Models

The models available through SERV, with pricing and context windows.

These are the models available through SERV. Use any model ID below with the SERV endpoint and your OpenAI or Anthropic SDK, or try them in the Playground.

Prices are per million tokens and include SERV Reasoning.

OpenAI

Model	API ID	Input	Output	Context
GPT 6 Astra	gpt-6-astra	$12.00	$60.00	1M
GPT-5.4	gpt-5.4	$3.25	$20.00	1M
GPT-5.4 Mini	gpt-5.4-mini	$1.00	$6.00	400K
GPT-5.4 Nano	gpt-5.4-nano	$0.250	$1.60	128K
GPT-5.5	gpt-5.5	$6.50	$39.00	1M
GPT-5.6 Luna	gpt-5.6-luna	$0.250	$1.50	1M
GPT-5.6 Sol	gpt-5.6-sol	$5.25	$25.00	1M
GPT-5.6 Terra	gpt-5.6-terra	$2.50	$15.00	1M
GPT-6-Luna	gpt-6-luna	$0.130	$0.650	1M
GPT-6-Sol	gpt-6-sol	$2.60	$13.00	1M

Anthropic

Model	API ID	Input	Output	Context
Claude Fable 5	claude-fable-5	$13.00	$65.00	1M
Claude Fable 5.1	claude-fable-5-1	$12.00	$60.00	1M
Claude Haiku 4.5	claude-haiku-4.5	$1.25	$6.50	200K
Claude Opus 4.6	claude-opus-4.6	$6.50	$32.50	200K
Claude Opus 4.7	claude-opus-4.7	$6.50	$32.50	1M
Claude Opus 4.8	claude-opus-4.8	$6.50	$32.50	1M
Claude Opus 5	claude-opus-5	$6.00	$30.00	1M
Claude Sonnet 4.6	claude-sonnet-4.6	$4.00	$20.00	200K
Claude Sonnet 5	claude-sonnet-5	$2.60	$13.00	1M
Claude Sonnet 5.5	claude-sonnet-5.5	$2.40	$12.00	1M

Google

Model	API ID	Input	Output	Context
Gemini 2.5 Flash	gemini-2.5-flash	$0.400	$3.50	1M
Gemini 3 Flash Preview	gemini-3-flash-preview	$0.600	$4.00	1M
Gemini 3.1 Flash Lite	gemini-3.1-flash-lite	$0.300	$1.80	1M
Gemini 3.1 Pro Preview	gemini-3.1-pro-preview	$2.50	$16.00	1M
Gemini 3.5 Flash	gemini-3.5-flash	$1.95	$12.00	1M
Gemini 3.5 Flash Lite	gemini-3.5-flash-lite	$0.400	$3.00	1M
Gemini 3.6 Flash	gemini-3.6-flash	$1.00	$4.50	1M
Gemini 3.7 Flash	gemini-3.7-flash	$1.00	$4.50	1M
Gemini 3.8 Flash	gemini-3.8-flash	$1.00	$4.50	1M

See also

• Quickstart — make your first request.
• SDK Integration — endpoints and parameter mapping.
• Endpoint compatibility — which models work on which endpoint.