MiniMax Week on AI/ML API! Music free, Video/TTS −30%, LLM −10%!

AI API Models Pricing

Compare 500+ AI models — all accessible with one API key
1
LLM
Image
Voice
Video
Music
Embedding
3D
Group by Creator
Active models are fully supported. Deprecated models are being phased out.
Status
1
Features supported by the model (function calling, streaming, web search, and more)
Capabilities
1
Creators
1
Price
1
Maximum number of tokens the model can process in a single request
Context
1
Reset
20 of 22 models
Creator
Features supported by the model (function calling, streaming, web search, and more)
Model
Features supported by the model (function calling, streaming, web search, and more)
Modalities
Input and output formats supported by the model (text, image, audio, video)
Capabilities
Features supported by the model (function calling, streaming, web search, and more)
Context
Maximum number of tokens the model can process in a single request
Input
Cost of the tokens you send to the model
Output
Cost of the tokens generated by the model
Links
Creator
Features supported by the model (function calling, streaming, web search, and more)
Model
Features supported by the model (function calling, streaming, web search, and more)
Modalities
Features supported by the model (function calling, streaming, web search, and more)
Capabilities
Features supported by the model (function calling, streaming, web search, and more)
Context
Features supported by the model (function calling, streaming, web search, and more)
Input
Features supported by the model (function calling, streaming, web search, and more)
Output
Features supported by the model (function calling, streaming, web search, and more)
Links
Language Models
per 1M tokens
Unbiased
Pareto 26.10
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
1.10032
$
4.40128
Docs
API
Chat
unbiased-pareto-26-10
Reflection
Beam 1.0 501B A23B
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1M
$
0.34385
$
1.3754
Docs
API
Chat
reflection-beam-1-0-501b-a23b
Elorian
Glimpse
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
256K
$
0.82524
$
4.1262
Docs
API
Chat
elorian-glimpse
MiniMax
MiniMax M3.1 Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
0.195
$
0.78
Docs
API
Chat
minimax-minimax-m3-1-flash
DeepSeek
DeepSeek V4.1 Flash 1017
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
0.39
$
1.56
Docs
API
Chat
deepseek-v4-1-flash-1017
Moondream
Moondream 3.1
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Vision
32K
$
0.41262
$
3.4385
Docs
API
Chat
moondream-moondream3-1-9b-a2b
Moondream
Moondream 3 Preview
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Vision
32K
$
0.41262
$
3.4385
Docs
API
Chat
moondream-moondream3-preview
xAI
Grok Imagine Image 2.0
Image
Active
false
→
—
—
$
0
0.104
Per/gen
Docs
API
Chat
grok-imagine-image-2-0
ElevenLabs
Scribe v2
Voice
Active
false
→
—
—
—
0
Per/sec
Docs
API
Chat
elevenlabs-scribe-v2
TypeSafe AI
Jev 1.14
Chat
Active
false
→
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
—
$
0.0546
$
0
Docs
API
Chat
typesafe-jev-1-14
TypeSafe AI
Jev 1.13
Chat
Active
false
→
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
—
$
0.0546
$
0
Docs
API
Chat
typesafe-jev-1-13
NVIDIA
Nemotron 3.5 Super VL
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
0.34385
$
2.0631
Docs
API
Chat
nvidia-nemotron-3-5-super-vl
Meta
Muse Spark Open
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
1.71925
$
5.84545
Docs
API
Chat
meta-muse-spark-open
Google
Gemini 3.5 Transcribe
Active
false
→
—
—
—
—
Docs
API
Chat
google-gemini-3-5-transcribe
