Gemini Argon family
New
- Input
- $2.31
- Output
- $11.55
- Cached
- $0.115595% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 33K
StandardNo training · ZDR by defaultView model
46 models · 12 providers · live list prices
Every model we sell, priced in the open
Concrete model ids, list prices per million tokens, context limits, and data posture. Search it, filter it, or switch to the comparison table — then open a model for its full specification and copy-ready request samples.
Models listed46live in the public catalog
Providers12one Responses contract
Cheapest input$0.0462 / Minception/mercury-2.5
Largest context1.05Mtokens per request
Anthropic
Claude Haiku family
New
Claude Haiku 5.5
anthropic/claude-haiku-5.5- Input
- $0.5775
- Output
- $2.888
- Cached
- $0.0577590% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 128K
StandardNo training · no ZDRView model
Gemini Nano Banana family
New
Nano Banana 2.1
google/gemini-nano-banana-2.1- Input
- $1.50
- Output
- $7.50
- Cached
- $0.1590% off input
USD per million tokens · list prices
- Context window
- 66K
- Max output
- 59K
StandardNo training · no ZDRView model
OpenAI
GPT Sol Pro family
New
GPT-6.1 Sol Pro
openai/gpt-6.1-sol-pro- Input
- $4.62
- Output
- $17.325
- Cached
- $0.23195% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · ZDR by defaultView model
OpenAI
GPT Sol family
New
GPT-6.1 Sol
openai/gpt-6.1-sol- Input
- $4.40
- Output
- $16.50
- Cached
- $0.2295% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
Anthropic
Claude Sonnet family
New
Claude Sonnet 5.5
anthropic/claude-sonnet-5.5- Input
- $2.31
- Output
- $11.55
- Cached
- $0.115595% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 128K
StandardNo training · no ZDRView model
OpenAI
GPT Luna Pro family
New
GPT-6 Luna Pro
openai/gpt-6-luna-pro- Input
- $0.231
- Output
- $0.8662
- Cached
- $0.023190% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · ZDR by defaultView model
OpenAI
GPT Luna family
New
GPT-6 Luna
openai/gpt-6-luna- Input
- $0.22
- Output
- $0.825
- Cached
- $0.02290% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
Anthropic
Claude Opus family
New
Claude Opus 5.5
anthropic/claude-opus-5.5- Input
- $4.62
- Output
- $23.10
- Cached
- $0.23195% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 128K
StandardNo training · no ZDRView model
Xiaomi MiMo
Mimo Flash family
New
MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash- Input
- $0.14
- Output
- $0.28
- Cached
- $0.002898% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
Xiaomi MiMo
Mimo Pro family
New
MiMo-V2.6-Pro
xiaomi/mimo-v2.6-pro- Input
- $0.435
- Output
- $0.87
- Cached
- $0.003699% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
Xiaomi MiMo
Mimo Pro Ultraspeed family
New
MiMo-V2.6-Pro-UltraSpeed
xiaomi/mimo-v2.6-pro-ultraspeed- Input
- $4.35
- Output
- $8.70
- Cached
- $0.03699% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
xAI
Grok family
New
Grok 4.7
x-ai/grok-4.7- Input
- $4.00
- Output
- $12.00
- Cached
- $1.0075% off input
USD per million tokens · list prices
- Context window
- 500K
- Max output
- 500K
StandardNo training · no ZDRView model
Z.ai
GLM Flashx family
New
GLM-5.3-FlashX
z-ai/glm-5.3-flashx- Input
- $0.4274
- Output
- $1.444
- Cached
- $0.10476% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 131K
StandardNo training · no ZDRView model
DeepSeek
Flash family
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash- Input
- $0.3
- Output
- $1.20
- Cached
- $0.0207993% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 944K
StandardNo training · no ZDRView model
Inception
Mercury family
- Input
- $0.0462
- Output
- $0.1732
- Cached
- $0.0046290% off input
