model directory

Every model, one endpoint.
Run it on your hardware or ours.

409 AI models — text, image, audio, embeddings — across 64 providers. Text models route through a single OpenAI-compatible gateway (your GPUs first, cloud when you need it); open models run free on hardware you own.

capabilities

409 models

AI21: Jamba Large 1.7
⚙ tools↓ self-hosttext
ai21/jamba-large-1.7
tools
in $2.20 · out $8.80 /1M256K ctx
AionLabs: Aion-2.0
⚙ toolstext
aion-labs/aion-2.0
toolsreasoning
in $0.88 · out $1.76 /1M131K ctx
AionLabs: Aion-3.0
⚙ toolstext
aion-labs/aion-3.0
toolsreasoning
in $3.30 · out $6.60 /1M131K ctx
AionLabs: Aion-3.0-Mini
⚙ toolstext
aion-labs/aion-3.0-mini
toolsreasoning
in $0.77 · out $1.54 /1M131K ctx
AionLabs: Aion-RP 1.0 (8B)
↓ self-hosttext
aion-labs/aion-rp-llama-3.1-8b
in $0.88 · out $1.76 /1M33K ctx
Wan 2.2
↓ self-hostvideo
alibaba/wan-2.2
video model
AllenAI: Olmo 3 32B Think
↓ self-hosttext
allenai/olmo-3-32b-think
reasoning
in $0.17 · out $0.55 /1M66K ctx
Amazon: Nova 2 Lite
⚙ toolstext
amazon/nova-2-lite-v1
visiontoolsreasoning
in $0.33 · out $2.75 /1M1M ctx
Amazon: Nova Lite 1.0
⚙ toolstext
amazon/nova-lite-v1
visiontools
in $0.066 · out $0.26 /1M300K ctx
Amazon: Nova Micro 1.0
⚙ toolstext
amazon/nova-micro-v1
tools
in $0.038 · out $0.15 /1M128K ctx
Amazon: Nova Premier 1.0
⚙ toolstext
amazon/nova-premier-v1
visiontools
in $2.75 · out $13.75 /1M1M ctx
Amazon: Nova Pro 1.0
⚙ toolstext
amazon/nova-pro-v1
visiontools
in $0.88 · out $3.52 /1M300K ctx
Magnum v4 72B
text
anthracite-org/magnum-v4-72b
in $3.30 · out $5.50 /1M16K ctx
Anthropic: Claude 3 Haiku
⚙ toolstext
anthropic/claude-3-haiku
visiontools
in $0.28 · out $1.38 /1M200K ctx
Anthropic: Claude Fable 5
⚙ toolstext
anthropic/claude-fable-5
visiontoolsreasoning
in $11.00 · out $55.00 /1M1M ctx
Anthropic: Claude Haiku 4.5
⚙ toolstext
anthropic/claude-haiku-4.5
visiontoolsreasoning
in $1.10 · out $5.50 /1M200K ctx
Anthropic: Claude Opus 4
⚙ toolstext
anthropic/claude-opus-4
visiontoolsreasoning
in $16.50 · out $82.50 /1M200K ctx
Anthropic: Claude Opus 4.1
⚙ toolstext
anthropic/claude-opus-4.1
visiontoolsreasoning
in $16.50 · out $82.50 /1M200K ctx
Anthropic: Claude Opus 4.5
⚙ toolstext
anthropic/claude-opus-4.5
visiontoolsreasoning
in $5.50 · out $27.50 /1M200K ctx
Anthropic: Claude Opus 4.6
⚙ toolstext
anthropic/claude-opus-4.6
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Opus 4.7
⚙ toolstext
anthropic/claude-opus-4.7
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Opus 4.8
⚙ toolstext
anthropic/claude-opus-4.8
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Claude Opus 5
⚙ toolstext
anthropic/claude-opus-5
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Sonnet 4
⚙ toolstext
anthropic/claude-sonnet-4
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Anthropic: Claude Sonnet 4.5
⚙ toolstext
anthropic/claude-sonnet-4.5
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Anthropic: Claude Sonnet 4.6
⚙ toolstext
anthropic/claude-sonnet-4.6
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Anthropic: Claude Sonnet 5
⚙ toolstext
anthropic/claude-sonnet-5
visiontoolsreasoning
in $2.20 · out $11.00 /1M1M ctx
Arcee AI: Trinity Large Thinking
⚙ toolstext
arcee-ai/trinity-large-thinking
toolsreasoning
in $0.24 · out $0.94 /1M262K ctx
Arcee AI: Virtuoso Large
⚙ toolstext
arcee-ai/virtuoso-large
tools
in $0.83 · out $1.32 /1M131K ctx
Baidu: ERNIE 4.5 VL 424B A47B
↓ self-hosttext
baidu/ernie-4.5-vl-424b-a47b
visionreasoning
in $0.46 · out $1.38 /1M123K ctx
ByteDance: UI-TARS 7B
text
bytedance/ui-tars-1.5-7b
vision
in $0.11 · out $0.22 /1M128K ctx
ByteDance Seed: Seed 1.6
⚙ toolstext
bytedance-seed/seed-1.6
visiontoolsreasoning
in $0.28 · out $2.20 /1M262K ctx
ByteDance Seed: Seed 1.6 Flash
⚙ toolstext
bytedance-seed/seed-1.6-flash
visiontoolsreasoning
in $0.083 · out $0.33 /1M262K ctx
ByteDance Seed: Seed-2.0-Lite
⚙ toolstext
bytedance-seed/seed-2.0-lite
visiontoolsreasoning
in $0.28 · out $2.20 /1M262K ctx
ByteDance Seed: Seed-2.0-Mini
⚙ toolstext
bytedance-seed/seed-2.0-mini
visiontoolsreasoning
in $0.11 · out $0.44 /1M262K ctx
ai4bharat/indictrans2-en-indic-1B
text
cloudflare/ai4bharat/indictrans2-en-indic-1B
in $0.38 · out $0.38 /1M
aisingapore/gemma-sea-lion-v4-27b-it
⚙ tools↓ self-hosttext
cloudflare/aisingapore/gemma-sea-lion-v4-27b-it
tools
in $0.39 · out $0.61 /1M128K ctx
baai/bge-base-en-v1.5
embeddings
cloudflare/baai/bge-base-en-v1.5
in $0.073 · out $0 /1M154K ctx
baai/bge-large-en-v1.5
embeddings
cloudflare/baai/bge-large-en-v1.5
in $0.22 · out $0 /1M
baai/bge-m3
embeddings
cloudflare/baai/bge-m3
in $0.013 · out $0 /1M60K ctx
baai/bge-reranker-base
other
cloudflare/baai/bge-reranker-base
in $0.003 · out $0 /1M
baai/bge-small-en-v1.5
embeddings
cloudflare/baai/bge-small-en-v1.5
in $0.022 · out $0 /1M
black-forest-labs/flux-1-schnell
image
cloudflare/black-forest-labs/flux-1-schnell
image model
black-forest-labs/flux-2-dev
image
cloudflare/black-forest-labs/flux-2-dev
image model
black-forest-labs/flux-2-klein-4b
image
cloudflare/black-forest-labs/flux-2-klein-4b
image model
black-forest-labs/flux-2-klein-9b
image
cloudflare/black-forest-labs/flux-2-klein-9b
image model
bytedance/stable-diffusion-xl-lightning
image
cloudflare/bytedance/stable-diffusion-xl-lightning
image model
deepgram/aura-1
audio
cloudflare/deepgram/aura-1
audio model
deepgram/aura-2-en
audio
cloudflare/deepgram/aura-2-en
audio model
deepgram/aura-2-es
audio
cloudflare/deepgram/aura-2-es
audio model
