Model catalog

103 AI models,one endpoint.

GPT, Claude, Gemini, DeepSeek, Qwen and more from 14 providers. Compare context windows and per-token prices, then copy a model ID into the SDK you already use.

Get your API keyView plans

free to call, no card: 45
model providers: 14
tokens of context, max: 1.05M
lowest input price per 1M tokens: $0.05

/

103 models

From these prices, when you use your whole allowance

OpenAI

8 models · from $0.1

OpenAI models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
GPT-6.1 SolUp to −96%Vision · Reasoning · Tool use	1.05M	$0.067$2	$0.34~~$10~~	$0.0034
GPT-6.1 TerraUp to −96%Vision · Reasoning · Tool use	1.05M	$0.034$1	$0.17$5	$0.0017
GPT-6 AstraUp to −96%Ultra and Power plansVision · Reasoning · Tool use	1.05M	$0.34~~$10~~	$1.70~~$50~~	$0.034
GPT-6 SolUp to −96%Vision · Reasoning · Tool use	1.05M	$0.067$2	$0.34~~$10~~	$0.0067
GPT-6 LunaUp to −96%Vision · Reasoning · Tool use	1.05M	$0.0034~~$0.1~~	$0.017~~$0.5~~	$0.0003
GPT-5.6 SolUp to −96%Vision · Reasoning · Tool use	1M	$0.067$2	$0.34~~$10~~	$0.0067
GPT-5.6 TerraUp to −96%Vision · Reasoning · Tool use	1M	$0.034$1	$0.2$6	$0.0042
GPT-5.6 LunaUp to −96%Vision · Reasoning · Tool use	1M	$0.0034~~$0.1~~	$0.02~~$0.6~~	$0.0017

Anthropic

15 models · from $0.1

Anthropic models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Fable 5.1Up to −96%Ultra and Power plansVision · Reasoning · Tool use	1M	$0.34~~$10~~	$1.70~~$50~~	$0.0084
Fable 5Up to −96%Vision · Reasoning · Tool use	1M	$0.34~~$10~~	$1.70~~$50~~	$0.034
Sonnet 5.5Up to −96%NewVision · Reasoning · Tool use	1M	$0.067$2	$0.34~~$10~~	$0.0034
Opus 5.5Up to −96%Vision · Reasoning · Tool use	1M	$0.14$4	$0.67~~$20~~	$0.0067
Opus 5Up to −96%Vision · Reasoning · Tool use	1M	$0.17$5	$0.84~~$25~~	$0.017
Sonnet 4.5Up to −96%Vision · Reasoning · Tool use	1M	$0.1$3	$0.5~~$15~~	$0.01
Opus 4.8Up to −96%Vision · Reasoning · Tool use	1M	$0.17$5	$0.84~~$25~~	$0.017
Haiku 5.5Up to −96%NewVision · Reasoning · Tool use	1M	$0.0034~~$0.1~~	$0.017~~$0.5~~	$0.0003
Sonnet 4Up to −96%Vision · Reasoning · Tool use	1M	$0.1$3	$0.5~~$15~~	$0.01
Opus 4.7Up to −96%Vision · Reasoning · Tool use	1M	$0.17$5	$0.84~~$25~~	$0.017
Opus 4.6Up to −96%Reasoning	1M	$0.17$5	$0.84~~$25~~	$0.017
Opus 4.5Up to −96%Vision · Reasoning · Tool use	200K	$0.17$5	$0.84~~$25~~	$0.017
Sonnet 5Up to −96%Vision · Reasoning · Tool use	1M	$0.067$2	$0.34~~$10~~	$0.0067
Sonnet 4.6Up to −96%Reasoning	1M	$0.1$3	$0.5~~$15~~	$0.01
Haiku 4.5Up to −96%Reasoning	200K	$0.034$1	$0.17$5	$0.0034

Google

8 models · from $0.3

Google models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Gemini 3.8 FlashUp to −96%Paid accountsVision · Video input · Reasoning · Tool use	1M	$0.025~~$0.75~~	$0.13~~$3.75~~	$0.0025
Gemini 3.7 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.025~~$0.75~~	$0.13~~$3.75~~	$0.0025
Gemini 3.5 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.05~~$1.50~~	$0.3$9	$0.005
Gemini 3.6 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.025~~$0.75~~	$0.13~~$3.75~~	$0.0025
Gemini 3.1 ProUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.067$2	$0.4~~$12~~	$0.0067
Gemini 3 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.025~~$0.75~~	$0.13~~$3.75~~	$0.0025
Gemini 2.5 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.01~~$0.3~~	$0.084~~$2.50~~	$0.001
Gemini 2.5 ProUp to −96%Vision · Video input · Reasoning · Tool use	1M	$0.042~~$1.25~~	$0.34~~$10~~	$0.0042

