[ providers ]
inference sources
79 live models across 13 providers. routed dynamically on price, latency, uptime and availability.
$
// all models · 79
live · auto-sorted by trafficgpt-5.5
OpenAI · 400K
chatvisiontools
latency
380ms
uptime
99.9%
users
5
gpt-5.4
OpenAI · 256K
chatreasoning
latency
410ms
uptime
99.9%
users
5
gpt-5
OpenAI · 256K
chatvisiontools
latency
410ms
uptime
99.9%
users
5
claude-opus-4.5
Anthropic · 500K
reasoninglong-context
latency
920ms
uptime
99.5%
users
5
claude-sonnet-4.5
Anthropic · 200K
chattoolsvision
latency
430ms
uptime
99.9%
users
5
gemini-3.1-pro-preview
Google · 2M
reasoningvision
latency
540ms
uptime
99.6%
users
5
gemini-3.5-flash
Google · 1M
fastreasoning
latency
200ms
uptime
99.9%
users
5
gemini-2.5-flash
Google · 1M
fastvision
latency
190ms
uptime
99.9%
users
5
llama-4-maverick
Meta · 1M
openchat
latency
320ms
uptime
99.6%
users
5
deepseek-v3.2
DeepSeek · 128K
openchat
latency
380ms
uptime
99.6%
users
5
gpt-5.5-pro
OpenAI · 400K
reasoning
latency
1100ms
uptime
99.7%
users
4
gpt-5.4-mini
OpenAI · 128K
chatfast
latency
220ms
uptime
99.8%
users
4
gpt-5.2
OpenAI · 256K
chatreasoning
latency
430ms
uptime
99.8%
users
4
gpt-5-mini
OpenAI · 128K
chatfast
latency
220ms
uptime
99.7%
users
4
gpt-4o
OpenAI · 128K
chatvision
latency
380ms
uptime
99.8%
users
4
claude-sonnet-4
Anthropic · 200K
chattools
latency
460ms
uptime
99.8%
users
4
claude-haiku-4.5
Anthropic · 200K
fastcheap
latency
160ms
uptime
99.9%
users
4
claude-haiku-4
Anthropic · 200K
fastcheap
latency
180ms
uptime
99.8%
users
4
gemini-3.1-flash-lite-preview
Google · 1M
fastcheap
latency
150ms
uptime
99.9%
users
4
gemini-3-flash-preview
Google · 1M
fast
latency
180ms
uptime
99.8%
users
4
gemini-2.5-pro
Google · 1M
chatvisionlong-context
latency
510ms
uptime
99.7%
users
4
gemini-2.5-flash-lite
Google · 1M
fastcheap
latency
120ms
uptime
99.9%
users
4
llama-4-behemoth
Meta · 1M
openreasoning
latency
720ms
uptime
99.3%
users
4
llama-3.3-70b
Meta · 128K
open
latency
360ms
uptime
99.7%
users
4
mistral-large-2
Mistral · 128K
chattools
latency
410ms
uptime
99.5%
users
4
codestral-25.01
Mistral · 256K
code
latency
260ms
uptime
99.6%
users
4
deepseek-v3.1
DeepSeek · 128K
openchat
latency
390ms
uptime
99.6%
users
4
deepseek-r1
DeepSeek · 128K
reasoningopen
latency
1400ms
uptime
99.3%
users
4
grok-4
xAI · 256K
chattools
latency
470ms
uptime
99.4%
users
4
sonar-pro
Perplexity · 200K
search
latency
620ms
uptime
99.6%
users
4
qwen-3-max
Qwen · 256K
openchat
latency
390ms
uptime
99.5%
users
4
gpt-5.4-nano
OpenAI · 64K
fastcheap
latency
110ms
uptime
99.9%
users
3
gpt-5-nano
OpenAI · 64K
fastcheap
latency
130ms
uptime
99.8%
users
3
gpt-4o-mini
OpenAI · 128K
chatfast
latency
180ms
uptime
99.9%
users
3
o3-mini
OpenAI · 128K
reasoningfast
latency
480ms
uptime
99.6%
users
3
o4-mini
OpenAI · 128K
reasoningfast
latency
540ms
uptime
99.6%
users
3
claude-opus-4.1
Anthropic · 200K
reasoninglong-context
latency
980ms
uptime
99.4%
users
3
claude-opus-4
Anthropic · 200K
reasoning
latency
1010ms
