Models
Allowlist
These rows are the server catalog, grouped by provider. A completion must use one of these ids. The live GET /api/v1/models response is this list when inference is off, and the enabled stored rows when inference is on. Every model here accepts text messages only.
Rates were copied from the OpenRouter catalog (openrouter:2026-11-19). They are micro-USD per 1,000,000 tokens, shown here in dollars. Reservation uses the higher published prompt tier, including cache-write and long-context rates, and the higher published completion tier. The settled charge is the provider-reported cost, not a new price invented for this page.
OpenAI
GPT-4.1 Mini
openai/gpt-4.1-mini
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 1,047,576 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $0.40 / 1,000,000 tokens
- Reservation prompt rate
- $0.40 / 1,000,000 tokens
- Completion rate
- $1.60 / 1,000,000 tokens
- Reservation completion rate
- $1.60 / 1,000,000 tokens
GPT-4.1
openai/gpt-4.1
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 1,047,576 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $2.00 / 1,000,000 tokens
- Reservation prompt rate
- $2.00 / 1,000,000 tokens
- Completion rate
- $8.00 / 1,000,000 tokens
- Reservation completion rate
- $8.00 / 1,000,000 tokens
GPT-5.4
openai/gpt-5.4
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 1,050,000 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $2.50 / 1,000,000 tokens
- Reservation prompt rate
- $5.00 / 1,000,000 tokens
- Completion rate
- $15.00 / 1,000,000 tokens
- Reservation completion rate
- $22.50 / 1,000,000 tokens
Anthropic
Claude Haiku 4.5
anthropic/claude-haiku-4.5
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 200,000 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $1.00 / 1,000,000 tokens
- Reservation prompt rate
- $1.25 / 1,000,000 tokens
- Completion rate
- $5.00 / 1,000,000 tokens
- Reservation completion rate
- $5.00 / 1,000,000 tokens
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 1,000,000 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $3.00 / 1,000,000 tokens
- Reservation prompt rate
- $3.75 / 1,000,000 tokens
- Completion rate
- $15.00 / 1,000,000 tokens
- Reservation completion rate
- $15.00 / 1,000,000 tokens
Claude Opus 4.6
anthropic/claude-opus-4.6
- Capability
- Text chat
- Status
- On the server allowlist
- Context
- 1,000,000 tokens
- Max output ModelOne will accept
- 4,096 tokens
- Prompt rate
- $5.00 / 1,000,000 tokens
- Reservation prompt rate
- $6.25 / 1,000,000 tokens
- Completion rate
- $25.00 / 1,000,000 tokens
- Reservation completion rate
- $25.00 / 1,000,000 tokens
Skip to main content