Available Models

72 models across 12 providers, plus 9 smart-routing aliases. Live pricing at api.jarvisclaw.ai/pricing.

Query the live list

GET /v1/models is authoritative. The tables below are a snapshot and models are added and retired regularly.

Smart Routing

Route	Description
auto	Best overall model (balances quality/cost/speed)
auto/premium	Highest quality available
auto/eco	Cheapest capable model
auto/free	Free models only (Nvidia hosted)
auto/image	Best image generation model
auto/video	Best video generation model
auto/tts	Best text-to-speech model
auto/music	Best music generation model
auto/search	Web search with citations

Free Models (Nvidia Hosted)

Unlimited usage, no cost.

Model	Context	Tags
nvidia/qwen3.5-122b-a10b	131K	chat, reasoning, coding
nvidia/qwen3-next-80b-a3b-instruct	262K	chat, reasoning, coding
nvidia/step-3.7-flash	131K	chat, reasoning
nvidia/nemotron-nano-12b-v2-vl	131K	chat, reasoning, vision
nvidia/seed-oss-36b	131K	chat, coding
nvidia/mistral-large-3-675b	131K	chat, reasoning, coding
nvidia/llama-4-maverick	131K	chat, reasoning, coding
nvidia/nemotron-nano-9b-v2	131K	chat, reasoning
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	256K	chat, reasoning, vision
nvidia/mistral-nemotron	131K	chat, coding

Chat & Reasoning Models

Pricing uses a ratio system. Input price is ratio × $2 per 1M tokens. Output price is input price × completion ratio, where the completion ratio is per-model — it ranges from 2× to roughly 8.3× and is not a flat 3×. Both figures come back from api.jarvisclaw.ai/pricing.

Model	Context	Ratio	Completion	Tags
openai/gpt-5.5	1050K	2.5	6×	chat, reasoning, coding, vision
openai/gpt-5.4-pro	1050K	15	6×	chat, reasoning, coding, vision
openai/gpt-5.4	1050K	1.25	6×	chat, reasoning, coding, vision
openai/gpt-5.4-mini	400K	0.375	6×	chat, coding, vision
openai/gpt-5.4-nano	1050K	0.1	6.25×	chat
openai/gpt-5.3-codex	400K	0.875	8×	coding, reasoning, chat
openai/gpt-5.3	128K	0.875	8×	chat, reasoning, coding, vision
openai/gpt-5.2-pro	400K	10.5	8×	chat, reasoning, coding, vision
openai/gpt-5.2	400K	0.875	8×	chat, reasoning, coding, vision
openai/gpt-5-mini	200K	0.125	8×	chat, coding
openai/gpt-4.1	128K	1	4×	chat, coding, vision
openai/gpt-4.1-mini	128K	0.2	4×	chat, coding
openai/gpt-4.1-nano	128K	0.05	4×	chat
openai/gpt-4o	128K	1.25	4×	chat, coding, vision
openai/gpt-4o-mini	128K	0.075	4×	chat, coding
openai/o3	200K	1	4×	chat, reasoning, coding
openai/o3-mini	128K	0.55	4×	chat, reasoning, coding
openai/o1	200K	7.5	4×	chat, reasoning, coding
openai/o4-mini	128K	0.55	4×	reasoning, coding
anthropic/claude-opus-4.8	1000K	2.5	5×	chat, coding, reasoning, vision
anthropic/claude-opus-4.7	1000K	2.5	5×	chat, coding, reasoning, vision
anthropic/claude-opus-4.5	200K	2.5	5×	chat, coding, reasoning, vision
anthropic/claude-sonnet-4.6	200K	1.5	5×	chat, coding, reasoning
anthropic/claude-sonnet-4.5	200K	1.5	5×	chat, coding, reasoning, vision
anthropic/claude-haiku-4.5	200K	0.5	5×	chat, coding
google/gemini-3.5-flash	1048K	0.25	6×	chat, reasoning, coding, vision
google/gemini-3.1-pro	1048K	1	6×	chat, reasoning, coding, vision
google/gemini-3.1-flash-lite	1048K	0.125	6×	chat, reasoning
google/gemini-3-flash-preview	1048K	0.25	6×	chat, reasoning, coding, vision
google/gemini-2.5-pro	1048K	0.625	8×	chat, reasoning, coding, vision
google/gemini-2.5-flash	1048K	0.15	8.33×	chat, coding, vision
google/gemini-2.5-flash-lite	1048K	0.05	4×	chat
deepseek/deepseek-chat	1048K	0.1	2×	chat, coding
deepseek/deepseek-reasoner	1048K	0.1	2×	chat, reasoning, coding
deepseek/deepseek-v4-pro	1048K	0.2175	2×	chat, reasoning, coding
xai/grok-4.3	1000K	0.75	2.67×	reasoning, coding, vision, chat
xai/grok-build-0.1	256K	0.75	2×	coding, chat
moonshot/kimi-k2.7	262K	0.475	4.21×	chat, reasoning, coding, vision
minimax/minimax-m3	1048K	0.15	4×	chat, reasoning, coding
minimax/minimax-m2.7	204K	0.15	4×	chat, reasoning, coding
zai/glm-5.2	1000K	0.7	3.14×	chat, reasoning, coding
zai/glm-5.1	200K	0.7	3.14×	chat, reasoning, coding
zai/glm-5	200K	0.3	3.2×	chat, reasoning, coding
zai/glm-5-turbo	200K	0.6	3.33×	chat, reasoning