DeepSeek

3 models · from $0.075

DeepSeek models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
DeepSeek V4.1 Flash−50%Pay as you goVision · Reasoning · Tool use	1.05M	$0.075~~$0.15~~	$0.3~~$0.6~~	$0.0015
DeepSeek V4 Pro 0813−35%Pay as you goReasoning · Tool use	1.05M	$0.2828~~$0.435~~	$0.5655~~$0.87~~	$0.0023
DeepSeek V4 Flash 0731−35%Pay as you goReasoning · Tool use	1.05M	$0.091~~$0.14~~	$0.182~~$0.28~~	$0.0182

Qwen

19 models · all free

Qwen models, with prices per 1M tokens
Model	Context	Input / 1M	Cache read / 1M
Qwen3.8 Omni Flash (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.8 Max (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.7 Max (Free)Reasoning · Tool use	1M	Free	—
Qwen3.7 Plus (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.7 Flash (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.6 Plus (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.6 Max Preview (Free)Reasoning · Tool use	262K	Free	—
Qwen3.6 27B (Free)Vision · Video input · Reasoning · Tool use	262K	Free	—
Qwen3.5 Plus (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.5 Omni Plus (Free)Vision · Video input · Tool use	262K	Free	—
Qwen3.6 35B A3B (Free)Vision · Video input · Reasoning · Tool use	262K	Free	—
Qwen3.5 Flash (Free)Vision · Video input · Reasoning · Tool use	1M	Free	—
Qwen3.5 397B A17B (Free)Vision · Video input · Reasoning · Tool use	262K	Free	—
Qwen3.5 Omni Flash (Free)Vision · Video input · Tool use	262K	Free	—
Qwen3 Max (Free)Vision · Video input · Reasoning · Tool use	262K	Free	—
Qwen Plus 0728 (Free)Vision · Video input · Reasoning · Tool use	131K	Free	—
Qwen3 Coder Plus (Free)Vision · Video input · Reasoning · Tool use	1.05M	Free	—
Qwen3 VL Plus (Free)Vision · Video input · Reasoning · Tool use	262K	Free	—
Qwen3 Omni Flash (Free)Vision · Video input · Tool use	262K	Free	—

Grok

3 models · from $2

Grok models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Grok 4.7Up to −96%Vision · Reasoning · Tool use	500K	$0.067$2	$0.2$6	$0.017
Grok 4.6Up to −96%Paid accountsVision · Reasoning · Tool use	500K	$0.067$2	$0.2$6	$0.017
Grok 4.5Up to −96%Vision · Reasoning · Tool use	500K	$0.067$2	$0.2$6	$0.01

Kimi

2 models · from $1

Kimi models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Kimi K3 AgentUp to −96%Paid accountsVision · Reasoning · Tool use	262K	$0.1$3	$0.5~~$15~~	$0.01
Kimi K2.8 Preview AgentUp to −96%Paid accountsVision · Reasoning · Tool use	262K	$0.034$1	$0.14$4	$0.0054

Mistral

9 models · from $0.68 · 8 free

Mistral models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Mistral Large 4Up to −96%Reasoning	256K	$0.023~~$0.68~~	$0.07~~$2.09~~	$0.0024
Mistral Large 3Vision · Tool use	256K	Free		—
Mistral Medium 3.5Vision · Reasoning · Tool use	256K	Free		—
Mistral Small 4Vision · Reasoning · Tool use	256K	Free		—
CodestralTool use	256K	Free		—
Devstral 2Tool use	256K	Free		—
Ministral 3 14BVision · Tool use	256K	Free		—
Ministral 3 8BVision · Tool use	256K	Free		—
Ministral 3 3BVision · Tool use	128K	Free		—

MiniMax

9 models · from $0.15

MiniMax models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
MiniMax M3.1 FlashUp to −96%NewVision · Video input · Reasoning · Tool use	1M	$0.005~~$0.15~~	$0.02~~$0.6~~	$0.0005
MiniMax M3Up to −96%Vision · Video input · Reasoning · Tool use	1M	$0.01~~$0.3~~	$0.04~~$1.20~~	$0.002
MiniMax M2.7Up to −96%Reasoning · Tool use	205K	$0.01~~$0.3~~	$0.04~~$1.20~~	$0.002
MiniMax M2.7 HighspeedUp to −96%Reasoning · Tool use	205K	$0.02~~$0.6~~	$0.08~~$2.40~~	$0.002
MiniMax M2.5Up to −96%Reasoning · Tool use	205K	$0.01~~$0.3~~	$0.04~~$1.20~~	$0.001
MiniMax M2.5 HighspeedUp to −96%Reasoning · Tool use	205K	$0.02~~$0.6~~	$0.08~~$2.40~~	$0.001
MiniMax M2.1Up to −96%Reasoning · Tool use	205K	$0.01~~$0.3~~	$0.04~~$1.20~~	$0.001
MiniMax M2.1 HighspeedUp to −96%Reasoning · Tool use	205K	$0.02~~$0.6~~	$0.08~~$2.40~~	$0.001
MiniMax M2Up to −96%Reasoning · Tool use	205K	$0.01~~$0.3~~	$0.04~~$1.20~~	$0.001