deepgram/flux
audio
cloudflare/deepgram/flux
audio model
deepgram/nova-3
audio
cloudflare/deepgram/nova-3
audio model
deepseek-ai/deepseek-r1-distill-qwen-32b
⚙ tools↓ self-hosttext
cloudflare/deepseek-ai/deepseek-r1-distill-qwen-32b
tools
in $0.55 · out $5.37 /1M80K ctx
google/embeddinggemma-300m
⚙ tools↓ self-hostembeddings
cloudflare/google/embeddinggemma-300m
tools
embeddings model
google/gemma-4-26b-a4b-it
⚙ tools↓ self-hosttext
cloudflare/google/gemma-4-26b-a4b-it
tools
in $0.11 · out $0.33 /1M256K ctx
huggingface/distilbert-sst-2-int8
other
cloudflare/huggingface/distilbert-sst-2-int8
in $0.029 · out $0 /1M
ibm-granite/granite-4.0-h-micro
⚙ tools↓ self-hosttext
cloudflare/ibm-granite/granite-4.0-h-micro
tools
in $0.019 · out $0.12 /1M131K ctx
leonardo/lucid-origin
image
cloudflare/leonardo/lucid-origin
image model
leonardo/phoenix-1.0
image
cloudflare/leonardo/phoenix-1.0
image model
llava-hf/llava-1.5-7b-hf
multimodal
cloudflare/llava-hf/llava-1.5-7b-hf
vision
multimodal model
lykon/dreamshaper-8-lcm
image
cloudflare/lykon/dreamshaper-8-lcm
image model
meta/llama-3.2-11b-vision-instruct
⚙ tools↓ self-hosttext
cloudflare/meta/llama-3.2-11b-vision-instruct
tools
in $0.053 · out $0.74 /1M128K ctx
meta/llama-3.2-1b-instruct
⚙ tools↓ self-hosttext
cloudflare/meta/llama-3.2-1b-instruct
tools
in $0.030 · out $0.22 /1M60K ctx
meta/llama-4-scout-17b-16e-instruct
⚙ tools↓ self-hosttext
cloudflare/meta/llama-4-scout-17b-16e-instruct
tools
in $0.30 · out $0.94 /1M131K ctx
meta/llama-guard-3-8b
⚙ tools↓ self-hosttext
cloudflare/meta/llama-guard-3-8b
tools
in $0.53 · out $0.033 /1M131K ctx
meta/m2m100-1.2b
text
cloudflare/meta/m2m100-1.2b
in $0.38 · out $0.38 /1M
microsoft/resnet-50
other
cloudflare/microsoft/resnet-50
other model
mistralai/mistral-small-3.1-24b-instruct
⚙ tools↓ self-hosttext
cloudflare/mistralai/mistral-small-3.1-24b-instruct
tools
in $0.39 · out $0.61 /1M128K ctx
moondream/moondream3.1-9B-A2B
multimodal
cloudflare/moondream/moondream3.1-9B-A2B
vision
in $0.33 · out $1.10 /1M
myshell-ai/melotts
audio
cloudflare/myshell-ai/melotts
audio model
nvidia/nemotron-3-120b-a12b
⚙ tools↓ self-hosttext
cloudflare/nvidia/nemotron-3-120b-a12b
tools
in $0.55 · out $1.65 /1M256K ctx
openai/whisper
audio
cloudflare/openai/whisper
audio model
openai/whisper-large-v3-turbo
audio
cloudflare/openai/whisper-large-v3-turbo
audio model
openai/whisper-tiny-en
audio
cloudflare/openai/whisper-tiny-en
audio model
pfnet/plamo-embedding-1b
embeddings
cloudflare/pfnet/plamo-embedding-1b
in $0.020 · out $0 /1M
qwen/qwen2.5-coder-32b-instruct
⚙ tools↓ self-hosttext
cloudflare/qwen/qwen2.5-coder-32b-instruct
tools
in $0.73 · out $1.10 /1M33K ctx
qwen/qwen3-30b-a3b-fp8
⚙ tools↓ self-hosttext
cloudflare/qwen/qwen3-30b-a3b-fp8
tools
in $0.056 · out $0.37 /1M33K ctx
qwen/qwen3-embedding-0.6b
⚙ tools↓ self-hostembeddings
cloudflare/qwen/qwen3-embedding-0.6b
tools
in $0.013 · out $0 /1M8K ctx
qwen/qwq-32b
⚙ tools↓ self-hosttext
cloudflare/qwen/qwq-32b
tools
in $0.73 · out $1.10 /1M24K ctx
runwayml/stable-diffusion-v1-5-img2img
image
cloudflare/runwayml/stable-diffusion-v1-5-img2img
image model
runwayml/stable-diffusion-v1-5-inpainting
image
cloudflare/runwayml/stable-diffusion-v1-5-inpainting
image model
stabilityai/stable-diffusion-xl-base-1.0
image
cloudflare/stabilityai/stable-diffusion-xl-base-1.0
image model
Venice: Uncensored
↓ self-hosttext
cognitivecomputations/dolphin-mistral-24b-venice-edition
in $0.22 · out $0.99 /1M128K ctx
Cohere: Command A
↓ self-hosttext
cohere/command-a
in $2.75 · out $11.00 /1M256K ctx
Cohere: Command R (08-2024)
⚙ tools↓ self-hosttext
cohere/command-r-08-2024
tools
in $0.17 · out $0.66 /1M128K ctx
Cohere: Command R+ (08-2024)
⚙ tools↓ self-hosttext
cohere/command-r-plus-08-2024
tools
in $2.75 · out $11.00 /1M128K ctx
Cohere: Command R7B (12-2024)
↓ self-hosttext
cohere/command-r7b-12-2024
in $0.041 · out $0.17 /1M128K ctx
Deep Cogito: Cogito v2.1 671B
text
deepcogito/cogito-v2.1-671b
reasoning
in $1.38 · out $1.38 /1M128K ctx
DeepSeek: DeepSeek V3
⚙ tools↓ self-hosttext
deepseek/deepseek-chat
tools
in $0.22 · out $0.88 /1M164K ctx
DeepSeek: DeepSeek V3 0324
⚙ tools↓ self-hosttext
deepseek/deepseek-chat-v3-0324
tools
in $0.30 · out $1.23 /1M164K ctx
DeepSeek: DeepSeek V3.1
⚙ tools↓ self-hosttext
deepseek/deepseek-chat-v3.1
toolsreasoning
in $0.28 · out $1.05 /1M164K ctx
DeepSeek: R1
⚙ tools↓ self-hosttext
deepseek/deepseek-r1
toolsreasoning
in $0.77 · out $2.75 /1M164K ctx
DeepSeek: R1 0528
⚙ tools↓ self-hosttext
deepseek/deepseek-r1-0528
toolsreasoning
in $0.55 · out $2.37 /1M164K ctx
DeepSeek: R1 Distill Llama 70B
↓ self-hosttext
deepseek/deepseek-r1-distill-llama-70b
reasoning
in $0.88 · out $0.88 /1M8K ctx
DeepSeek: DeepSeek V3.1 Terminus
⚙ tools↓ self-hosttext
deepseek/deepseek-v3.1-terminus
toolsreasoning
in $0.30 · out $1.10 /1M164K ctx
DeepSeek: DeepSeek V3.2
⚙ tools↓ self-hosttext
deepseek/deepseek-v3.2
toolsreasoning
in $0.30 · out $0.44 /1M164K ctx
DeepSeek: DeepSeek V3.2 Exp
⚙ tools↓ self-hosttext
deepseek/deepseek-v3.2-exp
toolsreasoning
in $0.30 · out $0.45 /1M164K ctx
DeepSeek: DeepSeek V4 Flash
⚙ tools↓ self-hosttext
deepseek/deepseek-v4-flash
toolsreasoning
in $0.15 · out $0.31 /1M1.0M ctx
DeepSeek: DeepSeek V4 Pro
⚙ tools↓ self-hosttext
deepseek/deepseek-v4-pro
toolsreasoning
in $0.48 · out $0.96 /1M1.0M ctx
Google: Nano Banana (Gemini 2.5 Flash Image)
image
google/gemini-2.5-flash-image
vision
in $0.33 · out $2.75 /1M33K ctx