USD per million tokens · list prices
- Context window
- 260K
- Max output
- 66K
StandardNo training · ZDR by defaultView model
OpenAI
GPT Astra family
GPT-6 Astra
openai/gpt-6-astra- Input
- $22.00
- Output
- $82.50
- Cached
- $2.2090% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
OpenAI
GPT Astra Pro family
GPT-6 Astra Pro
openai/gpt-6-astra-pro- Input
- $23.10
- Output
- $86.625
- Cached
- $2.3190% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · ZDR by defaultView model
Qwen
Max family
Qwen3.8 Max
qwen/qwen3.8-max- Input
- $2.00
- Output
- $6.00
- Cached
- $0.2588% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 131K
StandardNo training · no ZDRView model
Meta
Muse Spark family
Muse Spark 1.3
meta/muse-spark-1.3- Input
- $1.444
- Output
- $4.909
- Cached
- $0.173288% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
Gemini Flash family
Gemini 3.8 Flash
google/gemini-3.8-flash- Input
- $0.75
- Output
- $3.75
- Cached
- $0.07590% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 66K
StandardNo training · no ZDRView model
Anthropic
Claude Fable family
Claude Fable 5.1
anthropic/claude-fable-5.1- Input
- $10.00
- Output
- $50.00
- Cached
- $0.2598% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 128K
StandardNo training · no ZDRView model
Qwen
Flash family
Qwen3.8 Flash
qwen/qwen3.8-flash- Input
- $0.165
- Output
- $0.517
- Cached
- $0.017689% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 131K
StandardNo training · no ZDRView model
Z.ai
GLM Flash family
GLM-5.3-Flash
z-ai/glm-5.3-flash- Input
- $0.15
- Output
- $0.5
- Cached
- $0.0346577% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
Qwen
27B family
Qwen3.8 27B
qwen/qwen3.8-27b- Input
- $0.425
- Output
- $2.55
- Cached
- $0.08580% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 236K
StandardNo training · ZDR by defaultView model
Z.ai
GLM family
GLM-5.3
z-ai/glm-5.3- Input
- $1.40
- Output
- $4.40
- Cached
- $0.2681% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · no ZDRView model
Qwen
2.4t A95b family
Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b- Input
- $2.31
- Output
- $6.93
- Cached
- $0.288888% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 131K
StandardNo training · ZDR by defaultView model
DeepSeek
Pro family
DeepSeek V4 Pro
deepseek/deepseek-v4-pro- Input
- $1.206
- Output
- $2.412
- Cached
- $0.241280% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 393K
StandardNo training · no ZDRView model
Meta
Muse Glimmer 30B family
Muse Glimmer 30B
meta/muse-glimmer-30b- Input
- $0.3465
- Output
- $1.386
- Cached
- $0.046287% off input
USD per million tokens · list prices
- Context window
- 131K
- Max output
- 16K
StandardNo training · ZDR by defaultView model
Gemini Flash Lite family
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite- Input
- $0.3
- Output
- $2.50
- Cached
- $0.0390% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 66K
StandardNo training · no ZDRView model
Moonshot AI
Kimi family
Kimi K3
moonshotai/kimi-k3- Input
- $3.00
- Output
- $15.00
- Cached
- $0.390% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 1.05M
StandardNo training · no ZDRView model
OpenAI
GPT Terra Pro family
GPT-5.6 Terra Pro
openai/gpt-5.6-terra-pro- Input
- $4.62
- Output
- $20.79
- Cached
- $0.46290% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · ZDR by defaultView model
OpenAI
GPT Terra family
GPT-5.6 Terra
openai/gpt-5.6-terra- Input
- $4.40
- Output
- $19.80
- Cached
- $0.4490% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
Gemini Flash Lite family
Nano Banana 2 Lite
google/gemini-3.1-flash-lite-image- Input
- $0.2888
- Output
- $30.00
- Cached
- $0.0288890% off input
