RelayTokens
Deposit

Three models.
No roulette.

RelayTokens carries one default generalist, one careful reviewer, and one fast first pass. Rates are pulled from the live catalog.

Live catalogChecked Nov 5, 2026
01

GPT-6.1 Sol

OpenAI · 1.05M context

The long-context generalist.

A 1.05M-token workspace model for repository-scale reasoning, precise edits, and long tool loops. The default choice when the task will not fit in one sitting.

Coding agentsLong documentsTool use

Official $2 / $10 per 1M97.1% below official

Model page

Customer rate

Input / 1M0.058
Output / 1M0.29
Cache read / 1M0.0029
Official price$2 / $10

97.1% below official

Tiered model. Long requests can price above the base row.

02

Claude Opus 5.5

Anthropic · 1M context

Careful reasoning, clean prose.

A 1M-token frontier model for review, architecture, and work where the cost of a plausible-but-wrong answer is high. Strong at reading before writing.

ReviewArchitectureWriting

Official $4 / $20 per 1M94.8% below official

Model page

Customer rate

Input / 1M0.209
Output / 1M1.04
Cache read / 1M0.01
Official price$4 / $20

94.8% below official

Base row shown. Actual charges follow the reported count.

03

Grok 4.7

xAI · 500K context

Fast, blunt, real-time.

A 500K-token model tuned for quick iteration and direct answers. Useful when latency matters more than ceremony and the prompt is already sharp.

Fast draftsClassificationSearch loops

Official $2 / $6 per 1M97.6% below official

Model page

Customer rate

Input / 1M0.048
Output / 1M0.145
Cache read / 1M0.012
Official price$2 / $6

97.6% below official

Tiered model. Long requests can price above the base row.

One key reaches all three.

Open an account