Model Library
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Loading models...
Compare AI Models
Compare every AI model available on DEVUP AI side by side to choose the optimal engine for your workload. Evaluate input, output, and cached prompt reads priced in Algerian Dinar (DZD) per million tokens, alongside context window limits and support for tool calling, vision, and reasoning.
Prices and capabilities update within a minute of a change.
Capabilities:|Tiers:|
Showing 227 of 227 models
(Prices in DZD per 1M tokens)
Showing 227 of 227 models
(Prices in DZD per 1M tokens)
DeepSeek-V3.2
deepseek-ai
In91
Out133
Cached45.5
text-generationContext 163kMax output not specified
Supports
——
Flex
DeepSeek-V4-Flash
deepseek-ai
In35
Out70
Cached7
text-generationContext 1MMax output not specified
Supports
—
PriorityFlex5m1h
DeepSeek-V4-Flash-0731
deepseek-ai
In32
Out72
Cached6.4
text-generationContext 1MMax output not specified
Supports
—
PriorityFlex
DeepSeek-V4-Pro
deepseek-ai
In455
Out910
Cached35
text-generationContext 1MMax output not specified
Supports
——
PriorityFlex
DeepSeek-V4-Pro-0813
deepseek-ai
In455
Out910
Cached35
text-generationContext 1MMax output not specified
Supports
——
PriorityFlex
gemini-3.7-flash
google
In263
Out1,313
Cached—
text-generationContext 1MMax output not specified
Supports
gemma-4-26B-A4B-it
google
In24.5
Out119
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
gemma-4-31B-it
google
In45.5
Out133
Cached—
text-generationContext 256KMax output not specified
Supports
PriorityFlex
GLM-5.1
zai-org
In367.5
Out1,225
Cached71.75
text-generationContext 200KMax output not specified
Supports
—
GLM-5.2
zai-org
In263
Out630
Cached37
text-generationContext 1MMax output not specified
Supports
—
PriorityFlex5m1h
Kimi-K2.6
moonshotai
In262.5
Out1,225
Cached52.5
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Kimi-K2.7-Code
moonshotai
In238
Out1,190
Cached47.6
text-generationContext 262KMax output not specified
Supports
PriorityFlex5m1h
MiMo-V2.5
XiaomiMiMo
In140
Out700
Cached28
text-generationContext 262KMax output not specified
Supports
PriorityFlex
MiMo-V2.5-Pro
XiaomiMiMo
In350
Out1,050
Cached70
text-generationContext 1MMax output not specified
Supports
—
PriorityFlex
NVIDIA-Nemotron-3-Super-120B-A12B
nvidia
In35
Out175
Cached—
text-generationContext 262KMax output not specified
Supports
—
PriorityFlex
NVIDIA-Nemotron-3-Ultra-550B-A55B
nvidia
In175
Out875
Cached52.5
text-generationContext 1MMax output not specified
Supports
PriorityFlex5m1h
Qwen3-Max
Qwen
In1,050
Out5,250
Cached210
text-generationContext 262KMax output not specified
Supports
——
Qwen3-Max-Thinking
Qwen
In1,050
Out5,250
Cached210
text-generationContext 262KMax output not specified
Supports
——
Qwen3-TTS
Qwen
In7,000
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
Qwen3-TTS-VoiceDesign
Qwen
In7,000
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
Qwen3.5-397B-A17B
Qwen
In157.5
Out1,050
Cached77
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Qwen3.6-35B-A3B
Qwen
In52.5
Out332.5
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Step-3.7-Flash
stepfun-ai
In70
Out403
Cached14
text-generationContext 262KMax output not specified
Supports
—
gpt-6-astra
openai
In3,500
Out17,500
Cached350
text-generationContext 1MMax output 128,000
Supports
all-MiniLM-L12-v2
sentence-transformers
In3
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
all-MiniLM-L6-v2
sentence-transformers
In3
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
all-mpnet-base-v2
sentence-transformers
In3
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
Audio8-TTS-Preview-0.6b
Audio8
In1,750
Out—
Cached—
text-to-speechContext —Max output not specified
Supports
———
bge-base-en-v1.5
BAAI
In1.75
Out1.75
Cached—
embeddingsContext 512Max output not specified
Supports
———
bge-en-icl
BAAI
In5
Out—
Cached—
embeddingsContext 8kMax output not specified
Supports
———
bge-large-en-v1.5
BAAI
In5
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
bge-m3
BAAI
In5
Out—
Cached—
embeddingsContext 8kMax output not specified
Supports
———
bge-m3-multi
BAAI
In5
Out—
Cached—
embeddingsContext 8kMax output not specified
Supports
———
blur_background
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Bria-3.2
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Bria-3.2-vector
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
chatterbox-multilingual
ResembleAI
In350
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
chatterbox-turbo
ResembleAI
In350
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
claude-fable-5
anthropic
In3,500
Out17,500
Cached—
text-generationContext 1MMax output not specified
Supports
claude-haiku-4-5
anthropic
In350
Out1,750
Cached—
text-generationContext 200KMax output not specified
Supports
claude-opus-4-7
anthropic
In1,750
Out8,750
Cached—
text-generationContext 1MMax output not specified
Supports
claude-opus-4-8
anthropic
In1,750
Out8,750
Cached—
text-generationContext 1MMax output not specified
Supports
claude-opus-5
anthropic
In1,750
Out8,750
Cached—
text-generationContext 1MMax output not specified
Supports
claude-sonnet-4-6
anthropic
In1,050
Out5,250
Cached—
text-generationContext 1MMax output not specified
Supports
claude-sonnet-5
anthropic
In700
Out3,500
Cached—
text-generationContext 1MMax output not specified
Supports
clip-vit-base-patch32
openai
In0.175
Out—
Cached—
zero-shot-image-classificationContext image-classificationMax output not specified
Supports
———