MiMo

3 models · from $0.14

MiMo models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
MiMo v2.6 ProUp to −96%Vision · Video input · Reasoning · Tool use	1.05M	$0.015~~$0.435~~	$0.029~~$0.87~~	$0.0001
MiMo v2.6 FlashUp to −96%Vision · Video input · Reasoning · Tool use	1.05M	$0.0047~~$0.14~~	$0.0094~~$0.28~~	$0.0001
MiMo v2.5Up to −96%Vision · Video input · Reasoning · Tool use	1.05M	$0.0047~~$0.14~~	$0.0094~~$0.28~~	$0.0001

NVIDIA

3 models · from $0.05

NVIDIA models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Nemotron 3.5 Super VLUp to −96%Vision · Reasoning · Tool use	1M	$0.005~~$0.15~~	$0.017~~$0.5~~	$0.0007
Nemotron 3 UltraUp to −96%Reasoning · Tool use	1M	$0.02~~$0.6~~	$0.08~~$2.40~~	$0.004
Nemotron 3 Nano OmniUp to −96%Vision · Video input · Reasoning · Tool use	256K	$0.0017~~$0.05~~	$0.0067~~$0.2~~	$0.001

Tencent

3 models · from $0.132

Tencent models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Hy4 PreviewUp to −96%NewPaid accountsReasoning · Tool use	1.05M	$0.028~~$0.834~~	$0.084~~$2.50~~	—
Hy3Up to −96%Paid accountsReasoning · Tool use	192K	$0.0044~~$0.132~~	$0.018~~$0.528~~	$0.0011
Hy3 PreviewUp to −96%Paid accountsReasoning · Tool use	192K	$0.006~~$0.18~~	$0.02~~$0.6~~	$0.002

Cohere

16 models · all free

Cohere models, with prices per 1M tokens
Model	Context	Input / 1M	Cache read / 1M
Command A+Vision · Reasoning · Tool use	436K	Free	—
North Mini CodeReasoning · Tool use	256K	Free	—
Command A ReasoningReasoning · Tool use	289K	Free	—
Command A VisionVision	128K	Free	—
Command ATool use	288K	Free	—
Command A TranslateTool use	9K	Free	—
North Small Translate	33K	Free	—
Command R+ (08-2024)Tool use	128K	Free	—
Command R (08-2024)Tool use	128K	Free	—
Command R7B (12-2024)Tool use	132K	Free	—
Aya Expanse 32B	128K	Free	—
Aya Vision 32B	16K	Free	—
Tiny Aya GlobalTool use	8K	Free	—
Tiny Aya EarthTool use	8K	Free	—
Tiny Aya FireTool use	8K	Free	—
Tiny Aya WaterTool use	8K	Free	—

SenseNova

1 model · all free

SenseNova models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
SenseNova 6.8 Flash-LiteVision · Reasoning · Tool use	262K	Free		—

Stealth

1 model · all free · anonymous lab, not a provider

Stealth models, with prices per 1M tokens
Model	Context	Input / 1M	Output / 1M	Cache read / 1M
Big Pickle (Free)Reasoning · Tool use	200K	Free		—

One endpoint

Every model takes the same request.

Point your SDK at xKiro once, then switch models by changing the model ID — vendor prefix included. Nothing else in your code changes.

Read the SDK guides

OpenAI SDK · Base URL

https://api.xkiro.com/v1

Anthropic SDK · Claude Code · Base URL

https://api.xkiro.com

Anatomy of a model ID

openaivendorgpt-6.1-solmodel

Send the whole ID. The bare model name, without the vendor prefix, does not resolve.

Terminal

$ curl -s https://api.xkiro.com/v1/models | jq '.data | length'
103
$ curl -s https://api.xkiro.com/v1/models 
    | jq '.data[] | select(.id == "openai/gpt-6.1-sol") | .pricing'
{
  "currency": "USD",
  "unit": "per_1m_tokens",
  "input": 2,
  "output": 10,
  "cache_read": 0.1,
  "cache_write": 2.5
}

$ curl -s https://api.xkiro.com/v1/models | jq '.data | length'curl -s https://api.xkiro.com/v1/models | jq '.data | length'
103103
$ curl -s https://api.xkiro.com/v1/models 
    | jq '.data[] | select(.id == "openai/gpt-6.1-sol") | .pricing'curl -s https://api.xkiro.com/v1/models 
    | jq '.data[] | select(.id == "openai/gpt-6.1-sol") | .pricing'
{
  "currency": "USD",
  "unit": "per_1m_tokens",
  "input": 2,
  "output": 10,
  "cache_read": 0.1,
  "cache_write": 2.5
}{
  "currency": "USD",
  "unit": "per_1m_tokens",
  "input": 2,
  "output": 10,
  "cache_read": 0.1,
  "cache_write": 2.5
}

The catalog is public at GET /v1/models — no API key needed.

Base URLhttps://api.xkiro.com/v1

Pick a model. Ship it today.

45 models are free to call, no credit card. Paid models bill per token at the rates above.

Get your API keyRead the docs

No credit card · Cancel anytime · 45 free models, free forever