Appearance
Common Models
A quick pricing reference for common models. Prices are in USD per 1M tokens.
OpenAI Models
| Provider | Model | Cached | Input | Output |
|---|---|---|---|---|
| OpenAI | gpt-5.6-sol* / gpt-5.5 | $0.50 | $5.00 | $30.00 |
| OpenAI | gpt-5.6-terra | $0.20 | $2.00 | $12.00 |
| OpenAI | gpt-5.6-luna | $0.02 | $0.20 | $1.20 |
| CE Plus Pool (0.03x) | gpt-5.6-sol / gpt-5.5 | $0.015 | $0.15 | $0.90 |
| CE Plus Pool (0.03x) | gpt-5.6-terra | $0.006 | $0.06 | $0.36 |
| CE Plus Pool (0.03x) | gpt-5.6-luna | $0.0006 | $0.006 | $0.036 |
GPT-5.6 series charges for cache writes, but CE does not.
GPT models charge 1.5x–2x above long context (272K-1M).
CE offers GPT Image 2 separately at $0.015 per generated image.
Codex Plus Pool 0.03x · Codex Pro Pool 0.05x
gpt-5.6-sol gpt-5.6-terra gpt-5.6-luna gpt-5.5 gpt-5.4 gpt-5.4-mini codex-auto-review gpt-5.3-codex-spark gpt-image-2
Token usage is billed at 3% (Plus Pool) or 5% (Pro Pool) of official OpenAI pricing.
Pro Pool is a backup for when Plus Pool is unstable.
GPT Image 2 is billed at $0.015 / image independently.
* Unfortunately, OpenAI's recent promotional pricing on gpt-5.6-sol does not apply to Codex subscriptions, so CE is unable to pass on the discount for this model. Discounts on gpt-5.6-terra and gpt-5.6-luna are applied normally.
Anthropic Models
| Provider | Model | Cached | Input | Output |
|---|---|---|---|---|
| Anthropic | claude-fable-5 | $1.00 | $10.00 | $50.00 |
| Anthropic | claude-opus-5 | $0.50 | $5.00 | $25.00 |
| Anthropic | claude-sonnet-5 | $0.20 | $2.00 | $10.00 |
| CE Max Pool (0.24x) | claude-fable-5 | $0.24 | $2.40 | $12.00 |
| CE Kiro (0.045x) | claude-opus-5 | $0.0225 | $0.225 | $1.125 |
| CE Kiro (0.045x) | claude-sonnet-5 | $0.009 | $0.09 | $0.45 |
Claude 1h cache writes are billed at 2x input.
Claude 5m cache writes are billed at 1.25x input.
Claude via Kiro 0.045x · Claude Max Pool 0.24x
claude-fable-5 (Max Pool only) claude-opus-5 claude-sonnet-5 claude-opus-4.8 claude-opus-4.7 claude-opus-4.6 claude-sonnet-4.6 claude-haiku-4.5
Usage is billed at 4.5% (Kiro) or 24% (Max Pool) of official Anthropic pricing.
Max Pool quality is identical to official Claude Max.
Kiro routes have some system prompt contamination.
xAI Models
| Provider | Model | Cached | Input | Output |
|---|---|---|---|---|
| xAI | grok-4.6 | $0.50 | $2.00 | $6.00 |
| xAI | grok-4.5 | $0.30 | $2.00 | $6.00 |
| CE Heavy Pool (0.06x) | grok-4.6 | $0.03 | $0.12 | $0.36 |
| CE Heavy Pool (0.06x) | grok-4.5 | $0.018 | $0.12 | $0.36 |
Grok models charge 2x for long context (200K-500K).
Grok Heavy Pool 0.06x · Grok Free Pool 0.03x
grok-4.6 grok-4.5
Token usage is billed at 6% (Heavy Pool) or 3% (Free Pool) of official xAI pricing.
Grok Free Pool is currently suspended as xAI has reduced model intelligence for free-tier accounts, based on our observation.
Google Models
| Provider | Model | Cached | Input | Output |
|---|---|---|---|---|
| Google Cloud | gemini-3.1-pro | $0.20 | $2.00 | $12.00 |
| Google Cloud | gemini-3.7-flash | $0.075 | $0.75 | $3.75 |
| CE Antigravity (0.06x) | gemini-3.1-pro | $0.012 | $0.12 | $0.72 |
| CE Antigravity (0.06x) | gemini-3.7-flash | $0.0045 | $0.045 | $0.225 |
Gemini 3.1 Pro charges 2x for long context (>200K).
Gemini via Antigravity Beta 0.06x
gemini-3.7-flash gemini-3.6-flash gemini-3.5-flash gemini-3.1-pro gemini-3-flash-preview
Usage is billed at 6% of official Google Cloud pricing.
Still Testing. Known issue: cache hit rate is low during streaming.