USD per million tokens · list prices
- Context window
- 66K
- Max output
- 4K
StandardNo training · no ZDRView model
Moonshot AI
Kimi family
Kimi K2.7 Code
moonshotai/kimi-k2.7-code- Input
- $0.95
- Output
- $4.00
- Cached
- $0.207978% off input
USD per million tokens · list prices
- Context window
- 262K
- Max output
- 262K
StandardNo training · no ZDRView model
Qwen
Plus family
Qwen3.7 Plus
qwen/qwen3.7-plus- Input
- $1.20
- Output
- $4.80
- Cached
- $0.1290% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 131K
StandardNo training · no ZDRView model
MiniMax
Minimax family
MiniMax-M3
minimax/minimax-m3- Input
- $0.6
- Output
- $2.40
- Cached
- $0.1280% off input
USD per million tokens · list prices
- Context window
- 1.0M
- Max output
- 512K
StandardNo training · no ZDRView model
Gemini Pro family
Nano Banana Pro
google/gemini-3-pro-image- Input
- $2.31
- Output
- $120.00
- Cached
- $0.23190% off input
USD per million tokens · list prices
- Context window
- 66K
- Max output
- 33K
StandardNo training · ZDR by defaultView model
Gemini Flash family
Nano Banana 2
google/gemini-3.1-flash-image- Input
- $0.5775
- Output
- $60.00
- Cached
- $0.0577590% off input
USD per million tokens · list prices
- Context window
- 131K
- Max output
- 33K
StandardNo training · ZDR by defaultView model
Qwen
35B A3b family
Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b- Input
- $0.248
- Output
- $1.485
- Cached
- $0.0577577% off input
USD per million tokens · list prices
- Context window
- 262K
- Max output
- 66K
StandardNo training · no ZDRView model
OpenAI
GPT family
GPT-5.5
openai/gpt-5.5- Input
- $11.00
- Output
- $49.50
- Cached
- $1.1090% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
OpenAI
GPT Pro family
GPT-5.5 Pro
openai/gpt-5.5-pro- Input
- $66.00
- Output
- $297.00
- Cached
- $6.6090% off input
USD per million tokens · list prices
- Context window
- 1.05M
- Max output
- 128K
StandardNo training · no ZDRView model
OpenAI
GPT Image 2 family
GPT-5.4 Image 2
openai/gpt-5.4-image-2- Input
- $8.00
- Output
- $15.00
- Cached
- $2.0075% off input
USD per million tokens · list prices
- Context window
- 272K
- Max output
- 128K
StandardNo training · no ZDRView model
xAI
Grok Build family
Grok Build 0.1
x-ai/grok-build-0.1- Input
- $2.31
- Output
- $4.62
- Cached
- $0.46280% off input
USD per million tokens · list prices
- Context window
- 256K
- Max output
- 256K
StandardNo training · no ZDRView model
OpenAI
GPT Audio family
GPT Audio
openai/gpt-audio- Input
- $2.50
- Output
- $10.00
- Cached
- $0.2590% off input
USD per million tokens · list prices
- Context window
- 128K
- Max output
- 16K
StandardNo training · no ZDRView model
OpenAI
GPT Audio Mini family
GPT Audio Mini
openai/gpt-audio-mini- Input
- $0.6
- Output
- $2.40
- Cached
- $0.0690% off input
USD per million tokens · list prices
- Context window
- 128K
- Max output
- 16K
StandardNo training · no ZDRView model
How to read the prices
Every price is our list price in USD per million tokens, published by the same catalog API that serves this page. Cached input reads are billed at the cached price when a prefix is reused. Rate sheet
How to read the limits
Context window and max output are the published token limits for each model id. A limit the catalog does not publish is labelled “Not published” rather than guessed. Models and pricing
How to read the data posture
The label describes default routing: requests go to Zero Data Retention routes unless you opt in with x-sylphx-zdr: optional. Standard models do not train on what you send; consent-trained models may. Both come straight from the catalog row, so a compliance answer stays per model. Privacy