MODEL DIRECTORY

LLM models & pricing

Choose LLMs by native protocol, context and input/output pricing. Inspect declared capabilities and API examples.

26 models

Model
GPT-6 AstraOpenAI	Input$2.00Output$10.00per 1M tokens	80% OFF	— / $0.20per 1M tokens	Model details API ID gpt-6-astra Context 1.05M Cache write / read — / $0.20 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Fable 5.1Anthropic	Input$3.00Output$15.00per 1M tokens	70% OFF	$3.75 / $0.075per 1M tokens	Model details API ID claude-fable-5-1 Context 1M Cache write / read $3.75 / $0.075 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Opus 5Anthropic	Input$1.50Output$7.50per 1M tokens	70% OFF	$1.875 / $0.15per 1M tokens	Model details API ID claude-opus-5 Context 1M Cache write / read $1.875 / $0.15 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
GPT-5.6 SolOpenAI	Input$0.50Output$3.00per 1M tokens	90% OFF	— / $0.05per 1M tokens	Model details API ID gpt-5.6-sol Context 1.05M Cache write / read — / $0.05 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
GPT-5.6 TerraOpenAI	Input$0.20Output$1.20per 1M tokens	92% OFF	— / $0.02per 1M tokens	Model details API ID gpt-5.6-terra Context 1.05M Cache write / read — / $0.02 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Fable 5Anthropic	Input$3.00Output$15.00per 1M tokens	70% OFF	$3.75 / $0.30per 1M tokens	Model details API ID claude-fable-5 Context 1M Cache write / read $3.75 / $0.30 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Opus 4.8Anthropic	Input$1.50Output$7.50per 1M tokens	70% OFF	$1.875 / $0.15per 1M tokens	Model details API ID claude-opus-4-8 Context 1M Cache write / read $1.875 / $0.15 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
GPT-5.5OpenAI	Input$0.50Output$3.00per 1M tokens	90% OFF	— / $0.05per 1M tokens	Model details API ID gpt-5.5 Context 1.05M Cache write / read — / $0.05 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Opus 4.7Anthropic	Input$1.50Output$7.50per 1M tokens	70% OFF	$1.875 / $0.15per 1M tokens	Model details API ID claude-opus-4-7 Context 1M Cache write / read $1.875 / $0.15 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
Claude Opus 4.6Anthropic	Input$1.50Output$7.50per 1M tokens	70% OFF	$1.875 / $0.15per 1M tokens	Model details API ID claude-opus-4-6 Context 1M Cache write / read $1.875 / $0.15 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
claude-opus-4-5-20251101Anthropic	Input$1.50Output$7.50per 1M tokens	70% OFF	$1.875 / $0.15per 1M tokens	Model details API ID claude-opus-4-5-20251101 Context 128K Cache write / read $1.875 / $0.15 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
claude-sonnet-4-6Anthropic	Input$0.90Output$4.50per 1M tokens	70% OFF	$1.125 / $0.09per 1M tokens	Model details API ID claude-sonnet-4-6 Context 200K Cache write / read $1.125 / $0.09 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
claude-sonnet-5Anthropic	Input$0.60Output$3.00per 1M tokens	70% OFF	$0.75 / $0.06per 1M tokens	Model details API ID claude-sonnet-5 Context 128K Cache write / read $0.75 / $0.06 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-2.5-flashGoogle	Input$0.075Output$0.625per 1M tokens	75% OFF	— / $0.0075per 1M tokens	Model details API ID gemini-2.5-flash Context 128K Cache write / read — / $0.0075 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-2.5-flash LiteGoogle	Input$0.025Output$0.10per 1M tokens	75% OFF	— / $0.0025per 1M tokens	Model details API ID gemini-2.5-flash-lite Context 128K Cache write / read — / $0.0025 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3-flashGoogle	Input$0.125Output$0.75per 1M tokens	75% OFF	— / $0.0125per 1M tokens	Model details API ID gemini-3-flash Context 128K Cache write / read — / $0.0125 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.1-flash LiteGoogle	Input$0.0625Output$0.375per 1M tokens	75% OFF	— / $0.00625per 1M tokens	Model details API ID gemini-3.1-flash-lite Context 128K Cache write / read — / $0.00625 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.5-flash-highGoogle	Input$0.375Output$2.25per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.5-flash-high Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.5-flash-lowGoogle	Input$0.375Output$2.25per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.5-flash-low Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.5-flash-mediumGoogle	Input$0.375Output$2.25per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.5-flash-medium Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.6-flash-highGoogle	Input$0.375Output$1.875per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.6-flash-high Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.6-flash-lowGoogle	Input$0.375Output$1.875per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.6-flash-low Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.6-flash-mediumGoogle	Input$0.375Output$1.875per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.6-flash-medium Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gemini-3.6-flash-tieredGoogle	Input$0.375Output$1.875per 1M tokens	75% OFF	— / $0.0375per 1M tokens	Model details API ID gemini-3.6-flash-tiered Context 128K Cache write / read — / $0.0375 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gpt-5.3-codex-sparkOpenAI	Input$0.175Output$1.40per 1M tokens	90% OFF	— / $0.0175per 1M tokens	Model details API ID gpt-5.3-codex-spark Context 128K Cache write / read — / $0.0175 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.
gpt-5.4OpenAI	Input$0.25Output$1.50per 1M tokens	90% OFF	— / $0.025per 1M tokens	Model details API ID gpt-5.4 Context 1.05M Cache write / read — / $0.025 per 1M tokens Input → Output text → text Discount Based on equally weighted official standard input and output rates, excluding cache and other charges.

Choose and integrate

Native protocols in this catalog: openai · claude · gemini. Choose a protocol that matches your app, then inspect the model’s declared capabilities.

Context and maximum output constrain request size and generated length separately. Check each model’s declarations for tools, streaming and structured output.

The table shows input and output prices per million tokens, with cache rates separately. Price sorting uses the public input starting rate; inspect the model page for all billing items.

Docs: native API protocols → · Docs: your first request →