Model Pricing

Built-in pricing tables used by AgentKavach to calculate spend. Prices are per 1,000 tokens.

OpenAI Models #

Model	Input ($/1K tokens)	Output ($/1K tokens)	Aliases
`gpt-4o`	$0.0025	$0.0100	—
`gpt-4o-mini`	$0.00015	$0.0006	—
`gpt-4-turbo`	$0.0100	$0.0300	—
`gpt-4`	$0.0300	$0.0600	—
`gpt-3.5-turbo`	$0.0005	$0.0015	—
`o1`	$0.0150	$0.0600	—
`o1-mini`	$0.0030	$0.0120	—
`o3-mini`	$0.0011	$0.0044	—
`o3`	$0.0100	$0.0400	`o3-reasoning`
`o4-mini`	$0.0011	$0.0044	—
`gpt-4.1`	$0.0020	$0.0080	—
`gpt-4.1-mini`	$0.0004	$0.0016	—
`gpt-4.1-nano`	$0.0001	$0.0004	—
`gpt-4.5-preview`	$0.0750	$0.1500	`gpt-4.5`
`codex-mini`	$0.0015	$0.0060	`codex`

Model	Input ($/1K tokens)	Output ($/1K tokens)	Aliases
`claude-opus-4-0`	$0.0150	$0.0750	—
`claude-opus-4-6`	$0.0150	$0.0750	`claude-opus`
`claude-sonnet-4-0`	$0.0030	$0.0150	—
`claude-sonnet-4-6`	$0.0030	$0.0150	`claude-sonnet`
`claude-3-5-sonnet-20241022`	$0.0030	$0.0150	`claude-3.5-sonnet`
`claude-3-5-haiku-20241022`	$0.0008	$0.0040	`claude-3.5-haiku`
`claude-3-opus-20240229`	$0.0150	$0.0750	`claude-3-opus`
`claude-3-haiku-20240307`	$0.00025	$0.00125	`claude-3-haiku`
`claude-haiku-4-5`	$0.0008	$0.0040	`claude-haiku`

Model	Input ($/1K tokens)	Output ($/1K tokens)	Aliases
`gemini-2.0-flash`	$0.0001	$0.0004	—
`gemini-1.5-pro`	$0.00125	$0.0050	—
`gemini-1.5-flash`	$0.000075	$0.0003	—
`gemini-2.5-pro`	$0.00125	$0.0100	`gemini-pro`
`gemini-2.5-flash`	$0.00015	$0.0035	`gemini-flash`

Model	Input ($/1K tokens)	Output ($/1K tokens)	Aliases
`mistral-large-latest`	$0.0020	$0.0060	`mistral-large`
`mistral-small-latest`	$0.0001	$0.0003	`mistral-small`
`codestral-latest`	$0.0003	$0.0009	`codestral`
`pixtral-large-latest`	$0.0020	$0.0060	`pixtral-large`
`ministral-8b-latest`	$0.0001	$0.0001	`ministral-8b`
`mistral-embed`	$0.0001	$0.0001	—

Prices sourced as of April 2026. Updated manually from provider documentation: OpenAI, Anthropic, Google, Mistral.

ℹ️ Fetch pricing via API

You can also fetch current pricing via the API: GET /v1/pricing