uptime
99.4%
users
3
claude-3.7-sonnet
Anthropic · 200K
chat
latency
490ms
uptime
99.7%
users
3
gemini-3.1-flash-image-preview
Google · 1M
image
latency
260ms
uptime
99.8%
users
3
gemini-3-pro-image-preview
Google · 1M
image
latency
340ms
uptime
99.7%
users
3
gemini-2.5-flash-image
Google · 1M
image
latency
280ms
uptime
99.8%
users
3
gemini-2.0-flash
Google · 1M
fast
latency
210ms
uptime
99.8%
users
3
llama-4-scout
Meta · 10M
openlong-context
latency
480ms
uptime
99.4%
users
3
llama-3.2-90b-vision
Meta · 128K
openvision
latency
410ms
uptime
99.6%
users
3
llama-3.1-405b
Meta · 128K
open
latency
620ms
uptime
99.5%
users
3
mistral-medium-3
Mistral · 128K
chat
latency
280ms
uptime
99.7%
users
3
mistral-small-3.1
Mistral · 128K
fastopen
latency
160ms
uptime
99.8%
users
3
deepseek-r1-distill-70b
DeepSeek · 128K
reasoningopenfast
latency
520ms
uptime
99.5%
users
3
deepseek-coder-v3
DeepSeek · 128K
codeopen
latency
290ms
uptime
99.7%
users
3
grok-4-fast
xAI · 128K
fast
latency
230ms
uptime
99.7%
users
3
grok-4-heavy
xAI · 256K
reasoning
latency
1100ms
uptime
99.3%
users
3
command-a
Cohere · 256K
chatrag
latency
320ms
uptime
99.6%
users
3
sonar-reasoning-pro
Perplexity · 200K
searchreasoning
latency
980ms
uptime
99.5%
users
3
sonar
Perplexity · 128K
searchfast
latency
380ms
uptime
99.8%
users
3
qwen-3-coder-480b
Qwen · 256K
codeopen
latency
410ms
uptime
99.5%
users
3
qwen-3-coder
Qwen · 256K
codeopen
latency
310ms
uptime
99.6%
users
3
qwen-3-vl-235b
Qwen · 128K
openvision
latency
440ms
uptime
99.5%
users
3
qwen-3-72b
Qwen · 128K
open
latency
340ms
uptime
99.7%
users
3
nemotron-ultra-253b
NVIDIA · 128K
openreasoning
latency
580ms
uptime
99.3%
users
3
phi-4
Microsoft · 16K
edgeopen
latency
110ms
uptime
99.8%
users
3
nova-premier
Amazon · 1M
chatreasoning
latency
510ms
uptime
99.5%
users
3
nova-pro
Amazon · 300K
chatvision
latency
340ms
uptime
99.6%
users
3
o3
OpenAI · 200K
reasoning
latency
1200ms
uptime
99.5%
users
2
ministral-8b
Mistral · 128K
fastedge
latency
140ms
uptime
99.8%
users
2
pixtral-large
Mistral · 128K
vision
latency
380ms
uptime
99.6%
users
2
grok-3
xAI · 128K
chat
latency
410ms
uptime
99.5%
users
2
grok-3-mini
xAI · 128K
fast
latency
210ms
uptime
99.7%
users
2
command-r-plus
Cohere · 128K
ragtools
latency
340ms
uptime
99.5%
users
2
command-r
Cohere · 128K
ragfast
latency
210ms
uptime
99.7%
users
2
aya-expanse-32b
Cohere · 128K
openmultilingual
latency
360ms
uptime
99.6%
users
2
sonar-small
Perplexity · 128K
searchfast
latency
380ms
uptime
99.8%
users
2
qwq-32b
Qwen · 128K
reasoningopen
latency
760ms
uptime
99.5%
users
2
nemotron-4-340b
NVIDIA · 128K
open
latency
520ms
uptime
99.4%
users
2
phi-4-mini
Microsoft · 16K
edgeopenfast
latency
90ms
uptime
99.9%
users
2
phi-4-multimodal
Microsoft · 32K
visionopen
latency
180ms
uptime
99.7%
users
2
nova-lite
Amazon · 300K
fastvision
latency
180ms
uptime
99.8%
users
2
nova-micro
Amazon · 128K
fastcheap
latency
90ms
uptime
99.9%
users
2
nemotron-mini-4b
NVIDIA · 32K
edgeopen
latency
120ms
uptime
99.8%
users
1