Frequently asked questions
What does GPT-6.1 Sol cost?
Official rates per 1M tokens are $2 input, $0.10 cached input, $2.50 cache write and $10 output. With the normal 50% B2C discount, these are $1, $0.05, $1.25 and $5. OpenKeys uses the official rates.
How is GPT-6.1 Sol different from GPT-6 Sol?
GPT-6.1 Sol is a separate, newer model with its own ID. OpenAI positions it close to Astra on complex work. Input and output rates are the same as GPT-6 Sol, cached input is half ($0.10 against $0.20), and reasoning starts at low (no none). Both stay available; choose by model ID.
How do I select GPT-6.1 Sol?
Set model to gpt-6.1-sol on https://router.apitoken.sale/v1. Supported reasoning levels are low, medium, high, xhigh and max. Use service_tier priority for Fast.
Run GPT-6.1 Sol on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.