clip-vit-large-patch14-336
openai
In0.175
Out—
Cached—
zero-shot-image-classificationContext image-classificationMax output not specified
Supports
———
creative
ClarityAI
In17.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
DeepSeek-R1-0528
deepseek-ai
In175
Out753
Cached123
text-generationContext 163KMax output not specified
Supports
—
Flex
DeepSeek-V3
deepseek-ai
In112
Out312
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
DeepSeek-V3-0324
deepseek-ai
In70
Out270
Cached47.25
text-generationContext 163KMax output not specified
Supports
——
PriorityFlex
DeepSeek-V3.1
deepseek-ai
In74
Out277
Cached46
text-generationContext 163kMax output not specified
Supports
—
Flex
DeepSeek-V4-Flash-Vision-Exp
deepseek-ai
In154
Out462
Cached49
text-generationContext 1MMax output not specified
Supports
PriorityFlex
e5-base-v2
intfloat
In3
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
e5-large-v2
intfloat
In5
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
embeddinggemma-300m
google
In0.6533
Out—
Cached—
embeddingsContext 2KMax output not specified
Supports
———
enhance
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
erase
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
erase_foreground
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
expand
Bria
In14
Out—
Cached—
text-to-imageContext —Max output not specified
Supports
———
fibo
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
fibo_edit
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
fibo_edit-1.5
Bria
In16
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
fibo-1.5
Bria
In16
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
FLUX-1-dev
black-forest-labs
In3.15
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-1-Redux-dev
black-forest-labs
In4.2
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-1-schnell
black-forest-labs
In0.175
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-1.1-pro
black-forest-labs
In14
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-2-dev
black-forest-labs
In3.5
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-2-klein-4b
black-forest-labs
In4.9
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-2-klein-9b
black-forest-labs
In5.25
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-2-max
black-forest-labs
In24.5
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-2-pro
black-forest-labs
In5.25
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX-pro
black-forest-labs
In16.3333
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
FLUX.1-Kontext-dev
black-forest-labs
In3.5
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
gemini-2.5-flash
google
In105
Out875
Cached—
text-generationContext 1MMax output not specified
Supports
gemini-2.5-pro
google
In437.5
Out3,500
Cached—
text-generationContext 1MMax output not specified
Supports
gemini-3.1-flash-lite
google
In87.5
Out525
Cached—
text-generationContext 1MMax output not specified
Supports
gemini-3.1-pro
google
In700
Out4,200
Cached—
text-generationContext 1MMax output not specified
Supports
gemini-3.5-flash
google
In525
Out3,150
Cached—
text-generationContext 1MMax output not specified
Supports
gemma-3-12b-it
google
In17.5
Out52.5
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
gemma-3-27b-it
google
In28
Out56
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
gemma-3-4b-it
google
In17.5
Out35
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
gemma-4-31B-it-turbo
google
In42
Out129.5
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
gemma-4-31B-it-Ultra
google
In94.5
Out266
Cached—
text-generationContext 262KMax output not specified
Supports
gemma-4-E4B-it
google
In7
Out35
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
gen_fill
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
GLM-4.6
zai-org
In150.5
Out609
Cached28
text-generationContext 200KMax output not specified
Supports
—
GLM-4.7
zai-org
In140
Out613
Cached28
text-generationContext 200KMax output not specified
Supports
—
GLM-5.3
zai-org
In490
Out1,540
Cached91
text-generationContext 1MMax output not specified
Supports
—
GLM-5.3-Flash
zai-org
In60
Out200
Cached12
text-generationContext 1MMax output not specified
Supports
gpt-4o-mini
openai
In52.5
Out210
Cached26.25
text-generationContext 128KMax output not specified
Supports
—
gpt-5.3-codex
openai
In613
Out4,900
Cached61.25
text-generationContext 400KMax output 128,000
Supports
gpt-5.4
openai
In875
Out5,250
Cached87.5
text-generationContext 1MMax output 128,000
Supports
gpt-5.4-mini
openai
In263
Out1,575
Cached26.25
text-generationContext 400KMax output 128,000
Supports
gpt-5.4-nano
openai
In70
Out438
Cached7
text-generationContext 400kMax output 128,000
Supports
gpt-5.4-pro
openai
In10,500
Out63,000
Cached10,500
text-generationContext 1MMax output not specified
Supports
gpt-5.5
openai
In1,750
Out10,500
Cached175
text-generationContext 1MMax output 128,000
Supports
gpt-5.5-pro
openai
In10,500
Out63,000
Cached10,500
text-generationContext 1MMax output 128,000
Supports
gpt-5.6-luna
openai
In70
Out420
Cached7
text-generationContext 1MMax output 128,000
Supports
gpt-5.6-sol
openai
In1,400
Out7,000
Cached140
text-generationContext 1MMax output 128,000
Supports
gpt-5.6-terra
openai
In700
Out4,200
Cached70
text-generationContext 1MMax output 128,000
Supports
gpt-image-2
openai
In5,250
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
gpt-image-2.5-flare
openai
In10,500
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
gpt-image-2.5-sunburst