LFM2.5-24B-A2B
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
128K
$
0.13754
$
1.3754
Docs
API
Chat
liquid-lfm-2-5-24b-a2b
Meta
Muse Wonder
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1M
$
5.5016
$
27.508
Docs
API
Chat
meta-muse-wonder
StepFun
Step 5 Preview
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
1.3754
$
3.71358
Docs
API
Chat
stepfun-step-5-preview
Anthropic
Claude Haiku 5.5
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Web search
Web search
Searches the web during inference
1M
$
0.13
$
0.65
Docs
API
Chat
anthropic-claude-haiku-5-5
Mistral AI
Mistral Large 4
Chat
Active
false
→
—
—
$
1.768
$
5.434
Docs
API
Chat
mistralai-mistral-large-4-0
Google
Nano Banana 2.1
Image
Active
false
→
—
—
$
1.95
—
Docs
API
Chat
google-nano-banana-2-1
ElevenLabs
Eleven v4 Turbo
Voice
Active
false
→
—
—
$
52
—
Docs
API
Chat
elevenlabs-eleven-v4-turbo
ElevenLabs
Eleven v4
Voice
Active
false
→
—
—
$
104
—
Docs
API
Chat
elevenlabs-eleven-v4
Meshy
Meshy 6 Image to 3D
Image
Active
false
→
—
—
—
1.04
Per/gen
Docs
API
Chat
meshy-v6-image-to-3d
inclusionAI
Ling 3.1 Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Function calling
Function calling
Supports tool use and external API integrations
—
—
—
Docs
API
Chat
ling-3-1-flash
Unbiased
Pareto 26.10 Preview
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
1.10032
$
4.40128
Docs
API
Chat
unbiased-pareto-26-10-preview
Google
Gemini 4 Argon
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
1M
$
2.6
$
13
Docs
API
Chat
gemini-4-argon
Liquid AI
Liquid Router
Chat
Active
true
→
File input
Function calling
Function calling
Supports tool use and external API integrations
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
—
—
—
Docs
API
Chat
liquid-d1-router
TypeSafe AI
Jev Router
Chat
Active
true
→
File input
Function calling
Function calling
Supports tool use and external API integrations
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
—
—
—
Docs
API
Chat
typesafe-jev-router
Liquid AI
d1
Chat
Active
false
→
—
—
$
0.0546
$
0
Docs
API
Chat
liquid-d1
OpenAI
GPT-6.1 Sol
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
2.6
$
13
Docs
API
Chat
openai-gpt-6-1-sol
Anthropic
Claude Sonnet 5.5
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
2.6
$
13
Docs
API
Chat
anthropic-claude-sonnet-5-5
Perceptron
Mk1.5
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.20631
$
2.0631
Docs
API
Chat
perceptron-perceptron-mk1-5
Aion-3.5-Mini
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
0.96278
$
1.92556
Docs
API
Chat
aion-labs-aion-3-5-mini
Aion-3.5
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
4.1262
$
8.2524
Docs
API
Chat
aion-labs-aion-3-5
Fireworks
Ember-1
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Function calling
Function calling
Supports tool use and external API integrations
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
1048K
$
4.1262
$
20.631
Docs
API
Chat
fireworks-ember-1
Alibaba Cloud
Qwen3.8 Max Prime
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Function calling
Function calling
Supports tool use and external API integrations
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
1M
$
5.5016
$
16.5048
Docs
API
Chat
qwen3-8-max-prime
Upstage
Solar Mini 4
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
—
$
0.13754
$
0.55016
Docs
API
Chat
upstage-solar-mini-4
OpenAI
GPT-6 Luna
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Function calling
Function calling
Supports tool use and external API integrations
Vision
Structured outputs
Structured outputs
Returns data in a strict JSON format