Google: Gemini 2.5 Pro Preview 06-05
⚙ toolstext
google/gemini-2.5-pro-preview
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
Google: Gemini 2.5 Pro Preview 05-06
⚙ toolstext
google/gemini-2.5-pro-preview-05-06
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
Google: Gemini 3 Flash Preview
⚙ toolstext
google/gemini-3-flash-preview
visionaudio-intoolsreasoning
in $0.55 · out $3.30 /1M1.0M ctx
Google: Nano Banana Pro (Gemini 3 Pro Image)
⚙ toolsimage
google/gemini-3-pro-image
visiontoolsreasoning
in $2.20 · out $13.20 /1M131K ctx
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
image
google/gemini-3-pro-image-preview
visionreasoning
in $2.20 · out $13.20 /1M66K ctx
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
image
google/gemini-3.1-flash-image
visionreasoning
in $0.55 · out $3.30 /1M131K ctx
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
image
google/gemini-3.1-flash-image-preview
visionreasoning
in $0.55 · out $3.30 /1M66K ctx
Google: Gemini 3.1 Flash Lite
⚙ toolstext
google/gemini-3.1-flash-lite
visionaudio-intoolsreasoning
in $0.28 · out $1.65 /1M1.0M ctx
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
image
google/gemini-3.1-flash-lite-image
visionreasoning
in $0.28 · out $1.65 /1M66K ctx
Google: Gemini 3.1 Flash Lite Preview
⚙ toolstext
google/gemini-3.1-flash-lite-preview
visionaudio-intoolsreasoning
in $0.28 · out $1.65 /1M1.0M ctx
Google: Gemini 3.1 Pro Preview
⚙ toolstext
google/gemini-3.1-pro-preview
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
Google: Gemini 3.1 Pro Preview Custom Tools
⚙ toolstext
google/gemini-3.1-pro-preview-customtools
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
Google: Gemini 3.5 Flash
⚙ toolstext
google/gemini-3.5-flash
visionaudio-intoolsreasoning
in $1.65 · out $9.90 /1M1.0M ctx
Google: Gemini 3.5 Flash Lite
⚙ toolstext
google/gemini-3.5-flash-lite
visionaudio-intoolsreasoning
in $0.33 · out $2.75 /1M1.0M ctx
Google: Gemini 3.6 Flash
⚙ toolstext
google/gemini-3.6-flash
visionaudio-intoolsreasoning
in $1.65 · out $8.25 /1M1.0M ctx
Google: Gemma 2 27B
↓ self-hosttext
google/gemma-2-27b-it
in $0.71 · out $0.71 /1M8K ctx
Google: Gemma 3 12B
⚙ tools↓ self-hosttext
google/gemma-3-12b-it
visiontools
in $0.055 · out $0.17 /1M131K ctx
Google: Gemma 3 27B
⚙ tools↓ self-hosttext
google/gemma-3-27b-it
visiontools
in $0.088 · out $0.50 /1M262K ctx
Google: Gemma 3 4B
↓ self-hosttext
google/gemma-3-4b-it
vision
in $0.055 · out $0.11 /1M131K ctx
Google: Gemma 3n 4B
↓ self-hosttext
google/gemma-3n-e4b-it
in $0.066 · out $0.13 /1M33K ctx
Google: Gemma 4 31B
⚙ tools↓ self-hosttext
google/gemma-4-31b-it
visiontoolsreasoning
in $0.15 · out $0.44 /1M262K ctx
Imagen 4
image
google/imagen-4
image model
Google: Lyria 3 Clip Preview
audio
google/lyria-3-clip-preview
vision
audio model1.0M ctx
Google: Lyria 3 Pro Preview
audio
google/lyria-3-pro-preview
vision
audio model1.0M ctx
Veo 3.1
video
google/veo-3.1
video model
Veo 3.1 Lite
video
google/veo-3.1-lite
video model
Google: Gemini 2.5 Flash
⚙ toolstext
google/gemini-2.5-flash
visionaudio-intoolsreasoning
in $0.33 · out $2.75 /1M1.0M ctx
Google: Gemini 2.5 Flash Lite
⚙ toolstext
google/gemini-2.5-flash-lite
visionaudio-intoolsreasoning
in $0.11 · out $0.44 /1M1.0M ctx
Google: Gemini 2.5 Pro
⚙ toolstext
google/gemini-2.5-pro
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
MythoMax 13B
text
gryphe/mythomax-l2-13b
in $0.066 · out $0.066 /1M8K ctx
Cybersecurity BaronLLM Offensive Security LLM Q6 K
↓ self-hosttext
hf/AlicanKiraz0/Cybersecurity-BaronLLM_Offensive_Security_LLM_Q6_K_GGUF
text model
MiniCPM5 1B Claude Opus Fable5 Thinking
⚙ tools↓ self-hosttext
hf/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF
tools
text model
Qwopus GLM 18B Merged
⚙ tools↓ self-hosttext
hf/Jackrong/Qwopus-GLM-18B-Merged-GGUF
tools
text model
LFM2.5 8B A1B
↓ self-hosttext
hf/LiquidAI/LFM2.5-8B-A1B-GGUF
text model
LocoOperator 4B
↓ self-hosttext
hf/LocoreMind/LocoOperator-4B
text model
Meta Llama 3 8B Instruct
⚙ tools↓ self-hosttext
hf/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF
tools
text model
Qwen2.5 Coder 7B Instruct
⚙ tools↓ self-hosttext
hf/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF
tools
text model
Triplex
↓ self-hosttext
hf/SciPhi/Triplex
text model
Qwen3 14B Claude 4.5 Opus High Reasoning Distill
⚙ tools↓ self-hosttext
hf/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF
tools
text model
Llama 2 7B Chat
⚙ tools↓ self-hosttext
hf/TheBloke/Llama-2-7B-Chat-GGUF
tools
text model
Mistral 7B Instruct v0.1
⚙ tools↓ self-hosttext
hf/TheBloke/Mistral-7B-Instruct-v0.1-GGUF
tools
text model
Mistral 7B Instruct v0.2
⚙ tools↓ self-hosttext
hf/TheBloke/Mistral-7B-Instruct-v0.2-GGUF
tools
text model
Mistral 7B OpenOrca
⚙ tools↓ self-hosttext
hf/TheBloke/Mistral-7B-OpenOrca-GGUF
tools
text model
Mistral 7B v0.1
⚙ tools↓ self-hosttext
hf/TheBloke/Mistral-7B-v0.1-GGUF
tools
text model
phi 2
↓ self-hosttext
hf/TheBloke/phi-2-GGUF
text model
deepseek v4
⚙ tools↓ self-hosttext
hf/antirez/deepseek-v4-gguf
tools
text model
DeepSeek R1 Distill Qwen 14B
⚙ tools↓ self-hosttext
hf/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF
tools
text model
Ornith 1.0 35B
↓ self-hosttext
hf/deepreinforce-ai/Ornith-1.0-35B-GGUF
text model
Ornith 1.0 9B
↓ self-hosttext
hf/deepreinforce-ai/Ornith-1.0-9B-GGUF
text model
sqlcoder 7b 2
↓ self-hosttext
hf/defog/sqlcoder-7b-2
text model
Gemma 4 31B JANG 4M CRACK
⚙ tools↓ self-hosttext
hf/douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF
tools
text model
gemma 2b
⚙ tools↓ self-hosttext
hf/google/gemma-2b
tools
text model
gemma 2b it
⚙ tools↓ self-hosttext
hf/google/gemma-2b-it
tools
text model
gemma 7b
⚙ tools↓ self-hosttext
hf/google/gemma-7b
tools
text model
gemma 7b it
⚙ tools↓ self-hosttext
hf/google/gemma-7b-it
tools
text model
Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
⚙ tools↓ self-hosttext
hf/hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
tools
text model
Meta Llama 3.1 8B Instruct
⚙ tools↓ self-hosttext
hf/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF
tools
text model
Phi 3 mini 4k instruct
↓ self-hosttext
hf/microsoft/Phi-3-mini-4k-instruct-gguf
text model
bitnet b1.58 2B 4T
↓ self-hosttext
hf/microsoft/bitnet-b1.58-2B-4T-gguf
text model
Biggie SmoLlm 0.15B Base
↓ self-hosttext
hf/nisten/Biggie-SmoLlm-0.15B-Base
text model
Bonsai 27B
↓ self-hosttext
hf/prism-ml/Bonsai-27B-gguf
text model
Bonsai 8B
↓ self-hosttext
hf/prism-ml/Bonsai-8B-gguf
text model
Ternary Bonsai 27B
↓ self-hosttext
hf/prism-ml/Ternary-Bonsai-27B-gguf
text model
Llama3.1 8B Chinese Chat
⚙ tools↓ self-hosttext
hf/shenzhi-wang/Llama3.1-8B-Chinese-Chat
tools
text model
stable code 3b
↓ self-hosttext
hf/stabilityai/stable-code-3b
text model
DeepSeek R1 0528 Qwen3 8B
⚙ tools↓ self-hosttext
hf/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF
tools
text model
DeepSeek R1 Distill Llama 8B
⚙ tools↓ self-hosttext
hf/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
tools
text model
GLM 4.7 Flash REAP 23B A3B
⚙ tools↓ self-hosttext
hf/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF
tools
text model
gemma 4 12B agentic fable5 composer2.5 v2 3.5x tau2
⚙ tools↓ self-hosttext
hf/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
tools
text model
gemma 4 12B coder fable5 composer2.5 v1
⚙ tools↓ self-hosttext
hf/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
tools
text model
IBM: Granite 4.1 8B
⚙ tools↓ self-hosttext
ibm-granite/granite-4.1-8b
tools
in $0.055 · out $0.11 /1M131K ctx
Inception: Mercury 2
⚙ toolstext
inception/mercury-2
toolsreasoning
in $0.28 · out $0.83 /1M128K ctx
inclusionAI: Ling-2.6-1T
⚙ toolstext
inclusionai/ling-2.6-1t
tools
in $0.083 · out $0.69 /1M262K ctx
inclusionAI: Ling-2.6-flash
⚙ toolstext
inclusionai/ling-2.6-flash
tools
in $0.011 · out $0.033 /1M262K ctx
inclusionAI: Ring-2.6-1T
⚙ toolstext
inclusionai/ring-2.6-1t
toolsreasoning
in $0.083 · out $0.69 /1M262K ctx
Kling
video
kuaishou/kling
video model
Kwaipilot: KAT-Coder-Air V2.5
⚙ toolstext
kwaipilot/kat-coder-air-v2.5
tools
in $0.17 · out $0.66 /1M256K ctx
Kwaipilot: KAT-Coder-Pro V2
⚙ toolstext
kwaipilot/kat-coder-pro-v2
tools
in $0.33 · out $1.32 /1M262K ctx
Kwaipilot: KAT-Coder-Pro V2.5
⚙ toolstext
kwaipilot/kat-coder-pro-v2.5
tools
in $0.81 · out $3.26 /1M256K ctx
Luma Dream Machine
video
lumalabs/dream-machine
video model
Mancer: Weaver (alpha)
text
mancer/weaver
in $0.55 · out $0.83 /1M8K ctx
Meituan: LongCat 2.0
⚙ toolstext
meituan/longcat-2.0
toolsreasoning
in $0.33 · out $1.32 /1M1.0M ctx
Meta: Muse Spark 1.1
⚙ toolstext
meta/muse-spark-1.1
visionaudio-intoolsreasoning
in $1.38 · out $4.67 /1M1.0M ctx
Meta: Llama 3.1 70B Instruct
⚙ tools↓ self-hosttext
meta-llama/llama-3.1-70b-instruct
tools
in $0.44 · out $0.44 /1M131K ctx
Meta: Llama 3.1 8B Instruct
⚙ tools↓ self-hosttext
meta-llama/llama-3.1-8b-instruct
tools
in $0.055 · out $0.088 /1M131K ctx
Meta: Llama 3.2 3B Instruct
↓ self-hosttext
meta-llama/llama-3.2-3b-instruct
in $0.055 · out $0.36 /1M131K ctx
Meta: Llama 3.3 70B Instruct
⚙ tools↓ self-hosttext
meta-llama/llama-3.3-70b-instruct
tools
in $0.14 · out $0.44 /1M131K ctx
Meta: Llama 4 Maverick
⚙ tools↓ self-hosttext
meta-llama/llama-4-maverick
visiontools
in $0.22 · out $0.88 /1M1.0M ctx
Meta: Llama 4 Scout
⚙ tools↓ self-hosttext
meta-llama/llama-4-scout
visiontools
in $0.11 · out $0.33 /1M1.3M ctx
Meta: Llama Guard 4 12B
↓ self-hosttext
meta-llama/llama-guard-4-12b
vision
in $0.20 · out $0.20 /1M1.0M ctx
Microsoft: Phi 4
↓ self-hosttext
microsoft/phi-4
in $0.077 · out $0.15 /1M16K ctx
WizardLM-2 8x22B
↓ self-hosttext
microsoft/wizardlm-2-8x22b
in $0.68 · out $0.68 /1M66K ctx
MiniMax: MiniMax-01
text
minimax/minimax-01
vision
in $0.22 · out $1.21 /1M1.0M ctx
MiniMax: MiniMax M1
⚙ toolstext
minimax/minimax-m1
toolsreasoning
in $0.60 · out $2.42 /1M1M ctx
MiniMax: MiniMax M2
⚙ toolstext
minimax/minimax-m2
toolsreasoning
in $0.28 · out $1.12 /1M205K ctx
MiniMax: MiniMax M2-her
text
minimax/minimax-m2-her
in $0.33 · out $1.32 /1M66K ctx
MiniMax: MiniMax M2.1
⚙ toolstext
minimax/minimax-m2.1
toolsreasoning
in $0.33 · out $1.32 /1M205K ctx
MiniMax: MiniMax M2.5
⚙ tools↓ self-hosttext
minimax/minimax-m2.5
toolsreasoning
in $0.17 · out $0.99 /1M205K ctx
MiniMax: MiniMax M2.7
⚙ toolstext
minimax/minimax-m2.7
toolsreasoning
in $0.28 · out $1.10 /1M205K ctx
MiniMax: MiniMax M3
⚙ toolstext
minimax/minimax-m3
visiontoolsreasoning
in $0.33 · out $1.32 /1M1.0M ctx
Mistral: Codestral 2508
⚙ tools↓ self-hosttext
mistralai/codestral-2508
tools
in $0.33 · out $0.99 /1M256K ctx
Mistral: Devstral 2 2512
⚙ tools↓ self-hosttext
mistralai/devstral-2512
tools
in $0.44 · out $2.20 /1M262K ctx
Mistral: Ministral 3 14B 2512
⚙ tools↓ self-hosttext
mistralai/ministral-14b-2512
visiontools
in $0.22 · out $0.22 /1M262K ctx
Mistral: Ministral 3 3B 2512
⚙ tools↓ self-hosttext
mistralai/ministral-3b-2512
visiontools
in $0.11 · out $0.11 /1M131K ctx
Mistral: Ministral 3 8B 2512
⚙ tools↓ self-hosttext
mistralai/ministral-8b-2512