openai
In10,500
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
gpt-oss-120b
openai
In13.65
Out66.5
Cached—
text-generationContext 131KMax output not specified
Supports
—
gpt-oss-120b-Turbo
openai
In52.5
Out210
Cached—
text-generationContext 131KMax output not specified
Supports
—
Flex
gpt-oss-120b-Ultra
openai
In70
Out333
Cached—
text-generationContext 131KMax output not specified
Supports
—
gpt-oss-20b
openai
In10.5
Out49
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
granite-4.2-30b
ibm-granite
In64
Out260
Cached16
text-generationContext 131KMax output not specified
Supports
—
granite-4.2-8b
ibm-granite
In24
Out100
Cached6
text-generationContext 131KMax output not specified
Supports
—
Hermes-3-Llama-3.1-405B
NousResearch
In350
Out350
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
Hermes-3-Llama-3.1-70B
NousResearch
In245
Out245
Cached—
text-generationContext 131kMax output not specified
Supports
——
PriorityFlex
HiggsAudioV2.5
bosonai
In7,000
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
Hy3
tencent
In49
Out203
Cached12.25
text-generationContext 262KMax output not specified
Supports
—
Inkling
thinkingmachines
In350
Out1,418
Cached60
text-generationContext 131KMax output not specified
Supports
Inkling-Small
thinkingmachines
In203
Out504
Cached40.6
text-generationContext 524KMax output not specified
Supports
Janus-Pro-1B
deepseek-ai
In1
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Janus-Pro-7B
deepseek-ai
In1
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Kimi-K3
moonshotai
In998
Out4,988
Cached100
text-generationContext 1MMax output not specified
Supports
5m1h
Kokoro-82M
hexgrad
In217
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
L3-8B-Lunaris-v1-Turbo
Sao10K
In14
Out18
Cached—
text-generationContext 8KMax output not specified
Supports
———
Flex
L3.1-70B-Euryale-v2.2
Sao10K
In298
Out298
Cached—
text-generationContext 131KMax output not specified
Supports
———
Flex
Ling-3.0-flash
inclusionAI
In21
Out63
Cached4.2
text-generationContext 131KMax output not specified
Supports
—
Ling-3.0-flash-Fin
inclusionAI
In24
Out72
Cached4.8
text-generationContext 262KMax output not specified
Supports
—
Ling-3.0-flash-VL
inclusionAI
In24
Out72
Cached4.8
text-generationContext 131KMax output not specified
Supports
Llama-3.3-70B-Instruct-Turbo
meta-llama
In35
Out112
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
Llama-4-Maverick-17B-128E-Instruct-FP8
meta-llama
In52.5
Out210
Cached—
text-generationContext 1MMax output not specified
Supports
—
PriorityFlex
Llama-4-Scout-17B-16E-Instruct
meta-llama
In35
Out105
Cached—
text-generationContext 327KMax output not specified
Supports
—
PriorityFlex
Llama-Guard-4-12B
meta-llama
In63
Out63
Cached—
text-generationContext 163kMax output not specified
Supports
——
PriorityFlex
llama-nemotron-embed-vl-1b-v2
nvidia
In3.5
Out—
Cached—
embeddingsContext 10KMax output not specified
Supports
———
llama-nemotron-rerank-vl-1b-v2
nvidia
In3.5
Out—
Cached—
rerankerContext 10KMax output not specified
Supports
———
Meta-Llama-3.1-70B-Instruct-Turbo
meta-llama
In140
Out140
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
Meta-Llama-3.1-8B-Instruct-Turbo
meta-llama
In7
Out14
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
MiMo-V2.5-tts
XiaomiMiMo
In1,634
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
MiMo-V2.5-tts-voiceclone
XiaomiMiMo
In10
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
MiMo-V2.5-tts-voicedesign
XiaomiMiMo
In654
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
MiniMax-M2.7-Turbo
MiniMaxAI
In133
Out595
Cached24.5
text-generationContext 196KMax output not specified
Supports
—
MiniMax-M3
MiniMaxAI
In105
Out420
Cached21
text-generationContext 524KMax output not specified
Supports
Flex
Mistral-Nemo-Instruct-2407
mistralai
In7
Out14
Cached—
text-generationContext 131KMax output not specified
Supports
——
Flex
Mistral-Small-24B-Instruct-2501
mistralai
In17.5
Out28
Cached—
text-generationContext 32KMax output not specified
Supports
——
Flex
Mistral-Small-3.2-24B-Instruct-2506
mistralai
In26.25
Out70
Cached—
text-generationContext 131KMax output not specified
Supports
—
PriorityFlex
multilingual-e5-large
intfloat
In5
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
multilingual-e5-large-instruct
intfloat
In5
Out—
Cached—
embeddingsContext 512Max output not specified
Supports
———
Muse-Glimmer-30B
meta-models
In105
Out420
Cached14
text-generationContext 131KMax output not specified
Supports
Nemotron-3-Embed-1B-BF16
nvidia
In5.25
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Nemotron-3-Embed-1B-NVFP4
nvidia
In3.5
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Nemotron-3-Embed-8B
nvidia
In12.25
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Nemotron-3-Nano-30B-A3B
nvidia
In17.5
Out70
Cached—
text-generationContext 262KMax output not specified
Supports
—
PriorityFlex
Nemotron-3.5-ASR-Streaming-Multilingual-0.6b
nvidia
In0.07
Out—
Cached—
automatic-speech-recognitionContext —Max output not specified
Supports
———
Nemotron-Content-Safety-3.5
nvidia
In70
Out70
Cached—
text-generationContext 131KMax output not specified
Supports
——
orpheus-3b-0.1-ft
canopylabs
In2,450
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
p-image
PrunaAI
In2.4
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
p-image-Edit
PrunaAI
In3.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
p-video
PrunaAI
In14
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
p-video-avatar