Streaming
Streaming
Returns responses in real time, token by token
—
$
0.13
$
0.65
Docs
API
Chat
gpt-6-luna
OpenAI
GPT-6 Sol
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Function calling
Function calling
Supports tool use and external API integrations
Vision
Structured outputs
Structured outputs
Returns data in a strict JSON format
Streaming
Streaming
Returns responses in real time, token by token
—
$
2.6
$
13
Docs
API
Chat
gpt-6-sol
Anthropic
Claude Opus 5.5
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Web search
Web search
Searches the web during inference
1M
$
5.2
$
26
Docs
API
Chat
claude-opus-5-5
Xiaomi
MiMo V2.6 Pro UltraSpeed
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
5.98299
$
11.96598
Docs
API
Chat
xiaomi-mimo-v2-6-pro-ultraspeed
Xiaomi
MiMo V2.6 Pro
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.598299
$
1.196598
Docs
API
Chat
xiaomi-mimo-v2-6-pro
Xiaomi
MiMo V2.6 Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.192556
$
0.385112
Docs
API
Chat
xiaomi-mimo-v2-6-flash
Ternary Bonsai 2 27B
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.103155
$
0.6877
Docs
API
Chat
prism-ml-ternary-bonsai-2-27b
xAI
Grok 4.7
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Streaming
Streaming
Returns responses in real time, token by token
File input
—
$
2.6
$
7.8
Docs
API
Chat
grok-4-7
Zhipu AI
GLM 5.3 FlashX
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.481
$
1.625
Docs
API
Chat
glm-5-3-flashx
Alibaba Cloud
Qwen3.8 Omni Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
0.195
$
0.611
Docs
API
Chat
alibaba-qwen3-8-omni-flash
Unbiased
Pareto
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
—
$
3.4385
$
10.3155
Docs
API
Chat
unbiased-pareto
TypeSafe AI
Jev 1.13
Chat
Active
false
→
—
—
$
0.0546
$
0
Docs
API
Chat
typesafe-jev
Inference.net
Schematron V2 Turbo
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
128K
$
0.041262
$
0.20631
Docs
API
Chat
inference-net-schematron-v2-turbo
Inference.net
Schematron V2 Small
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
128K
$
0.06877
$
0.316342
Docs
API
Chat
inference-net-schematron-v2-small
DeepSeek
DeepSeek Chat (V4.1 Flash)
Chat
Active
false
→
File input
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
0.39
$
1.56
Docs
API
Chat
deepseek-deepseek-chat
Sakana AI
Fugu Max
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1M
$
2.7508
$
8.2524
Docs
API
Chat
fugu-max
Sakana AI
Fugu Ultra v2
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1M
$
6.877
$
41.262
Docs
API
Chat
fugu-ultra-v2
inclusionAI
Ling 3.0 Flash VL
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
131K
$
0.082524
$
0.247572
Docs
API
Chat
ling-3-0-flash-vl
DeepSeek
DeepSeek V4.1 Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1M
$
0.39
$
1.56
Docs
API
Chat
deepseek-v4-1-flash
NVIDIA
Nemotron 3.5 Content Safety
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Vision
131K
$
0.27508
$
0.27508
Docs
API
Chat
nvidia-nemotron-3-5-content-safety
OpenAI
GPT Image 2.5 Sunburst
Image
Active
false
→
—
—
$
6.5
—
Docs
API
Chat
gpt-image-2-5-sunburst
OpenAI
GPT Image 2.5 Flare
Image
Active
false
→
—
—
$
6.5
—
Docs
API
Chat
gpt-image-2-5-flare
inclusionAI
Ling 3.0 Flash Fin
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
0.082524
$
0.247572
Docs
API
Chat
inclusionai-ling-3-0-flash-fin
IBM
Granite 4.2 8B
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
0.13754
$
0.34385
Docs
API
Chat
ibm-granite-granite-4-2-8b
Inception
Mercury 2.5
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
0.27508
$
1.03155
Docs
API
Chat
