Ellipsis-managed models
The zero-setup default: agents run on Ellipsis's own model access. Tokens are metered to your Ellipsis subscription at published per-model rates.
With no provider setup, agents run on Ellipsis's own model access. There is nothing to connect and no key to manage: name a model in the agent config and the session runs on it. This is how every account starts; connecting your own Anthropic key, Bedrock, or your own proxy changes who pays for tokens, never which models exist.
Default models
An agent picks its model with claude.model. Rates are USD per 1M tokens; a cache read is a prompt token replayed from the provider's prompt cache, and agent sessions resend their conversation on every turn, so most session input is billed at the cache-read rate.
| Model | claude.model | Input | Cache read | Output |
|---|---|---|---|---|
| Claude Opus 4.1 | claude-opus-4-1-20250805 | $15.00 | $1.50 | $75.00 |
| Claude Fable 5 | claude-fable-5 | $10.00 | $1.00 | $50.00 |
| Claude Opus 5 | claude-opus-5 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.8 | claude-opus-4-8 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.7 | claude-opus-4-7 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.6 | claude-opus-4-6 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.5 | claude-opus-4-5-20251101 | $5.00 | $0.50 | $25.00 |
| Claude Sonnet 5 | claude-sonnet-5 | $3.00 | $0.30 | $15.00 |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | $3.00 | $0.30 | $15.00 |
| Claude Sonnet 4.5 | claude-sonnet-4-5-20250929 | $3.00 | $0.30 | $15.00 |
| Claude Sonnet 4 | claude-sonnet-4-20250514 | $3.00 | $0.30 | $15.00 |
| Claude 3 Sonnet | claude-3-sonnet-20240229 | $3.00 | $0.30 | $15.00 |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | $1.00 | $0.10 | $5.00 |
| Claude 3 Haiku | claude-3-haiku-20240307 | $0.25 | $0.03 | $1.25 |
claude-opus-5 is the default: an agent that names no model runs on it.
An agent with a codex: block runs on OpenAI's Codex CLI instead, and picks from the models that serve the OpenAI Responses API:
| Model | codex.model | Input | Cache read | Output |
|---|---|---|---|---|
| GPT-5.6 Sol (Bedrock) | bedrock-gpt-5.6-sol | $5.50 | $0.55 | $33.00 |
| GPT-5.6 Terra (Bedrock) | bedrock-gpt-5.6-terra | $2.20 | $0.22 | $13.20 |
| GPT-5.6 Luna (Bedrock) | bedrock-gpt-5.6-luna | $0.22 | $0.03 | $1.32 |
bedrock-gpt-5.6-terra is the Codex default. A Claude model in codex.model fails validation at parse time rather than at run time, because Codex cannot call it.
The same list with the complete rate card, including the prompt-cache write lanes omitted above, is on the Models page of the dashboard and at GET /v1/models.
How it's billed
Token usage is metered to your Ellipsis subscription at the rates above, alongside sandbox compute and the platform fee. See Billing for how credits, usage billing, and the fee fit together.
- Every session shows its cost breakdown per turn, so you can see which step spent what.
- Spend limits bound token spend at the account, agent, and session level; a session that reaches its cap stops and says so.
- Repeated identical model calls (replays, retries) are served from Ellipsis's response cache and cost nothing.
Models
Every agent names the model it runs on. Ellipsis routes each model call to the provider setup you choose, from zero-setup Ellipsis-managed keys to your own gateway.
Bring your own Anthropic key
Connect your own Anthropic API key so agent tokens bill your Anthropic account. The Ellipsis platform fee is unchanged.