PrunaAI
In15.75
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
phi-4
microsoft
In24.5
Out49
Cached—
text-generationContext 16KMax output not specified
Supports
———
Flex
Pixverse-6-I2V
Pixverse
In41
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Pixverse-6-T2V
Pixverse
In41
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Pixverse-T2V
Pixverse
In70
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Pixverse-T2V-HD
Pixverse
In140
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Qwen-Image-Edit
Qwen
In8.75
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Qwen-Image-Edit-Max
Qwen
In24.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Qwen-Image-Max
Qwen
In26.25
Out—
Cached—
text-to-imageContext ImageMax output not specified
Supports
———
Qwen2.5-72B-Instruct
Qwen
In126
Out140
Cached—
text-generationContext 32KMax output not specified
Supports
——
Flex
Qwen3-14B
Qwen
In42
Out84
Cached—
text-generationContext 32KMax output not specified
Supports
—
PriorityFlex
Qwen3-235B-A22B-Instruct-2507
Qwen
In32
Out193
Cached—
text-generationContext 262KMax output not specified
Supports
——
PriorityFlex
Qwen3-30B-A3B
Qwen
In39.2
Out164
Cached—
text-generationContext 32KMax output not specified
Supports
—
PriorityFlex
Qwen3-32B
Qwen
In28
Out98
Cached—
text-generationContext 32KMax output not specified
Supports
—
PriorityFlex
Qwen3-ASR-0.6B
Qwen
In0.08
Out—
Cached—
automatic-speech-recognitionContext —Max output not specified
Supports
———
Qwen3-ASR-1.7B
Qwen
In0.2
Out—
Cached—
automatic-speech-recognitionContext —Max output not specified
Supports
———
Qwen3-Coder-480B-A35B-Instruct-Turbo
Qwen
In105
Out350
Cached35
text-generationContext 262KMax output not specified
Supports
——
Flex
Qwen3-Embedding-0.6B
Qwen
In3.5
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Qwen3-Embedding-4B
Qwen
In6.6
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Qwen3-Embedding-8B
Qwen
In3.5
Out—
Cached—
embeddingsContext 32KMax output not specified
Supports
———
Qwen3-Next-80B-A3B-Instruct
Qwen
In31.5
Out385
Cached—
text-generationContext 262KMax output not specified
Supports
——
PriorityFlex
Qwen3-Reranker-0.6B
Qwen
In3.5
Out—
Cached—
rerankerContext 32KMax output not specified
Supports
———
Qwen3-Reranker-4B
Qwen
In8.75
Out—
Cached—
rerankerContext 32KMax output not specified
Supports
———
Qwen3-Reranker-8B
Qwen
In17.5
Out—
Cached—
rerankerContext 32KMax output not specified
Supports
———
Qwen3-VL-235B-A22B-Instruct
Qwen
In70
Out308
Cached38.5
text-generationContext 262KMax output not specified
Supports
—
PriorityFlex
Qwen3-VL-30B-A3B-Instruct
Qwen
In52.5
Out210
Cached—
text-generationContext 262KMax output not specified
Supports
—
PriorityFlex
Qwen3.5-122B-A10B
Qwen
In102
Out840
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Qwen3.5-27B
Qwen
In91
Out910
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Qwen3.5-35B-A3B
Qwen
In49
Out350
Cached17.5
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Qwen3.5-9B
Qwen
In35
Out52.5
Cached—
text-generationContext 262KMax output not specified
Supports
—
PriorityFlex
Qwen3.6-27B
Qwen
In112
Out1,120
Cached—
text-generationContext 262KMax output not specified
Supports
PriorityFlex
Qwen3.7-Max
Qwen
In2,188
Out6,475
Cached438
text-generationContext 256KMax output not specified
Supports
——
Qwen3.8-2.4T-A95B
Qwen
In700
Out2,100
Cached70
text-generationContext 262KMax output not specified
Supports
—
Qwen3.8-27B
Qwen
In140
Out1,050
Cached14
text-generationContext 262KMax output not specified
Supports
Qwen3.8-Flash
Qwen
In40
Out140
Cached5
text-generationContext 1MMax output not specified
Supports
——
Qwen3.8-Max
Qwen
In578
Out1,733
Cached73
text-generationContext 256KMax output not specified
Supports
——
realtime-tts-1.5-max
inworld-ai
In17,500
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
realtime-tts-1.5-mini
inworld-ai
In8,750
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
realtime-tts-2
inworld-ai
In12,250
Out—
Cached—
text-to-speechContext speechMax output not specified
Supports
———
remove_background
Bria
In6.3
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
replace_background
Bria
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
sdxl-turbo
stabilityai
In0.07
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Seed-1.8
ByteDance
In175
Out1,400
Cached35
text-generationContext 256KMax output not specified
Supports
Seed-2.0-code
ByteDance
In350
Out2,100
Cached70
text-generationContext 256KMax output not specified
Supports
Seed-2.0-mini
ByteDance
In70
Out280
Cached70
text-generationContext 256KMax output not specified
Supports
Seed-2.0-pro
ByteDance
In350
Out2,100
Cached70
text-generationContext 256KMax output not specified
Supports
Seedance-1.5-Pro
ByteDance
In420
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Seedance-2.0
ByteDance
In2,450
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Seedream-4
ByteDance
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Seedream-4.5
ByteDance
In14
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
text-embedding-3-large
openai
In45.5
Out45.5
Cached—
embeddingsContext 8191Max output not specified
Supports
———
text-embedding-3-small
openai
In7
Out7
Cached—
embeddingsContext 8191Max output not specified
Supports
———
veo-3.1
google
In140
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
veo-3.1-fast
google
In52.5
Out—
Cached—
text-to-videoContext VideoMax output not specified
Supports
———
video_foreground_mask
Bria
In49