inception-mercury-2-5
OpenAI
GPT-6 Astra
Chat
Active
false
→
Function calling
Function calling
Supports tool use and external API integrations
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Vision
—
$
13
$
65
Docs
API
Chat
openai-gpt-6-astra
Meta
Muse Spark 1.3
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
1.71925
$
5.84545
Docs
API
Chat
meta-muse-spark-1-3
Google
Gemini 3.8 Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
Vision
1048K
$
0.975
$
4.875
Docs
API
Chat
gemini-3-8-flash
Anthropic
Claude Fable 5.1
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
1M
$
13
$
65
Docs
API
Chat
claude-fable-5-1
MiniMax
MiniMax H3 Max
Video
Active
false
→
—
—
—
0.104
Per/sec
Docs
API
Chat
minimax-h3-max
Tencent
Hy4 Preview
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
—
$
1.1470836
$
3.4398754
Docs
API
Chat
tencent-hy4-preview
Google
Gemini Omni 1.1 Flash
Video
Active
false
→
—
—
—
0.132
Per/sec
Docs
API
Chat
gemini-omni-1-1-flash
Meta
Meta Muse Image Edit
Image
Active
false
→
—
—
—
0.013
Per/gen
Docs
API
Chat
meta-muse-image-edit
Meta
Meta Muse Image
Image
Active
false
→
—
—
—
0.013
Per/gen
Docs
API
Chat
meta-muse-image
Alibaba Cloud
Qwen3.8-Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1M
$
0.208
$
0.611
Docs
API
Chat
qwen3-8-flash
Zhipu AI
GLM-5.3-Flash
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Structured outputs
Structured outputs
Returns data in a strict JSON format
Function calling
Function calling
Supports tool use and external API integrations
1048K
$
0.195
$
0.65
Docs
API
Chat
glm-5-3-flash
Thinking Machines
Inkling
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
—
$
1.3754
$
5.57037
Docs
API
Chat
thinkingmachines-inkling
Venice Uncensored
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
Web search
Web search
Searches the web during inference
128K
$
0.27508
$
1.23786
Docs
API
Chat
cognitivecomputations-dolphin-mistral-24b-venice-edition
Aion-3.0
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
Web search
Web search
Searches the web during inference
131K
$
4.1262
$
8.2524
Docs
API
Chat
aion-labs-aion-3-0
Aion-3.0-Mini
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
Web search
Web search
Searches the web during inference
131K
$
0.96278
$
1.92556
Docs
API
Chat
aion-labs-aion-3-0-mini
Alibaba Cloud
Qwen Text Embedding v3
Embedding
Active
false
—
8K
$
0.091
—
Docs
API
Chat
alibaba-qwen-text-embedding-v3
Alibaba Cloud
Qwen Text Embedding v4
Embedding
Active
false
—
8K
$
0.091
—
Docs
API
Chat
alibaba-qwen-text-embedding-v4
Alibaba Cloud
Qwen3.8 2.4T A95B
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
—
$
3.4385
$
8.59625
Docs
API
Chat
alibaba-qwen3-8-2-4t-a95b
Zhipu AI
GLM 5.2 Fast Preview
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
1M
$
4.55
$
14.3
Docs
API
Chat
zhipu-glm-5-2-fast-preview
Alibaba Cloud
Qwen3 Next 80B A3B Thinking
Chat
Active
false
→
Streaming
Streaming
Returns responses in real time, token by token
Web search
Web search
Searches the web during inference
—
$
0.20631
$
1.65048
Docs
API
Chat
alibaba-qwen3-next-80b-a3b-thinking
Zhipu AI
GLM 5.2 Fast Preview
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
1M
$
4.55
$
14.3
Docs
API
Chat
alibaba-glm-5-2-fast-preview
Zhipu AI
GLM 5.2
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
1M
$
1.82
$
5.72
Docs
API
Chat
alibaba-glm-5-2
Google
Gemini 3 Pro Image Edit
Image
Active
false
→
—
—
—
0.325
Per/gen
Docs
API
Chat
google-gemini-3-pro-image-edit
Google
Gemini Flash Latest
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
Web search
Web search
