Frontier Models,
85-95% off
One prepaid key for OpenAI, Responses, and Anthropic-compatible clients. No subscription.
Try before you pay: one real gpt-5.6-terra call through our gateway, metered in front of you. Three per visitor per day, no signup.
| GPT-5.6 Sol | $0.250 | Reference unavailable |
| GPT-5.6 Terra | $0.100 | Reference unavailable |
| GPT-5.5 | $0.250 | Reference unavailable |
| GPT-5.6 | $0.200 | Reference unavailable |
| GPT-6 Astra | $0.500 | Reference unavailable |
Savings on both rates vs OpenRouter
Sources and full comparisons →Current model rates
Scroll sideways to see every column.
| Model | Input / 1M | Output / 1M | OpenRouter input / output | Savings on both rates | Access |
|---|---|---|---|---|---|
gpt-5.6-sol | $0.250 | $1.500 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-5.6-terra | $0.100 | $0.600 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-5.5 | $0.250 | $1.500 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-5.6 | $0.200 | $1.000 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-6-astra | $0.500 | $2.500 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-6-sol | $0.100 | $0.500 | No verified quote / No verified quote | Reference unavailable | Buy → |
gpt-6.1-sol | $0.100 | $0.500 | No verified quote / No verified quote | Reference unavailable | Buy → |
codex-auto-review | $0.250 | $1.500 | No verified quote / No verified quote Not checked | Reference unavailable | Buy → |
Frontier routes first
136 routes are listed upstream. Each becomes purchasable here only after its own completion, billing and feature checks pass.
Compare provider prices
USD per 1M tokens. Input and output compared separately.
Scroll sideways to see every column.
| Model | DiscountedTokens Input / Output | Compare with | Provider input / output | Input difference | Output difference |
|---|---|---|---|---|---|
| GPT-5.6 Sol gpt-5.6-sol | $0.250 / $1.500 No current comparison | OpenRouter ↗Historical / unverified | $4.000 / $20.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-5.6 Sol gpt-5.6-sol | $0.250 / $1.500 No current comparison | OpenAI ↗Historical / unverified | $4.000 / $20.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-5.6 Sol gpt-5.6-sol | $0.250 / $1.500 No current comparison | RunAPI ↗Historical / unverified | $3.200 / $16.000 Starting rates; context-dependent ranges: $3.20-$6.40 / 1M tokens input; $16.00-$24.00 / 1M tokens output. | Not comparable | Not comparable |
| GPT-5.6 Terra gpt-5.6-terra | $0.100 / $0.600 No current comparison | OpenRouter ↗Historical / unverified | $2.000 / $12.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-5.6 Terra gpt-5.6-terra | $0.100 / $0.600 No current comparison | OpenAI ↗Historical / unverified | $2.000 / $12.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-5.6 Terra gpt-5.6-terra | $0.100 / $0.600 No current comparison | RunAPI ↗Historical / unverified | $1.600 / $9.600 Starting rates; context-dependent ranges: $1.60-$3.20 / 1M tokens input; $9.60-$14.40 / 1M tokens output. | Not comparable | Not comparable |
| GPT-5.5 gpt-5.5 | $0.250 / $1.500 No current comparison | OpenRouter ↗Historical / unverified | $5.000 / $30.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-5.5 gpt-5.5 | $0.250 / $1.500 No current comparison | OpenAI ↗Historical / unverified | $5.000 / $30.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-5.5 gpt-5.5 | $0.250 / $1.500 No current comparison | RunAPI ↗Historical / unverified | $4.000 / $24.000 Starting rates; context-dependent ranges: $4.00-$8.00 / 1M tokens input; $24.00-$36.00 / 1M tokens output. | Not comparable | Not comparable |
| GPT-5.6 gpt-5.6 | $0.200 / $1.000 No current comparison | OpenRouter ↗Historical / unverified | $1.000 / $2.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-6 Astra gpt-6-astra | $0.500 / $2.500 No current comparison | OpenRouter ↗Historical / unverified | $10.000 / $50.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-6 Astra gpt-6-astra | $0.500 / $2.500 No current comparison | OpenAI ↗Historical / unverified | $10.000 / $50.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-6 Astra gpt-6-astra | $0.500 / $2.500 No current comparison | RunAPI ↗Historical / unverified | $8.000 / $40.000 Starting rates; context-dependent ranges: $8.00-$16.00 / 1M tokens input; $40.00-$60.00 / 1M tokens output. | Not comparable | Not comparable |
| GPT-6 Sol gpt-6-sol | $0.100 / $0.500 No current comparison | OpenRouter ↗Historical / unverified | $2.000 / $10.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-6 Sol gpt-6-sol | $0.100 / $0.500 No current comparison | OpenAI ↗Historical / unverified | $2.000 / $10.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-6 Sol gpt-6-sol | $0.100 / $0.500 No current comparison | RunAPI ↗Historical / unverified | $1.600 / $8.000 Starting rates; context-dependent ranges: $1.60-$3.20 / 1M tokens input; $8.00-$12.00 / 1M tokens output. | Not comparable | Not comparable |
| GPT-6.1 Sol gpt-6.1-sol | $0.100 / $0.500 No current comparison | OpenRouter ↗Historical / unverified | $2.000 / $10.000 Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| GPT-6.1 Sol gpt-6.1-sol | $0.100 / $0.500 No current comparison | OpenAI ↗Historical / unverified | $2.000 / $10.000 Standard short-context token rates, not Batch, Flex or Fast mode. | Not comparable | Not comparable |
| GPT-6.1 Sol gpt-6.1-sol | $0.100 / $0.500 No current comparison | RunAPI ↗Historical / unverified | $1.600 / $8.000 Starting rates; context-dependent ranges: $1.60-$3.20 / 1M tokens input; $8.00-$12.00 / 1M tokens output. | Not comparable | Not comparable |
| Codex Auto Review codex-auto-review | $0.250 / $1.500 No current comparison | OpenRouter ↗ Not checked Historical / unverified | No verified quote / No verified quote Base token rates only; excludes cache, batch, tools, long context and platform fees. | Not comparable | Not comparable |
| Codex Auto Review codex-auto-review | $0.250 / $1.500 No current comparison | RunAPI ↗Historical / unverified | $0.160 / $0.960 Starting rates; context-dependent ranges: $0.16-$0.32 / 1M tokens input; $0.96-$1.44 / 1M tokens output. | Not comparable | Not comparable |
Base token rates only; excludes cache, batch, tools, long context and platform fees.
Single discount badges use the smaller input/output saving, rounded down. Quotes older than 24 hours do not generate discount claims. Sources are checked every four hours; availability and model identity are not independently guaranteed.
Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.
Estimate a repeated workload
Example assumes every request has the token counts above. Mixed request sizes produce a different total. USD at current rates; list comparison is token-only, not a provider invoice.
Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.
JavaScript is needed for the interactive calculator. Current token rates are listed on this page.
Three changes, then call the API
Card or crypto, prepaid.
It is revealed once after payment.
Use your existing OpenAI or Anthropic client.
Useful before you need paid capacity
Inspect before you buy
Same SDK. Different base URL.
Buy credits, copy the key once, and point your existing client at DiscountedTokens.
Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.