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
video_increase_resolution
Bria
In49
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
video_mask_by_key_points
Bria
In49
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
video_remove_background
Bria
In2.3
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Voxtral-Mini-3B-2507
mistralai
In0.35
Out—
Cached—
automatic-speech-recognitionContext 32KMax output not specified
Supports
———
Voxtral-Small-24B-2507
mistralai
In1.05
Out—
Cached—
automatic-speech-recognitionContext 32KMax output not specified
Supports
———
Wan2.2-T2V-A14B
Wan-AI
In12.6
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Wan2.6-I2V
Wan-AI
In52.5
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Wan2.6-Image-Edit
Wan-AI
In10.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Wan2.6-T2I
Wan-AI
In10.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Wan2.6-T2V
Wan-AI
In52.5
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Wan2.7-I2V
Wan-AI
In52.5
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Wan2.7-Image-Edit
Wan-AI
In10.5
Out—
Cached—
text-to-imageContext imageMax output not specified
Supports
———
Wan2.7-R2V
Wan-AI
In52.5
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
Wan3.0-Video
Wan-AI
In70
Out—
Cached—
text-to-videoContext videoMax output not specified
Supports
———
whisper-large-v3
openai
In0.1575
Out—
Cached—
automatic-speech-recognitionContext speech-recognitionMax output not specified
Supports
———
whisper-large-v3-turbo
openai
In0.07
Out—
Cached—
automatic-speech-recognitionContext speech-recognitionMax output not specified
Supports
———
DeepSeek-V4.1-Flash
deepseek-ai
In70
Out210
Cached2.4
text-generationContext 1,048,576Max output not specified
Supports
PriorityFlex
Model | Type | Input | Output | Cached | Context | Max output | Capabilities | Tiers |
|---|---|---|---|---|---|---|---|---|
DeepSeek-V3.2 deepseek-ai | text-generation | 91 | 133 | 45.5 | 163k | Not specified | Flex | |
DeepSeek-V4-Flash deepseek-ai | text-generation | 35 | 70 | 7 | 1M | Not specified | PriorityFlex5m1h | |
DeepSeek-V4-Flash-0731 deepseek-ai | text-generation | 32 | 72 | 6.4 | 1M | Not specified | PriorityFlex | |
DeepSeek-V4-Pro deepseek-ai | text-generation | 455 | 910 | 35 | 1M | Not specified | PriorityFlex | |
DeepSeek-V4-Pro-0813 deepseek-ai | text-generation | 455 | 910 | 35 | 1M | Not specified | PriorityFlex | |
gemini-3.7-flash google | text-generation | 263 | 1,313 | — | 1M | Not specified | — | |
gemma-4-26B-A4B-it google | text-generation | 24.5 | 119 | — | 262K | Not specified | PriorityFlex | |
gemma-4-31B-it google | text-generation | 45.5 | 133 | — | 256K | Not specified | PriorityFlex | |
GLM-5.1 zai-org | text-generation | 367.5 | 1,225 | 71.75 | 200K | Not specified | — | |
GLM-5.2 zai-org | text-generation | 263 | 630 | 37 | 1M | Not specified | PriorityFlex5m1h | |
Kimi-K2.6 moonshotai | text-generation | 262.5 | 1,225 | 52.5 | 262K | Not specified | PriorityFlex | |
Kimi-K2.7-Code moonshotai | text-generation | 238 | 1,190 | 47.6 | 262K | Not specified | PriorityFlex5m1h | |
MiMo-V2.5 XiaomiMiMo | text-generation | 140 | 700 | 28 | 262K | Not specified | PriorityFlex | |
MiMo-V2.5-Pro XiaomiMiMo | text-generation | 350 | 1,050 | 70 | 1M | Not specified | PriorityFlex | |
| text-generation | 35 | 175 | — | 262K | Not specified | PriorityFlex | ||
| text-generation | 175 | 875 | 52.5 | 1M | Not specified | PriorityFlex5m1h | ||
Qwen3-Max Qwen | text-generation | 1,050 | 5,250 | 210 | 262K | Not specified | — | |
| text-generation | 1,050 | 5,250 | 210 | 262K | Not specified | — | ||
Qwen3-TTS Qwen | text-to-speech | 7,000 | — | — | speech | Not specified | — | |
| text-to-speech | 7,000 | — | — | speech | Not specified | — | ||
| text-generation | 157.5 | 1,050 | 77 | 262K | Not specified | PriorityFlex | ||
Qwen3.6-35B-A3B Qwen | text-generation | 52.5 | 332.5 | — | 262K | Not specified | PriorityFlex | |
Step-3.7-Flash stepfun-ai | text-generation | 70 | 403 | 14 | 262K | Not specified | — | |
gpt-6-astra openai | text-generation | 3,500 | 17,500 | 350 | 1M | 128,000 | — | |
all-MiniLM-L12-v2 sentence-transformers | embeddings | 3 | — | — | 512 | Not specified | — | |
all-MiniLM-L6-v2 sentence-transformers | embeddings | 3 | — | — | 512 | Not specified | — | |
all-mpnet-base-v2 sentence-transformers | embeddings | 3 | — | — | 512 | Not specified | — | |
Audio8-TTS-Preview-0.6b Audio8 | text-to-speech | 1,750 | — | — | — | Not specified | — | |
bge-base-en-v1.5 BAAI | embeddings | 1.75 | 1.75 | — | 512 | Not specified | — | |
bge-en-icl BAAI | embeddings | 5 | — | — | 8k | Not specified | — | |
| embeddings | 5 | — | — | 512 | Not specified | — | ||
bge-m3 BAAI | embeddings | 5 | — | — | 8k | Not specified | — | |
bge-m3-multi BAAI | embeddings | 5 | — | — | 8k | Not specified | — | |
blur_background Bria | text-to-image | 14 | — | — | image | Not specified | — | |
Bria-3.2 Bria | text-to-image | 14 | — | — | image | Not specified | — | |
Bria-3.2-vector Bria | text-to-image | 14 | — | — | image | Not specified | — | |
chatterbox-multilingual ResembleAI | text-to-speech | 350 | — | — | speech | Not specified | — | |
chatterbox-turbo ResembleAI | text-to-speech | 350 | — | — | speech | Not specified | — | |
claude-fable-5 anthropic | text-generation | 3,500 | 17,500 | — | 1M | Not specified | — | |
claude-haiku-4-5 anthropic | text-generation | 350 | 1,750 | — | 200K | Not specified | — | |