Searches the web during inference
—
$
2.0631
$
12.3786
Docs
API
Chat
google-gemini-flash-latest
Google
Gemini Pro Latest
Chat
Active
false
→
File input
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
Web search
Web search
Searches the web during inference
—
$
2.7508
$
16.5048
Docs
API
Chat
google-gemini-pro-latest
Google
Gemini 2.5 Flash Lite Preview
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
1M
$
0.0975
$
0.39
Docs
API
Chat
google-gemini-2-5-flash-lite-preview
Google
Nano Banana Edit
Image
Active
false
→
—
—
—
0.052
Per/gen
Docs
API
Chat
google-nano-banana-edit
Google
Gemini 2.5 Flash Image Edit
Image
Active
false
→
—
—
—
0.052
Per/gen
Docs
API
Chat
google-gemini-2-5-flash-image-edit
Google
Nano Banana
Image
Active
false
→
—
—
—
0.051
Per/gen
Docs
API
Chat
google-nano-banana
Google
Nano Banana Pro Edit
Image
Active
false
→
—
—
—
0.195
Per/gen
Docs
API
Chat
google-nano-banana-pro-edit
Google
Gemini 3 Pro Image Edit
Image
Active
false
→
—
—
—
0.325
Per/gen
Docs
API
Chat
google-gemini-3-pro-image-preview-edit
Google
Nano Banana Pro
Image
Active
false
→
—
—
—
0.325
Per/gen
Docs
API
Chat
google-nano-banana-pro
Google
Gemma 4 26B A4B IT
Chat
Active
false
→
File input
Streaming
Streaming
Returns responses in real time, token by token
Vision
—
$
0.195
$
0.78
Docs
API
Chat
google-gemma-4-26b-a4b-it-maas
DeepSeek
DeepSeek V4 Pro 0813
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
—
$
2.393196
$
4.786392
Docs
API
Chat
deepseek-deepseek-v4-pro-0813
DeepSeek
DeepSeek V3.1
Chat
Active
false
→
File input
Streaming
Streaming
Returns responses in real time, token by token
128K
$
0.371358
$
1.3754
Docs
API
Chat
deepseek-deepseek-reasoner-v3-1-terminus
ByteDance
Dola-Seed 2.0 Mini
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
256K
$
0.13
$
0.52
Docs
API
Chat
bytedance-dola-seed-2-0-mini
ByteDance
Dola-Seed 2.0 Lite
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
256K
$
0.325
$
2.6
Docs
API
Chat
bytedance-dola-seed-2-0-lite
ByteDance
Dola-Seed 2.0 Pro
Chat
Active
false
→
Reasoning
Reasoning
Performs step-by-step reasoning for complex tasks
Streaming
Streaming
Returns responses in real time, token by token
Vision
256K
$
0.65
$
3.9
Docs
API
Chat
bytedance-dola-seed-2-0-pro
No models match your filters

Frequently asked questions

What is a token?

A token is a small chunk of text — roughly 4 characters or ¾ of a word. "Hello world" is about 3 tokens. Pricing is based on the total number of tokens sent and received.

How many requests is 1M tokens?

It depends on prompt size, but as a rough guide: 1M tokens ≈ 750,000 words ≈ 1,000 typical API requests.

What is a context window, and how does it affect pricing?

The maximum text a model can process in one request — input and output combined. Longer inputs consume more tokens and increase cost.

What's the difference between input and output pricing?

Input is what you send, output is what the model returns. Output tokens are typically priced higher, so longer responses cost more.

How does pricing work? Am I charged for input, output, or both?

Both. Total cost = input tokens × input price + output tokens × output price. All prices are per 1M tokens.

Are there any rate limits?

Yes, limits vary by model and account tier. Default limits cover most development and production use cases. Need more? Contact us about Enterprise plans.

Start building with one API key

Get API Key
Copy as API Request
Python
JavaScript
cURL
Copy
Copied
Filters
Reset
Group by Creator
Status
All
Capabilities
Any
Creators
All
Price
Any
Context
Any
Clear
2 of 100 models