visiontools
in $0.17 · out $0.17 /1M262K ctx
Mistral Large
⚙ tools↓ self-hosttext
mistralai/mistral-large
tools
in $2.20 · out $6.60 /1M128K ctx
Mistral Large 2407
⚙ tools↓ self-hosttext
mistralai/mistral-large-2407
tools
in $2.20 · out $6.60 /1M131K ctx
Mistral: Mistral Large 3 2512
⚙ tools↓ self-hosttext
mistralai/mistral-large-2512
visiontools
in $0.55 · out $1.65 /1M262K ctx
Mistral: Mistral Medium 3
⚙ tools↓ self-hosttext
mistralai/mistral-medium-3
visiontools
in $0.44 · out $2.20 /1M131K ctx
Mistral: Mistral Medium 3.5
⚙ tools↓ self-hosttext
mistralai/mistral-medium-3-5
visiontoolsreasoning
in $1.65 · out $8.25 /1M262K ctx
Mistral: Mistral Medium 3.1
⚙ tools↓ self-hosttext
mistralai/mistral-medium-3.1
visiontools
in $0.44 · out $2.20 /1M131K ctx
Mistral: Mistral Nemo
⚙ tools↓ self-hosttext
mistralai/mistral-nemo
tools
in $0.021 · out $0.033 /1M131K ctx
Mistral: Saba
⚙ tools↓ self-hosttext
mistralai/mistral-saba
tools
in $0.22 · out $0.66 /1M33K ctx
Mistral: Mistral Small 3
↓ self-hosttext
mistralai/mistral-small-24b-instruct-2501
in $0.055 · out $0.088 /1M33K ctx
Mistral: Mistral Small 4
⚙ tools↓ self-hosttext
mistralai/mistral-small-2603
visiontoolsreasoning
in $0.17 · out $0.66 /1M262K ctx
Mistral: Mistral Small 3.2 24B
⚙ tools↓ self-hosttext
mistralai/mistral-small-3.2-24b-instruct
visiontools
in $0.11 · out $0.33 /1M256K ctx
Mistral: Mixtral 8x22B Instruct
⚙ tools↓ self-hosttext
mistralai/mixtral-8x22b-instruct
tools
in $2.20 · out $6.60 /1M66K ctx
Mistral: Voxtral Small 24B 2507
⚙ tools↓ self-hosttext
mistralai/voxtral-small-24b-2507
audio-intools
in $0.11 · out $0.33 /1M32K ctx
MoonshotAI: Kimi K2 0711
⚙ tools↓ self-hosttext
moonshotai/kimi-k2
tools
in $0.63 · out $2.53 /1M131K ctx
MoonshotAI: Kimi K2 0905
⚙ tools↓ self-hosttext
moonshotai/kimi-k2-0905
tools
in $0.66 · out $2.75 /1M262K ctx
MoonshotAI: Kimi K2 Thinking
⚙ tools↓ self-hosttext
moonshotai/kimi-k2-thinking
toolsreasoning
in $0.66 · out $2.75 /1M262K ctx
MoonshotAI: Kimi K2.5
⚙ tools↓ self-hosttext
moonshotai/kimi-k2.5
visiontoolsreasoning
in $0.63 · out $3.14 /1M262K ctx
MoonshotAI: Kimi K2.6
⚙ tools↓ self-hosttext
moonshotai/kimi-k2.6
visiontoolsreasoning
in $0.71 · out $2.99 /1M262K ctx
MoonshotAI: Kimi K2.7 Code
⚙ tools↓ self-hosttext
moonshotai/kimi-k2.7-code
visiontoolsreasoning
in $0.80 · out $3.85 /1M262K ctx
MoonshotAI: Kimi K3
⚙ tools↓ self-hosttext
moonshotai/kimi-k3
visiontoolsreasoning
in $3.30 · out $16.50 /1M1.0M ctx
Morph: Morph V3 Fast
text
morph/morph-v3-fast
in $0.88 · out $1.32 /1M82K ctx
Morph: Morph V3 Large
text
morph/morph-v3-large
in $0.99 · out $2.09 /1M262K ctx
Nex AGI: Nex-N2-Mini
⚙ toolstext
nex-agi/nex-n2-mini
visiontoolsreasoning
in $0.028 · out $0.11 /1M262K ctx
Nex AGI: Nex-N2-Pro
⚙ toolstext
nex-agi/nex-n2-pro
visiontoolsreasoning
in $0.28 · out $1.10 /1M262K ctx
Nous: Hermes 3 405B Instruct
↓ self-hosttext
nousresearch/hermes-3-llama-3.1-405b
in $1.10 · out $1.10 /1M131K ctx
Nous: Hermes 3 70B Instruct
↓ self-hosttext
nousresearch/hermes-3-llama-3.1-70b
in $0.77 · out $0.77 /1M131K ctx
Nous: Hermes 4 405B
↓ self-hosttext
nousresearch/hermes-4-405b
reasoning
in $1.10 · out $3.30 /1M131K ctx
Nous: Hermes 4 70B
↓ self-hosttext
nousresearch/hermes-4-70b
reasoning
in $0.14 · out $0.44 /1M131K ctx
NVIDIA: Nemotron 3 Nano 30B A3B
⚙ tools↓ self-hosttext
nvidia/nemotron-3-nano-30b-a3b
toolsreasoning
in $0.055 · out $0.22 /1M262K ctx
NVIDIA: Nemotron 3 Super
⚙ tools↓ self-hosttext
nvidia/nemotron-3-super-120b-a12b
toolsreasoning
in $0.094 · out $0.44 /1M1M ctx
NVIDIA: Nemotron 3 Ultra
⚙ tools↓ self-hosttext
nvidia/nemotron-3-ultra-550b-a55b
toolsreasoning
in $0.55 · out $2.42 /1M512K ctx
OpenAI: GPT-3.5 Turbo
⚙ toolstext
openai/gpt-3.5-turbo
tools
in $0.55 · out $1.65 /1M16K ctx
OpenAI: GPT-3.5 Turbo (older v0613)
⚙ toolstext
openai/gpt-3.5-turbo-0613
tools
in $1.10 · out $2.20 /1M4K ctx
OpenAI: GPT-3.5 Turbo 16k
⚙ toolstext
openai/gpt-3.5-turbo-16k
tools
in $3.30 · out $4.40 /1M16K ctx
OpenAI: GPT-3.5 Turbo Instruct
text
openai/gpt-3.5-turbo-instruct
in $1.65 · out $2.20 /1M4K ctx
OpenAI: GPT-4 Turbo
⚙ toolstext
openai/gpt-4-turbo
visiontools
in $11.00 · out $33.00 /1M128K ctx
OpenAI: GPT-4 Turbo Preview
⚙ toolstext
openai/gpt-4-turbo-preview
tools
in $11.00 · out $33.00 /1M128K ctx
OpenAI: GPT-4.1
⚙ toolstext
openai/gpt-4.1
visiontools
in $2.20 · out $8.80 /1M1.0M ctx
OpenAI: GPT-4.1 Mini
⚙ toolstext
openai/gpt-4.1-mini
visiontools
in $0.44 · out $1.76 /1M1.0M ctx
OpenAI: GPT-4.1 Nano
⚙ toolstext
openai/gpt-4.1-nano
visiontools
in $0.11 · out $0.44 /1M1.0M ctx
OpenAI: GPT-4o
⚙ toolstext
openai/gpt-4o
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o (2024-05-13)
⚙ toolstext
openai/gpt-4o-2024-05-13
visiontools
in $5.50 · out $16.50 /1M128K ctx
OpenAI: GPT-4o (2024-08-06)
⚙ toolstext
openai/gpt-4o-2024-08-06
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o (2024-11-20)
⚙ toolstext
openai/gpt-4o-2024-11-20
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o-mini
⚙ toolstext
openai/gpt-4o-mini
visiontools
in $0.17 · out $0.66 /1M128K ctx
OpenAI: GPT-4o-mini (2024-07-18)
⚙ toolstext
openai/gpt-4o-mini-2024-07-18
visiontools
in $0.17 · out $0.66 /1M128K ctx
OpenAI: GPT-4o Search Preview
text
openai/gpt-4o-search-preview
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-5
⚙ toolstext
openai/gpt-5
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Chat
text
openai/gpt-5-chat
vision
in $1.38 · out $11.00 /1M128K ctx
OpenAI: GPT-5 Codex
⚙ toolstext