claude-opus-4-7 anthropic | text-generation | 1,750 | 8,750 | — | 1M | Not specified | — | |
claude-opus-4-8 anthropic | text-generation | 1,750 | 8,750 | — | 1M | Not specified | — | |
claude-opus-5 anthropic | text-generation | 1,750 | 8,750 | — | 1M | Not specified | — | |
claude-sonnet-4-6 anthropic | text-generation | 1,050 | 5,250 | — | 1M | Not specified | — | |
claude-sonnet-5 anthropic | text-generation | 700 | 3,500 | — | 1M | Not specified | — | |
clip-vit-base-patch32 openai | zero-shot-image-classification | 0.175 | — | — | image-classification | Not specified | — | |
| zero-shot-image-classification | 0.175 | — | — | image-classification | Not specified | — | ||
creative ClarityAI | text-to-image | 17.5 | — | — | image | Not specified | — | |
DeepSeek-R1-0528 deepseek-ai | text-generation | 175 | 753 | 123 | 163K | Not specified | Flex | |
DeepSeek-V3 deepseek-ai | text-generation | 112 | 312 | — | 131K | Not specified | Flex | |
DeepSeek-V3-0324 deepseek-ai | text-generation | 70 | 270 | 47.25 | 163K | Not specified | PriorityFlex | |
DeepSeek-V3.1 deepseek-ai | text-generation | 74 | 277 | 46 | 163k | Not specified | Flex | |
DeepSeek-V4-Flash-Vision-Exp deepseek-ai | text-generation | 154 | 462 | 49 | 1M | Not specified | PriorityFlex | |
e5-base-v2 intfloat | embeddings | 3 | — | — | 512 | Not specified | — | |
e5-large-v2 intfloat | embeddings | 5 | — | — | 512 | Not specified | — | |
embeddinggemma-300m google | embeddings | 0.6533 | — | — | 2K | Not specified | — | |
enhance Bria | text-to-image | 14 | — | — | image | Not specified | — | |
erase Bria | text-to-image | 14 | — | — | image | Not specified | — | |
erase_foreground Bria | text-to-image | 14 | — | — | image | Not specified | — | |
expand Bria | text-to-image | 14 | — | — | — | Not specified | — | |
fibo Bria | text-to-image | 14 | — | — | image | Not specified | — | |
fibo_edit Bria | text-to-image | 14 | — | — | image | Not specified | — | |
fibo_edit-1.5 Bria | text-to-image | 16 | — | — | image | Not specified | — | |
fibo-1.5 Bria | text-to-image | 16 | — | — | image | Not specified | — | |
FLUX-1-dev black-forest-labs | text-to-image | 3.15 | — | — | Image | Not specified | — | |
FLUX-1-Redux-dev black-forest-labs | text-to-image | 4.2 | — | — | Image | Not specified | — | |
FLUX-1-schnell black-forest-labs | text-to-image | 0.175 | — | — | Image | Not specified | — | |
FLUX-1.1-pro black-forest-labs | text-to-image | 14 | — | — | Image | Not specified | — | |
FLUX-2-dev black-forest-labs | text-to-image | 3.5 | — | — | Image | Not specified | — | |
FLUX-2-klein-4b black-forest-labs | text-to-image | 4.9 | — | — | Image | Not specified | — | |
FLUX-2-klein-9b black-forest-labs | text-to-image | 5.25 | — | — | Image | Not specified | — | |
FLUX-2-max black-forest-labs | text-to-image | 24.5 | — | — | Image | Not specified | — | |
FLUX-2-pro black-forest-labs | text-to-image | 5.25 | — | — | Image | Not specified | — | |
FLUX-pro black-forest-labs | text-to-image | 16.3333 | — | — | Image | Not specified | — | |
FLUX.1-Kontext-dev black-forest-labs | text-to-image | 3.5 | — | — | Image | Not specified | — | |
gemini-2.5-flash google | text-generation | 105 | 875 | — | 1M | Not specified | — | |
gemini-2.5-pro google | text-generation | 437.5 | 3,500 | — | 1M | Not specified | — | |
gemini-3.1-flash-lite google | text-generation | 87.5 | 525 | — | 1M | Not specified | — | |
gemini-3.1-pro google | text-generation | 700 | 4,200 | — | 1M | Not specified | — | |
gemini-3.5-flash google | text-generation | 525 | 3,150 | — | 1M | Not specified | — | |
gemma-3-12b-it google | text-generation | 17.5 | 52.5 | — | 131K | Not specified | PriorityFlex | |
gemma-3-27b-it google | text-generation | 28 | 56 | — | 131K | Not specified | PriorityFlex | |
gemma-3-4b-it google | text-generation | 17.5 | 35 | — | 131K | Not specified | PriorityFlex | |
gemma-4-31B-it-turbo google | text-generation | 42 | 129.5 | — | 262K | Not specified | PriorityFlex | |
gemma-4-31B-it-Ultra google | text-generation | 94.5 | 266 | — | 262K | Not specified | — | |
gemma-4-E4B-it google | text-generation | 7 | 35 | — | 131K | Not specified | PriorityFlex | |
gen_fill Bria | text-to-image | 14 | — | — | image | Not specified | — | |
GLM-4.6 zai-org | text-generation | 150.5 | 609 | 28 | 200K | Not specified | — | |
GLM-4.7 zai-org | text-generation | 140 | 613 | 28 | 200K | Not specified | — | |
GLM-5.3 zai-org | text-generation | 490 | 1,540 | 91 | 1M | Not specified | — | |
GLM-5.3-Flash zai-org | text-generation | 60 | 200 | 12 | 1M | Not specified | — | |
gpt-4o-mini openai | text-generation | 52.5 | 210 | 26.25 | 128K | Not specified | — | |
gpt-5.3-codex openai | text-generation | 613 | 4,900 | 61.25 | 400K | 128,000 | — | |
gpt-5.4 openai | text-generation | 875 | 5,250 | 87.5 | 1M | 128,000 | — | |
gpt-5.4-mini openai | text-generation | 263 | 1,575 | 26.25 | 400K | 128,000 | — | |
gpt-5.4-nano openai | text-generation | 70 | 438 | 7 | 400k | 128,000 | — | |
gpt-5.4-pro openai | text-generation | 10,500 | 63,000 | 10,500 | 1M | Not specified | — | |
gpt-5.5 openai | text-generation | 1,750 | 10,500 | 175 | 1M | 128,000 | — | |
gpt-5.5-pro openai | text-generation | 10,500 | 63,000 | 10,500 | 1M | 128,000 | — | |
gpt-5.6-luna openai | text-generation | 70 | 420 | 7 | 1M | 128,000 | — | |
gpt-5.6-sol openai | text-generation | 1,400 | 7,000 | 140 | 1M | 128,000 | — | |
gpt-5.6-terra openai | text-generation | 700 | 4,200 | 70 | 1M | 128,000 | — | |
