These rates match the model directory. Whether a model is enabled depends on your signed-in account group.
GPT public unit prices
Unit: USD per 1M tokens.
| Model ID | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
gpt-5.6-terra | $1 | $6 | $0.10 | $1.25 |
gpt-6-astra | $5 | $25 | $0.50 | $6.25 |
gpt-6-sol | $1 | $5 | $0.10 | $1.25 |
gpt-6.1-sol | $1 | $5 | $0.05 | $1.25 |
gpt-6.1-terra | $0.50 | $2.50 | $0.025 | $0.625 |
gpt-5.6-sol | $2 | $10 | $0.20 | $2.50 |
gpt-6-luna | $0.05 | $0.25 | $0.005 | $0.0625 |
Claude public unit prices
Unit: USD per 1M tokens. These rates are 50% of the official standard price. The 1-hour cache-write column is 50% of the official 1-hour tier. Official pricing for claude-haiku-5-5 has a higher tier above 100,000 tokens; this page lists the tier at or below that threshold (50% of that official tier). For longer prompts, check the actual charge on the usage page.
| Model ID | Input | Output | Cache read | Cache write | Cache write 1h |
|---|---|---|---|---|---|
claude-fable-5 | $5 | $25 | $0.50 | $6.25 | $10 |
claude-sonnet-5 | $1 | $5 | $0.10 | $1.25 | $2 |
claude-fable-5-1 | $5 | $25 | $0.125 | $6.25 | $10 |
claude-sonnet-5-5 | $1 | $5 | $0.05 | $1.25 | $2 |
claude-opus-5 | $2.50 | $12.50 | $0.25 | $3.125 | $5 |
claude-opus-5-5 | $2 | $10 | $0.10 | $2.50 | $4 |
claude-haiku-4-5-20251001 | $0.50 | $2.50 | $0.05 | $0.625 | $1 |
claude-haiku-5-5 | $0.05 | $0.25 | $0.005 | $0.0625 | $0.10 |
Image public unit prices
Unit: USD per image. 1K is 1024x1024, 2K is 2048x2048, and 4K is 3840x2160. These models share one size schedule.
| Model ID | 1K | 2K | 4K | Note |
|---|---|---|---|---|
gpt-image-2.6-flare | $0.08 | $0.10 | $0.15 | Default image model (used when model is omitted) |
gpt-image-2.6-sunburst | $0.08 | $0.10 | $0.15 | Listed above |
gpt-image-2 | $0.08 | $0.10 | $0.15 | Listed above |
gpt-image-2.5-flare | $0.08 | $0.10 | $0.15 | Listed above |
gpt-image-2.5-sunburst | $0.08 | $0.10 | $0.15 | Listed above |
Grok public unit prices
Unit: USD per 1M tokens. The retail row lists cache write as 0.
| Model ID | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
grok-4.5 | $1 | $3 | $0.15 | $0 |
grok-4.6 | $1 | $3 | $0.25 | $0 |
grok-4.7 | $1 | $3 | $0.25 | $0 |
Gemini public unit prices
Unit: USD per 1M tokens. Billed at these rates from 2026-11-12. The current official introductory price through 2026-11-30 is $2 input / $10 output per 1M tokens; this table is 50% of that. Official pricing changes on 2026-12-01, and this table will be updated if we keep the 50% rate.
| Model ID | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
gemini-4-argon | $1 | $5 | $0.05 | — |
Balance, access, and usage
After signing in, the console shows the models enabled for your account, your balance, and usage. Account groups control access. They do not replace the rates on this page. These figures are APIrove retail prices, not a model provider's list price.
API calls stop when your balance is 0. Need credits? Email help@apirove.com with your account email.
Sign in to APIrove · Model status and the same rates
Before your first call
- Check the model's public unit and rate in the tables above.
- Sign in and confirm the model is enabled for your account.
- Create a dedicated API key and keep it on a trusted server.
- Start with a small output limit or a low image size, then review usage.
Support: help@apirove.com. Refund rules for prepaid credits are in terms section 4.
After a call
After a successful request, check its usage record in the signed-in console. If the charge differs from what you expected, pause further requests and use the request time and any response request ID. Do not post an API key, prompt, or private bill.
gpt-5.6-sol is 50% of the official promotional price (through 2026-11-30) at the standard tier. Image rates are per image and are not stated as a percentage of official token prices.