openai/gpt-5-codex
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Image
image
openai/gpt-5-image
visionreasoning
in $11.00 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Image Mini
image
openai/gpt-5-image-mini
visionreasoning
in $2.75 · out $2.20 /1M400K ctx
OpenAI: GPT-5 Mini
⚙ toolstext
openai/gpt-5-mini
visiontoolsreasoning
in $0.28 · out $2.20 /1M400K ctx
OpenAI: GPT-5 Nano
⚙ toolstext
openai/gpt-5-nano
visiontoolsreasoning
in $0.055 · out $0.44 /1M400K ctx
OpenAI: GPT-5 Pro
⚙ toolstext
openai/gpt-5-pro
visiontoolsreasoning
in $16.50 · out $132.00 /1M400K ctx
OpenAI: GPT-5.1
⚙ toolstext
openai/gpt-5.1
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1 Chat
⚙ toolstext
openai/gpt-5.1-chat
visiontools
in $1.38 · out $11.00 /1M128K ctx
OpenAI: GPT-5.1-Codex
⚙ toolstext
openai/gpt-5.1-codex
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1-Codex-Max
⚙ toolstext
openai/gpt-5.1-codex-max
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1-Codex-Mini
⚙ toolstext
openai/gpt-5.1-codex-mini
visiontoolsreasoning
in $0.28 · out $2.20 /1M400K ctx
OpenAI: GPT-5.2
⚙ toolstext
openai/gpt-5.2
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.2 Chat
⚙ toolstext
openai/gpt-5.2-chat
visiontools
in $1.93 · out $15.40 /1M128K ctx
OpenAI: GPT-5.2-Codex
⚙ toolstext
openai/gpt-5.2-codex
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.2 Pro
⚙ toolstext
openai/gpt-5.2-pro
visiontoolsreasoning
in $23.10 · out $184.80 /1M400K ctx
OpenAI: GPT-5.3 Chat
⚙ toolstext
openai/gpt-5.3-chat
visiontools
in $1.93 · out $15.40 /1M128K ctx
OpenAI: GPT-5.3-Codex
⚙ toolstext
openai/gpt-5.3-codex
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.4
⚙ toolstext
openai/gpt-5.4
visiontoolsreasoning
in $2.75 · out $16.50 /1M1.1M ctx
OpenAI: GPT-5.4 Image 2
image
openai/gpt-5.4-image-2
visionreasoning
in $8.80 · out $16.50 /1M272K ctx
OpenAI: GPT-5.4 Mini
⚙ toolstext
openai/gpt-5.4-mini
visiontoolsreasoning
in $0.83 · out $4.95 /1M400K ctx
OpenAI: GPT-5.4 Nano
⚙ toolstext
openai/gpt-5.4-nano
visiontoolsreasoning
in $0.22 · out $1.38 /1M400K ctx
OpenAI: GPT-5.4 Pro
⚙ toolstext
openai/gpt-5.4-pro
visiontoolsreasoning
in $33.00 · out $198.00 /1M1.1M ctx
OpenAI: GPT-5.5
⚙ toolstext
openai/gpt-5.5
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI: GPT-5.5 Pro
⚙ toolstext
openai/gpt-5.5-pro
visiontoolsreasoning
in $33.00 · out $198.00 /1M1.1M ctx
OpenAI: GPT-5.6 Luna
⚙ toolstext
openai/gpt-5.6-luna
visiontoolsreasoning
in $1.10 · out $6.60 /1M1.1M ctx
OpenAI: GPT-5.6 Luna Pro
⚙ toolstext
openai/gpt-5.6-luna-pro
visiontoolsreasoning
in $1.10 · out $6.60 /1M1.1M ctx
OpenAI: GPT-5.6 Sol
⚙ toolstext
openai/gpt-5.6-sol
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI: GPT-5.6 Sol Pro
⚙ toolstext
openai/gpt-5.6-sol-pro
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI: GPT-5.6 Terra
⚙ toolstext
openai/gpt-5.6-terra
visiontoolsreasoning
in $2.75 · out $16.50 /1M1.1M ctx
OpenAI: GPT-5.6 Terra Pro
⚙ toolstext
openai/gpt-5.6-terra-pro
visiontoolsreasoning
in $2.75 · out $16.50 /1M1.1M ctx
OpenAI: GPT Audio
⚙ toolsaudio
openai/gpt-audio
audio-intools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT Audio Mini
⚙ toolsaudio
openai/gpt-audio-mini
audio-intools
in $0.66 · out $2.64 /1M128K ctx
OpenAI: GPT Chat Latest
⚙ toolstext
openai/gpt-chat-latest
visiontools
in $5.50 · out $33.00 /1M400K ctx
OpenAI: gpt-oss-120b
⚙ tools↓ self-hosttext
openai/gpt-oss-120b
toolsreasoning
in $0.041 · out $0.19 /1M131K ctx
OpenAI: gpt-oss-20b
⚙ tools↓ self-hosttext
openai/gpt-oss-20b
toolsreasoning
in $0.033 · out $0.15 /1M131K ctx
OpenAI: gpt-oss-safeguard-20b
⚙ tools↓ self-hosttext
openai/gpt-oss-safeguard-20b
toolsreasoning
in $0.083 · out $0.33 /1M131K ctx
OpenAI: o1
⚙ toolstext
openai/o1
visiontoolsreasoning
in $16.50 · out $66.00 /1M200K ctx
OpenAI: o1-pro
text
openai/o1-pro
visionreasoning
in $165.00 · out $660.00 /1M200K ctx
OpenAI: o3
⚙ toolstext
openai/o3
visiontoolsreasoning
in $2.20 · out $8.80 /1M200K ctx
OpenAI: o3 Deep Research
⚙ toolstext
openai/o3-deep-research
visiontoolsreasoning
in $11.00 · out $44.00 /1M200K ctx
OpenAI: o3 Mini
⚙ toolstext
openai/o3-mini
toolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o3 Mini High
⚙ toolstext
openai/o3-mini-high
toolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o3 Pro
⚙ toolstext
openai/o3-pro
visiontoolsreasoning
in $22.00 · out $88.00 /1M200K ctx
OpenAI: o4 Mini
⚙ toolstext
openai/o4-mini
visiontoolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o4 Mini Deep Research
⚙ toolstext
openai/o4-mini-deep-research
visiontoolsreasoning
in $2.20 · out $8.80 /1M200K ctx
OpenAI: o4 Mini High
⚙ toolstext
openai/o4-mini-high
visiontoolsreasoning
in $1.21 · out $4.84 /1M200K ctx
Sora 2
video
openai/sora-2
video model
Sora 2 Pro
video
openai/sora-2-pro
video model
Text Embedding 3 Large
embeddings
openai/text-embedding-3-large
in $0.14 · out $0 /1M
Text Embedding 3 Small
embeddings
openai/text-embedding-3-small
in $0.022 · out $0 /1M
Auto Router
⚙ toolsimage
openrouter/auto
visionaudio-intoolsreasoning
image model2M ctx
Auto Router (Beta)
⚙ toolsimage
openrouter/auto-beta
visionaudio-intoolsreasoning
image model2M ctx
Perceptron: Perceptron Mk1
text
perceptron/perceptron-mk1
visionreasoning
in $0.17 · out $1.65 /1M33K ctx
Perplexity: Sonar
text
perplexity/sonar
vision
in $1.10 · out $1.10 /1M127K ctx
Perplexity: Sonar Deep Research
text
perplexity/sonar-deep-research
reasoning
in $2.20 · out $8.80 /1M128K ctx
Perplexity: Sonar Pro