gpt-image-2 openai | text-to-image | 5,250 | — | — | image | Not specified | — | |
gpt-image-2.5-flare openai | text-to-image | 10,500 | — | — | image | Not specified | — | |
gpt-image-2.5-sunburst openai | text-to-image | 10,500 | — | — | image | Not specified | — | |
gpt-oss-120b openai | text-generation | 13.65 | 66.5 | — | 131K | Not specified | — | |
gpt-oss-120b-Turbo openai | text-generation | 52.5 | 210 | — | 131K | Not specified | Flex | |
gpt-oss-120b-Ultra openai | text-generation | 70 | 333 | — | 131K | Not specified | — | |
gpt-oss-20b openai | text-generation | 10.5 | 49 | — | 131K | Not specified | PriorityFlex | |
granite-4.2-30b ibm-granite | text-generation | 64 | 260 | 16 | 131K | Not specified | — | |
granite-4.2-8b ibm-granite | text-generation | 24 | 100 | 6 | 131K | Not specified | — | |
Hermes-3-Llama-3.1-405B NousResearch | text-generation | 350 | 350 | — | 131K | Not specified | Flex | |
Hermes-3-Llama-3.1-70B NousResearch | text-generation | 245 | 245 | — | 131k | Not specified | PriorityFlex | |
HiggsAudioV2.5 bosonai | text-to-speech | 7,000 | — | — | speech | Not specified | — | |
Hy3 tencent | text-generation | 49 | 203 | 12.25 | 262K | Not specified | — | |
Inkling thinkingmachines | text-generation | 350 | 1,418 | 60 | 131K | Not specified | — | |
Inkling-Small thinkingmachines | text-generation | 203 | 504 | 40.6 | 524K | Not specified | — | |
Janus-Pro-1B deepseek-ai | text-to-image | 1 | — | — | image | Not specified | — | |
Janus-Pro-7B deepseek-ai | text-to-image | 1 | — | — | image | Not specified | — | |
Kimi-K3 moonshotai | text-generation | 998 | 4,988 | 100 | 1M | Not specified | 5m1h | |
Kokoro-82M hexgrad | text-to-speech | 217 | — | — | speech | Not specified | — | |
L3-8B-Lunaris-v1-Turbo Sao10K | text-generation | 14 | 18 | — | 8K | Not specified | Flex | |
L3.1-70B-Euryale-v2.2 Sao10K | text-generation | 298 | 298 | — | 131K | Not specified | Flex | |
Ling-3.0-flash inclusionAI | text-generation | 21 | 63 | 4.2 | 131K | Not specified | — | |
Ling-3.0-flash-Fin inclusionAI | text-generation | 24 | 72 | 4.8 | 262K | Not specified | — | |
Ling-3.0-flash-VL inclusionAI | text-generation | 24 | 72 | 4.8 | 131K | Not specified | — | |
Llama-3.3-70B-Instruct-Turbo meta-llama | text-generation | 35 | 112 | — | 131K | Not specified | Flex | |
Llama-4-Maverick-17B-128E-Instruct-FP8 meta-llama | text-generation | 52.5 | 210 | — | 1M | Not specified | PriorityFlex | |
Llama-4-Scout-17B-16E-Instruct meta-llama | text-generation | 35 | 105 | — | 327K | Not specified | PriorityFlex | |
Llama-Guard-4-12B meta-llama | text-generation | 63 | 63 | — | 163k | Not specified | PriorityFlex | |
| embeddings | 3.5 | — | — | 10K | Not specified | — | ||
| reranker | 3.5 | — | — | 10K | Not specified | — | ||
Meta-Llama-3.1-70B-Instruct-Turbo meta-llama | text-generation | 140 | 140 | — | 131K | Not specified | Flex | |
Meta-Llama-3.1-8B-Instruct-Turbo meta-llama | text-generation | 7 | 14 | — | 131K | Not specified | Flex | |
MiMo-V2.5-tts XiaomiMiMo | text-to-speech | 1,634 | — | — | speech | Not specified | — | |
MiMo-V2.5-tts-voiceclone XiaomiMiMo | text-to-speech | 10 | — | — | speech | Not specified | — | |
MiMo-V2.5-tts-voicedesign XiaomiMiMo | text-to-speech | 654 | — | — | speech | Not specified | — | |
MiniMax-M2.7-Turbo MiniMaxAI | text-generation | 133 | 595 | 24.5 | 196K | Not specified | — | |
MiniMax-M3 MiniMaxAI | text-generation | 105 | 420 | 21 | 524K | Not specified | Flex | |
Mistral-Nemo-Instruct-2407 mistralai | text-generation | 7 | 14 | — | 131K | Not specified | Flex | |
Mistral-Small-24B-Instruct-2501 mistralai | text-generation | 17.5 | 28 | — | 32K | Not specified | Flex | |
Mistral-Small-3.2-24B-Instruct-2506 mistralai | text-generation | 26.25 | 70 | — | 131K | Not specified | PriorityFlex | |
multilingual-e5-large intfloat | embeddings | 5 | — | — | 512 | Not specified | — | |
multilingual-e5-large-instruct intfloat | embeddings | 5 | — | — | 512 | Not specified | — | |
Muse-Glimmer-30B meta-models | text-generation | 105 | 420 | 14 | 131K | Not specified | — | |
Nemotron-3-Embed-1B-BF16 nvidia | embeddings | 5.25 | — | — | 32K | Not specified | — | |
| embeddings | 3.5 | — | — | 32K | Not specified | — | ||
Nemotron-3-Embed-8B nvidia | embeddings | 12.25 | — | — | 32K | Not specified | — | |
Nemotron-3-Nano-30B-A3B nvidia | text-generation | 17.5 | 70 | — | 262K | Not specified | PriorityFlex | |
| automatic-speech-recognition | 0.07 | — | — | — | Not specified | — | ||
| text-generation | 70 | 70 | — | 131K | Not specified | — | ||
orpheus-3b-0.1-ft canopylabs | text-to-speech | 2,450 | — | — | speech | Not specified | — | |
p-image PrunaAI | text-to-image | 2.4 | — | — | image | Not specified | — | |
p-image-Edit PrunaAI | text-to-image | 3.5 | — | — | image | Not specified | — | |
p-video PrunaAI | text-to-video | 14 | — | — | video | Not specified | — | |
p-video-avatar PrunaAI | text-to-video | 15.75 | — | — | video | Not specified | — | |
phi-4 microsoft | text-generation | 24.5 | 49 | — | 16K | Not specified | Flex | |
Pixverse-6-I2V Pixverse | text-to-video | 41 | — | — | video | Not specified | — | |
Pixverse-6-T2V Pixverse | text-to-video | 41 | — | — | video | Not specified | — | |
Pixverse-T2V Pixverse | text-to-video | 70 | — | — | video | Not specified | — | |
Pixverse-T2V-HD Pixverse | text-to-video | 140 | — | — | video | Not specified | — | |