Image Generation Models

Flat per-image pricing at the default 1024×1024. Larger sizes cost more — see Image Generation for the per-size table.

Model	Price/image	Notes
openai/gpt-image-1	$0.021	Standard quality
openai/gpt-image-2	$0.063	Higher quality
google/nano-banana	$0.053	Artistic generation
google/nano-banana-pro	$0.105	Premium quality
zai/cogview-4	$0.015	Budget option
xai/grok-imagine-image	$0.021	xAI generation
xai/grok-imagine-image-pro	$0.074	xAI premium

Video Generation Models

Video is priced per second, not per clip

Multiply by your requested duration. A 5-second seedance-2.0 clip at 720p costs 5 × $0.227 ≈ $1.14, not $0.227. Higher resolutions cost more again — see Video Generation for the resolution multipliers.

Model	Price/second	Notes
bytedance/seedance-2.5	$0.315	Newest generation, up to 30s, no RealFace
bytedance/seedance-2.0	$0.227	Up to 4K, supports RealFace
bytedance/seedance-2.0-fast	$0.165	Fast generation, supports RealFace
bytedance/seedance-1.5-pro	$0.070	Image-to-video only
azure/sora-2	$0.10	720p + audio, 4/8/12s durations only
xai/grok-imagine-video	$0.05	xAI video

Audio Models

TTS is billed per 1,000 characters of input.

Model	Type	Price	Notes
elevenlabs/flash-v2.5	TTS	$0.05/1k chars	Fast speech synthesis (~75ms latency)
elevenlabs/turbo-v2.5	TTS	$0.05/1k chars	Balanced quality and latency
elevenlabs/multilingual-v2	TTS	$0.12/1k chars	Multi-language support
elevenlabs/v3	TTS	$0.12/1k chars	Highest quality
elevenlabs/sound-effects	SFX	$0.12/1k chars	Sound effect generation
minimax/music-2.5+	Music	$0.1575/track	Up to ~3 min

Providers

ID	Provider	Models
1	OpenAI	21
2	Anthropic	6
3	Google	9
4	DeepSeek	3
5	Moonshot	1
6	ZAI (智谱)	5
7	xAI	5
8	MiniMax	3
9	Nvidia	10 (all free)
10	ElevenLabs	5
11	ByteDance	3
12	Azure	1

Prices shown are reference rates

The settled amount for a given call can differ slightly. Every response carries a price object with the exact amount charged — read that rather than this table.

Full pricing details and live availability at api.jarvisclaw.ai/pricing.