text
perplexity/sonar-pro
vision
in $3.30 · out $16.50 /1M200K ctx
Perplexity: Sonar Pro Search
text
perplexity/sonar-pro-search
visionreasoning
in $3.30 · out $16.50 /1M200K ctx
Perplexity: Sonar Reasoning Pro
text
perplexity/sonar-reasoning-pro
visionreasoning
in $2.20 · out $8.80 /1M128K ctx
Poolside: Laguna M.1
⚙ toolstext
poolside/laguna-m.1
toolsreasoning
in $0.22 · out $0.44 /1M262K ctx
Poolside: Laguna S 2.1
⚙ toolstext
poolside/laguna-s-2.1
toolsreasoning
in $0.11 · out $0.22 /1M1.0M ctx
Poolside: Laguna XS 2.1
⚙ toolstext
poolside/laguna-xs-2.1
toolsreasoning
in $0.066 · out $0.13 /1M262K ctx
Qwen2.5 72B Instruct
⚙ tools↓ self-hosttext
qwen/qwen-2.5-72b-instruct
tools
in $0.40 · out $0.44 /1M33K ctx
Qwen: Qwen2.5 7B Instruct
⚙ tools↓ self-hosttext
qwen/qwen-2.5-7b-instruct
tools
in $0.044 · out $0.11 /1M33K ctx
Qwen: Qwen-Plus
⚙ tools↓ self-hosttext
qwen/qwen-plus
tools
in $0.29 · out $0.86 /1M1M ctx
Qwen: Qwen Plus 0728
⚙ tools↓ self-hosttext
qwen/qwen-plus-2025-07-28
tools
in $0.29 · out $0.86 /1M1M ctx
Qwen: Qwen2.5 VL 72B Instruct
↓ self-hosttext
qwen/qwen2.5-vl-72b-instruct
vision
in $0.88 · out $1.10 /1M128K ctx
Qwen: Qwen3 14B
⚙ tools↓ self-hosttext
qwen/qwen3-14b
toolsreasoning
in $0.25 · out $1.00 /1M131K ctx
Qwen: Qwen3 235B A22B
⚙ tools↓ self-hosttext
qwen/qwen3-235b-a22b
toolsreasoning
in $0.50 · out $2.00 /1M131K ctx
Qwen: Qwen3 235B A22B Instruct 2507
⚙ tools↓ self-hosttext
qwen/qwen3-235b-a22b-2507
tools
in $0.099 · out $0.60 /1M262K ctx
Qwen: Qwen3 235B A22B Thinking 2507
⚙ tools↓ self-hosttext
qwen/qwen3-235b-a22b-thinking-2507
toolsreasoning
in $0.33 · out $3.30 /1M262K ctx
Qwen: Qwen3 30B A3B Instruct 2507
⚙ tools↓ self-hosttext
qwen/qwen3-30b-a3b-instruct-2507
tools
in $0.053 · out $0.21 /1M262K ctx
Qwen: Qwen3 30B A3B Thinking 2507
⚙ tools↓ self-hosttext
qwen/qwen3-30b-a3b-thinking-2507
toolsreasoning
in $0.14 · out $1.72 /1M82K ctx
Qwen: Qwen3 32B
⚙ tools↓ self-hosttext
qwen/qwen3-32b
toolsreasoning
in $0.088 · out $0.31 /1M131K ctx
Qwen: Qwen3 8B
⚙ tools↓ self-hosttext
qwen/qwen3-8b
toolsreasoning
in $0.13 · out $0.50 /1M131K ctx
Qwen: Qwen3 Coder 480B A35B
⚙ tools↓ self-hosttext
qwen/qwen3-coder
tools
in $0.33 · out $1.10 /1M262K ctx
Qwen: Qwen3 Coder 30B A3B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-coder-30b-a3b-instruct
tools
in $0.077 · out $0.30 /1M262K ctx
Qwen: Qwen3 Coder Flash
⚙ tools↓ self-hosttext
qwen/qwen3-coder-flash
tools
in $0.21 · out $1.07 /1M1M ctx
Qwen: Qwen3 Coder Next
⚙ tools↓ self-hosttext
qwen/qwen3-coder-next
tools
in $0.12 · out $0.88 /1M262K ctx
Qwen: Qwen3 Coder Plus
⚙ tools↓ self-hosttext
qwen/qwen3-coder-plus
tools
in $0.71 · out $3.58 /1M1M ctx
Qwen: Qwen3 Max
⚙ tools↓ self-hosttext
qwen/qwen3-max
tools
in $0.86 · out $4.29 /1M262K ctx
Qwen: Qwen3 Max Thinking
⚙ tools↓ self-hosttext
qwen/qwen3-max-thinking
toolsreasoning
in $0.86 · out $4.29 /1M262K ctx
Qwen: Qwen3 Next 80B A3B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-next-80b-a3b-instruct
tools
in $0.11 · out $1.21 /1M262K ctx
Qwen: Qwen3 Next 80B A3B Thinking
⚙ tools↓ self-hosttext
qwen/qwen3-next-80b-a3b-thinking
toolsreasoning
in $0.11 · out $0.86 /1M262K ctx
Qwen: Qwen3 VL 235B A22B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-vl-235b-a22b-instruct
visiontools
in $0.23 · out $2.09 /1M262K ctx
Qwen: Qwen3 VL 235B A22B Thinking
⚙ tools↓ self-hosttext
qwen/qwen3-vl-235b-a22b-thinking
visiontoolsreasoning
in $0.29 · out $2.86 /1M131K ctx
Qwen: Qwen3 VL 30B A3B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-vl-30b-a3b-instruct
visiontools
in $0.17 · out $0.66 /1M262K ctx
Qwen: Qwen3 VL 30B A3B Thinking
⚙ tools↓ self-hosttext
qwen/qwen3-vl-30b-a3b-thinking
visiontoolsreasoning
in $0.14 · out $1.72 /1M262K ctx
Qwen: Qwen3 VL 32B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-vl-32b-instruct
visiontools
in $0.11 · out $0.46 /1M131K ctx
Qwen: Qwen3 VL 8B Instruct
⚙ tools↓ self-hosttext
qwen/qwen3-vl-8b-instruct
visiontools
in $0.13 · out $0.50 /1M262K ctx
Qwen: Qwen3 VL 8B Thinking
⚙ tools↓ self-hosttext
qwen/qwen3-vl-8b-thinking
visiontoolsreasoning
in $0.13 · out $1.50 /1M131K ctx
Qwen: Qwen3.5-122B-A10B
⚙ tools↓ self-hosttext
qwen/qwen3.5-122b-a10b
visiontoolsreasoning
in $0.29 · out $2.29 /1M262K ctx
Qwen: Qwen3.5-27B
⚙ tools↓ self-hosttext
qwen/qwen3.5-27b
visiontoolsreasoning
in $0.21 · out $1.72 /1M262K ctx
Qwen: Qwen3.5-35B-A3B
⚙ tools↓ self-hosttext
qwen/qwen3.5-35b-a3b
visiontoolsreasoning
in $0.17 · out $1.10 /1M262K ctx
Qwen: Qwen3.5 397B A17B
⚙ tools↓ self-hosttext
qwen/qwen3.5-397b-a17b
visiontoolsreasoning
in $0.43 · out $2.57 /1M262K ctx
Qwen: Qwen3.5-9B
⚙ tools↓ self-hosttext
qwen/qwen3.5-9b
visiontoolsreasoning
in $0.11 · out $0.17 /1M262K ctx
Qwen: Qwen3.5-Flash
⚙ tools↓ self-hosttext
qwen/qwen3.5-flash-02-23
visiontoolsreasoning
in $0.071 · out $0.29 /1M1M ctx
Qwen: Qwen3.5 Plus 2026-02-15
⚙ tools↓ self-hosttext
qwen/qwen3.5-plus-02-15
visiontoolsreasoning
in $0.29 · out $1.72 /1M1M ctx
Qwen: Qwen3.5 Plus 2026-04-20
⚙ tools↓ self-hosttext
qwen/qwen3.5-plus-20260420
visiontoolsreasoning
in $0.33 · out $1.98 /1M1M ctx
Qwen: Qwen3.6 27B
⚙ tools↓ self-hosttext
qwen/qwen3.6-27b
visiontoolsreasoning
in $0.33 · out $2.20 /1M262K ctx
Qwen: Qwen3.6 35B A3B
⚙ tools↓ self-hosttext
qwen/qwen3.6-35b-a3b
visiontoolsreasoning
in $0.15 · out $1.10 /1M262K ctx
Qwen: Qwen3.6 Flash
⚙ tools↓ self-hosttext
qwen/qwen3.6-flash
visiontoolsreasoning
in $0.21 · out $1.24 /1M1M ctx
Qwen: Qwen3.6 Max Preview
⚙ tools↓ self-hosttext