Qwen-Image-Edit Qwen | text-to-image | 8.75 | — | — | image | Not specified | — | |
| text-to-image | 24.5 | — | — | image | Not specified | — | ||
Qwen-Image-Max Qwen | text-to-image | 26.25 | — | — | Image | Not specified | — | |
| text-generation | 126 | 140 | — | 32K | Not specified | Flex | ||
Qwen3-14B Qwen | text-generation | 42 | 84 | — | 32K | Not specified | PriorityFlex | |
| text-generation | 32 | 193 | — | 262K | Not specified | PriorityFlex | ||
Qwen3-30B-A3B Qwen | text-generation | 39.2 | 164 | — | 32K | Not specified | PriorityFlex | |
Qwen3-32B Qwen | text-generation | 28 | 98 | — | 32K | Not specified | PriorityFlex | |
Qwen3-ASR-0.6B Qwen | automatic-speech-recognition | 0.08 | — | — | — | Not specified | — | |
Qwen3-ASR-1.7B Qwen | automatic-speech-recognition | 0.2 | — | — | — | Not specified | — | |
| text-generation | 105 | 350 | 35 | 262K | Not specified | Flex | ||
| embeddings | 3.5 | — | — | 32K | Not specified | — | ||
| embeddings | 6.6 | — | — | 32K | Not specified | — | ||
| embeddings | 3.5 | — | — | 32K | Not specified | — | ||
| text-generation | 31.5 | 385 | — | 262K | Not specified | PriorityFlex | ||
| reranker | 3.5 | — | — | 32K | Not specified | — | ||
| reranker | 8.75 | — | — | 32K | Not specified | — | ||
| reranker | 17.5 | — | — | 32K | Not specified | — | ||
| text-generation | 70 | 308 | 38.5 | 262K | Not specified | PriorityFlex | ||
| text-generation | 52.5 | 210 | — | 262K | Not specified | PriorityFlex | ||
| text-generation | 102 | 840 | — | 262K | Not specified | PriorityFlex | ||
Qwen3.5-27B Qwen | text-generation | 91 | 910 | — | 262K | Not specified | PriorityFlex | |
Qwen3.5-35B-A3B Qwen | text-generation | 49 | 350 | 17.5 | 262K | Not specified | PriorityFlex | |
Qwen3.5-9B Qwen | text-generation | 35 | 52.5 | — | 262K | Not specified | PriorityFlex | |
Qwen3.6-27B Qwen | text-generation | 112 | 1,120 | — | 262K | Not specified | PriorityFlex | |
Qwen3.7-Max Qwen | text-generation | 2,188 | 6,475 | 438 | 256K | Not specified | — | |
| text-generation | 700 | 2,100 | 70 | 262K | Not specified | — | ||
Qwen3.8-27B Qwen | text-generation | 140 | 1,050 | 14 | 262K | Not specified | — | |
Qwen3.8-Flash Qwen | text-generation | 40 | 140 | 5 | 1M | Not specified | — | |
Qwen3.8-Max Qwen | text-generation | 578 | 1,733 | 73 | 256K | Not specified | — | |
realtime-tts-1.5-max inworld-ai | text-to-speech | 17,500 | — | — | speech | Not specified | — | |
realtime-tts-1.5-mini inworld-ai | text-to-speech | 8,750 | — | — | speech | Not specified | — | |
realtime-tts-2 inworld-ai | text-to-speech | 12,250 | — | — | speech | Not specified | — | |
| text-to-image | 6.3 | — | — | image | Not specified | — | ||
| text-to-image | 14 | — | — | image | Not specified | — | ||
sdxl-turbo stabilityai | text-to-image | 0.07 | — | — | image | Not specified | — | |
Seed-1.8 ByteDance | text-generation | 175 | 1,400 | 35 | 256K | Not specified | — | |
Seed-2.0-code ByteDance | text-generation | 350 | 2,100 | 70 | 256K | Not specified | — | |
Seed-2.0-mini ByteDance | text-generation | 70 | 280 | 70 | 256K | Not specified | — | |
Seed-2.0-pro ByteDance | text-generation | 350 | 2,100 | 70 | 256K | Not specified | — | |
Seedance-1.5-Pro ByteDance | text-to-video | 420 | — | — | video | Not specified | — | |
Seedance-2.0 ByteDance | text-to-video | 2,450 | — | — | video | Not specified | — | |
Seedream-4 ByteDance | text-to-image | 14 | — | — | image | Not specified | — | |
Seedream-4.5 ByteDance | text-to-image | 14 | — | — | image | Not specified | — | |
text-embedding-3-large openai | embeddings | 45.5 | 45.5 | — | 8191 | Not specified | — | |
text-embedding-3-small openai | embeddings | 7 | 7 | — | 8191 | Not specified | — | |
veo-3.1 google | text-to-video | 140 | — | — | video | Not specified | — | |
veo-3.1-fast google | text-to-video | 52.5 | — | — | Video | Not specified | — | |
| text-to-video | 49 | — | — | video | Not specified | — | ||
| text-to-video | 49 | — | — | video | Not specified | — | ||
| text-to-video | 49 | — | — | video | Not specified | — | ||
| text-to-video | 2.3 | — | — | video | Not specified | — | ||
Voxtral-Mini-3B-2507 mistralai | automatic-speech-recognition | 0.35 | — | — | 32K | Not specified | — | |
Voxtral-Small-24B-2507 mistralai | automatic-speech-recognition | 1.05 | — | — | 32K | Not specified | — | |
Wan2.2-T2V-A14B Wan-AI | text-to-video | 12.6 | — | — | video | Not specified | — | |
Wan2.6-I2V Wan-AI | text-to-video | 52.5 | — | — | video | Not specified | — | |
Wan2.6-Image-Edit Wan-AI | text-to-image | 10.5 | — | — | image | Not specified | — | |
Wan2.6-T2I Wan-AI | text-to-image | 10.5 | — | — | image | Not specified | — | |
Wan2.6-T2V Wan-AI | text-to-video | 52.5 | — | — | video | Not specified | — | |
Wan2.7-I2V Wan-AI | text-to-video | 52.5 | — | — | video | Not specified | — | |
Wan2.7-Image-Edit Wan-AI | text-to-image | 10.5 | — | — | image | Not specified | — | |
Wan2.7-R2V Wan-AI | text-to-video | 52.5 | — | — | video | Not specified | — | |
Wan3.0-Video Wan-AI | text-to-video | 70 | — | — | video | Not specified | — | |
whisper-large-v3 openai | automatic-speech-recognition | 0.1575 | — | — | speech-recognition | Not specified | — | |
whisper-large-v3-turbo openai | automatic-speech-recognition | 0.07 | — | — | speech-recognition | Not specified | — | |
DeepSeek-V4.1-Flash deepseek-ai | text-generation | 70 | 210 | 2.4 | 1,048,576 | Not specified | PriorityFlex |
— means not offered. Not specified means unknown.
