gpt-6.1-sol
Platform OpenAI
Billing ModePer-token
Paid Price
$0.40/ 1M tokens (input)From
Pricing by Group
OpenAI-ChatGPT
Rate0.2x| Input tokens | Output tokens | Cache write (5m) | Cache write (1h) | Cache read |
|---|---|---|---|---|
| ≤272K $0.40 | $2.00 | $0.50 | $0.50 | $0.04 |
| >272K $0.80 | $3.00 | $1.00 | $1.00 | $0.08 |
≤272K
- Input tokens
- $0.40
- Output tokens
- $2.00
- Cache write (5m)
- $0.50
- Cache write (1h)
- $0.50
- Cache read
- $0.04
>272K
- Input tokens
- $0.80
- Output tokens
- $3.00
- Cache write (5m)
- $1.00
- Cache write (1h)
- $1.00
- Cache read
- $0.08
The whole request is billed at the tier matching its total context (input + cache write + cache read)
Official reference price
| Input tokens | Output tokens | Cache write (5m) | Cache write (1h) | Cache read |
|---|---|---|---|---|
| ≤272K $2.00 | $10.00 | $2.50 | $2.50 | $0.10 |
| >272K $4.00 | $15.00 | $5.00 | $5.00 | $0.20 |
Official reference price is read-only and never multiplied; "Not provided" means the dimension has no data — never treat it as zero.
Access
quickstart.sh
curl -N https://api.routefast.ai/v1/chat/completions \
-H "Authorization: Bearer $ROUTEFAST_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"messages": [{"role":"user","content":"Hello"}],
"stream": true
}'