qwen/qwen3.6-max-preview
toolsreasoning
in $1.14 · out $6.86 /1M262K ctx
Qwen: Qwen3.6 Plus
⚙ tools↓ self-hosttext
qwen/qwen3.6-plus
visiontoolsreasoning
in $0.36 · out $2.15 /1M1M ctx
Qwen: Qwen3.7 Max
⚙ tools↓ self-hosttext
qwen/qwen3.7-max
toolsreasoning
in $1.62 · out $4.87 /1M1M ctx
Qwen: Qwen3.7 Plus
⚙ tools↓ self-hosttext
qwen/qwen3.7-plus
visiontoolsreasoning
in $0.35 · out $1.41 /1M1M ctx
Reka Edge
⚙ toolstext
rekaai/reka-edge
visiontools
in $0.11 · out $0.11 /1M16K ctx
Reka Flash 3
text
rekaai/reka-flash-3
reasoning
in $0.11 · out $0.22 /1M66K ctx
Relace: Relace Apply 3
text
relace/relace-apply-3
in $0.94 · out $1.38 /1M256K ctx
Relace: Relace Search
⚙ toolstext
relace/relace-search
tools
in $1.10 · out $3.30 /1M256K ctx
Runway Gen-4
video
runwayml/gen-4
video model
Sakana: Fugu Ultra
⚙ toolstext
sakana/fugu-ultra
visiontoolsreasoning
in $5.50 · out $33.00 /1M1M ctx
Sao10K: Llama 3 8B Lunaris
text
sao10k/l3-lunaris-8b
in $0.044 · out $0.055 /1M8K ctx
Sao10K: Llama 3.1 Euryale 70B v2.2
⚙ toolstext
sao10k/l3.1-euryale-70b
tools
in $0.94 · out $0.94 /1M131K ctx
Sao10K: Llama 3.3 Euryale 70B
text
sao10k/l3.3-euryale-70b
in $0.71 · out $0.83 /1M131K ctx
StepFun: Step 3.5 Flash
⚙ toolstext
stepfun/step-3.5-flash
toolsreasoning
in $0.11 · out $0.33 /1M262K ctx
StepFun: Step 3.7 Flash
⚙ toolstext
stepfun/step-3.7-flash
visiontoolsreasoning
in $0.22 · out $1.26 /1M262K ctx
Tencent: Hunyuan A13B Instruct
text
tencent/hunyuan-a13b-instruct
reasoning
in $0.15 · out $0.63 /1M131K ctx
Tencent: Hy3
⚙ toolstext
tencent/hy3
toolsreasoning
in $0.15 · out $0.58 /1M262K ctx
Tencent: Hy3 preview
⚙ toolstext
tencent/hy3-preview
toolsreasoning
in $0.069 · out $0.23 /1M262K ctx
TheDrummer: Cydonia 24B V4.1
text
thedrummer/cydonia-24b-v4.1
in $0.33 · out $0.55 /1M131K ctx
TheDrummer: Rocinante 12B
text
thedrummer/rocinante-12b
in $0.28 · out $0.55 /1M66K ctx
TheDrummer: Skyfall 36B V2
text
thedrummer/skyfall-36b-v2
in $0.60 · out $0.88 /1M33K ctx
TheDrummer: UnslopNemo 12B
⚙ toolstext
thedrummer/unslopnemo-12b
tools
in $0.44 · out $0.44 /1M33K ctx
Thinking Machines: Inkling
⚙ toolstext
thinkingmachines/inkling
visionaudio-intoolsreasoning
in $1.10 · out $4.46 /1M1.0M ctx
ReMM SLERP 13B
text
undi95/remm-slerp-l2-13b
in $0.50 · out $0.71 /1M6K ctx
Upstage: Solar Pro 3
⚙ tools↓ self-hosttext
upstage/solar-pro-3
toolsreasoning
in $0.17 · out $0.66 /1M128K ctx
Writer: Palmyra X5
text
writer/palmyra-x5
in $0.66 · out $6.60 /1M1.0M ctx
xAI: Grok 4.20
⚙ toolstext
x-ai/grok-4.20
visiontoolsreasoning
in $1.38 · out $2.75 /1M2M ctx
xAI: Grok 4.20 Multi-Agent
text
x-ai/grok-4.20-multi-agent
visionreasoning
in $1.38 · out $2.75 /1M2M ctx
xAI: Grok 4.3
⚙ toolstext
x-ai/grok-4.3
visiontoolsreasoning
in $1.38 · out $2.75 /1M1M ctx
xAI: Grok 4.5
⚙ toolstext
x-ai/grok-4.5
visiontoolsreasoning
in $2.20 · out $6.60 /1M500K ctx
xAI: Grok Build 0.1
⚙ toolstext
x-ai/grok-build-0.1
visiontoolsreasoning
in $1.10 · out $2.20 /1M256K ctx
Xiaomi: MiMo-V2.5
⚙ toolstext
xiaomi/mimo-v2.5
visionaudio-intoolsreasoning
in $0.15 · out $0.31 /1M1.1M ctx
Xiaomi: MiMo-V2.5-Pro
⚙ toolstext
xiaomi/mimo-v2.5-pro
toolsreasoning
in $0.48 · out $0.96 /1M1.1M ctx
Z.ai: GLM 4.5
⚙ tools↓ self-hosttext
z-ai/glm-4.5
toolsreasoning
in $0.66 · out $2.42 /1M131K ctx
Z.ai: GLM 4.5 Air
⚙ tools↓ self-hosttext
z-ai/glm-4.5-air
toolsreasoning
in $0.14 · out $0.94 /1M131K ctx
Z.ai: GLM 4.5V
⚙ tools↓ self-hosttext
z-ai/glm-4.5v
visiontoolsreasoning
in $0.66 · out $1.98 /1M66K ctx
Z.ai: GLM 4.6
⚙ tools↓ self-hosttext
z-ai/glm-4.6
toolsreasoning
in $0.55 · out $2.20 /1M205K ctx
Z.ai: GLM 4.6V
⚙ tools↓ self-hosttext
z-ai/glm-4.6v
visiontoolsreasoning
in $0.33 · out $0.99 /1M131K ctx
Z.ai: GLM 4.7
⚙ tools↓ self-hosttext
z-ai/glm-4.7
toolsreasoning
in $0.44 · out $1.93 /1M205K ctx
Z.ai: GLM 4.7 Flash
⚙ tools↓ self-hosttext
z-ai/glm-4.7-flash
toolsreasoning
in $0.066 · out $0.44 /1M203K ctx
Z.ai: GLM 5
⚙ tools↓ self-hosttext
z-ai/glm-5
toolsreasoning
in $1.05 · out $2.81 /1M205K ctx
Z.ai: GLM 5.1
⚙ tools↓ self-hosttext
z-ai/glm-5.1
toolsreasoning
in $1.06 · out $3.34 /1M205K ctx
Z.ai: GLM 5.2
⚙ tools↓ self-hosttext
z-ai/glm-5.2
toolsreasoning
in $0.89 · out $2.80 /1M1.0M ctx
Z.ai: GLM 5V Turbo
⚙ tools↓ self-hosttext
z-ai/glm-5v-turbo
visiontoolsreasoning
in $1.32 · out $4.40 /1M203K ctx
Anthropic: Claude Fable Latest
⚙ toolstext
~anthropic/claude-fable-latest
visiontoolsreasoning
in $11.00 · out $55.00 /1M1M ctx
Anthropic Claude Haiku Latest
⚙ toolstext
~anthropic/claude-haiku-latest
visiontoolsreasoning
in $1.10 · out $5.50 /1M200K ctx
Anthropic: Claude Opus Latest
⚙ toolstext
~anthropic/claude-opus-latest
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic Claude Sonnet Latest
⚙ toolstext
~anthropic/claude-sonnet-latest
visiontoolsreasoning
in $2.20 · out $11.00 /1M1M ctx
Google Gemini Flash Latest
⚙ toolstext
~google/gemini-flash-latest
visionaudio-intoolsreasoning
in $1.65 · out $8.25 /1M1.0M ctx
Google Gemini Pro Latest
⚙ toolstext
~google/gemini-pro-latest
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
MoonshotAI Kimi Latest
⚙ tools↓ self-hosttext
~moonshotai/kimi-latest
visiontoolsreasoning
in $3.30 · out $16.50 /1M1.0M ctx
OpenAI GPT Latest
⚙ toolstext
~openai/gpt-latest
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI GPT Mini Latest
⚙ toolstext
~openai/gpt-mini-latest
visiontoolsreasoning
in $0.83 · out $4.95 /1M400K ctx
xAI: Grok Latest
⚙ toolstext
~x-ai/grok-latest
visiontoolsreasoning
in $2.20 · out $6.60 /1M500K ctx