Live model catalog

Loading models…

Fetching current CloudService availability and prices.

Live model catalog

Models and pricing

Routed: 15
Providers: 2
Access: Public

Compare display names, exact copyable API IDs, active routing, token limits, and the rates currently used by CloudService. Only models on an active configured route appear; each listing states whether it is available through self-service checkout.

15 routed models across 2 providers. Copy the API ID exactly; the display name is for people. A limited-access label means the model is listed for comparison but cannot be purchased through checkout.

Choose a plan Model helpPublic catalog · no sign-in required← Back to website

Choose by task

Guidance comes from the live catalog, published rates, and route names—not hidden benchmarks.

“Lower published rate” compares the current input and output rates. “Fast responses” is based on active route naming and should be tested for your workload.

15 active routed models shown. Limits and capabilities come from the current catalog record.

Active CloudService models with production planning fields and prices per one million tokens
Model	Active route	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Claude Haiku 4.5 API ID · copy exactly`claude-haiku-4-5-20251001` Fast responseLower published rate	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $1.20 Output $6.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Claude Opus 4.6 API ID · copy exactly`claude-opus-4-6`	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $6.00 Output $30.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Claude Opus 4.7 API ID · copy exactly`claude-opus-4-7`	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $6.00 Output $30.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Claude Opus 4.8 API ID · copy exactly`claude-opus-4-8`	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $6.00 Output $30.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Claude Opus 5 API ID · copy exactly`claude-opus-5` Long context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $6.00 Output $30.00	Context 1,000,000 Max output 128,000 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Claude Sonnet 5 API ID · copy exactly`claude-sonnet-5` Lower published rate	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $2.40 Output $12.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Fable 5 API ID · copy exactly`fable-5` Long context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $12.00 Output $60.00	Context 1,050,000 Max output 128,000 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Fable 5 Ultra API ID · copy exactly`fable-5-ultra` Long context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $12.00 Output $60.00	Context 1,050,000 Max output 128,000 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name Codex Auto Review API ID · copy exactly`codex-auto-review` Build & code	custom	Chat CompletionsOpenAI-compatible	Input $6.00 Output $36.00	Context Limit unavailable Max output 4,096 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.3 Codex API ID · copy exactly`gpt-5.3-codex` Build & code	custom	Chat CompletionsOpenAI-compatible	Input $2.10 Output $16.80	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.4 API ID · copy exactly`gpt-5.4`	custom	Chat CompletionsOpenAI-compatible	Input $3.00 Output $18.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.4 mini API ID · copy exactly`gpt-5.4-mini` Fast responseLower published rate	custom	Chat CompletionsOpenAI-compatible	Input $0.90 Output $5.40	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.5 API ID · copy exactly`gpt-5.5`	custom	Chat CompletionsOpenAI-compatible	Input $6.00 Output $36.00	Context Limit unavailable Max output 65,536 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.6 Sol API ID · copy exactly`gpt-5.6-sol` Long context	custom	Chat CompletionsOpenAI-compatible	Input $6.00 Output $36.00	Context 1,050,000 Max output 128,000 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC
Display name GPT-5.6 Terra API ID · copy exactly`gpt-5.6-terra` Lower published rateLong context	custom	Chat CompletionsOpenAI-compatible	Input $2.40 Output $14.40	Context 1,050,000 Max output 128,000 Input Input types unavailable Output Output types unavailable	No additional capabilities declared	No separate long-context rate published	RefreshedAug 15 2026, 16:06 UTC

Display name

Claude Haiku 4.5

API ID · copy exactlyclaude-haiku-4-5-20251001

Fast responseLower published rate

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $1.20
Output: $6.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Claude Opus 4.6

API ID · copy exactlyclaude-opus-4-6

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $30.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Claude Opus 4.7

API ID · copy exactlyclaude-opus-4-7

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $30.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Claude Opus 4.8

API ID · copy exactlyclaude-opus-4-8

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $30.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Claude Opus 5

API ID · copy exactlyclaude-opus-5

Long context

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: 1,000,000
Max output: 128,000
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $30.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Claude Sonnet 5

API ID · copy exactlyclaude-sonnet-5

Lower published rate

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $2.40
Output: $12.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Fable 5

API ID · copy exactlyfable-5

Long context

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $12.00
Output: $60.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Fable 5 Ultra

API ID · copy exactlyfable-5-ultra

Long context

Active route: Anthropic
API surface: Chat Completions + Messages
Input: Input types unavailable
Output: Output types unavailable
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $12.00
Output: $60.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

Codex Auto Review

API ID · copy exactlycodex-auto-review

Build & code

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 4,096
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $36.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.3 Codex

API ID · copy exactlygpt-5.3-codex

Build & code

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $2.10
Output: $16.80

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.4

API ID · copy exactlygpt-5.4

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $3.00
Output: $18.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.4 mini

API ID · copy exactlygpt-5.4-mini

Fast responseLower published rate

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $0.90
Output: $5.40

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.5

API ID · copy exactlygpt-5.5

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: Limit unavailable
Max output: 65,536
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $36.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.6 Sol

API ID · copy exactlygpt-5.6-sol

Long context

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $6.00
Output: $36.00

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published

Display name

GPT-5.6 Terra

API ID · copy exactlygpt-5.6-terra

Lower published rateLong context

Active route: custom
API surface: Chat Completions
Input: Input types unavailable
Output: Output types unavailable
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Aug 15 2026, 16:06 UTC

Standard price / 1M tokens

Input: $2.40
Output: $14.40

Catalog-declared features

No additional capabilities declared

Long-context pricing

No separate long-context rate published