model directory
Every model, one endpoint.
Run it on your hardware or ours.
397 AI models — text, image, audio, embeddings — across 62 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
397 models
AI21: Jamba Large 1.7
ai21/jamba-large-1.7↓ self-hosttext
tools
in $2.20 · out $8.80 /1M256K ctx
AionLabs: Aion-1.0
aion-labs/aion-1.0text
reasoning
in $4.40 · out $8.80 /1M131K ctx
AionLabs: Aion-1.0-Mini
aion-labs/aion-1.0-minitext
reasoning
in $0.77 · out $1.54 /1M131K ctx
AionLabs: Aion-2.0
aion-labs/aion-2.0text
reasoning
in $0.88 · out $1.76 /1M131K ctx
AionLabs: Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8b↓ self-hosttext
in $0.88 · out $1.76 /1M33K ctx
Wan 2.2
alibaba/wan-2.2↓ self-hostvideo
video model
AllenAI: Olmo 3 32B Think
allenai/olmo-3-32b-think↓ self-hosttext
reasoning
in $0.17 · out $0.55 /1M66K ctx
Amazon: Nova 2 Lite
amazon/nova-2-lite-v1text
visiontoolsreasoning
in $0.33 · out $2.75 /1M1M ctx
Amazon: Nova Lite 1.0
amazon/nova-lite-v1text
visiontools
in $0.066 · out $0.26 /1M300K ctx
Amazon: Nova Micro 1.0
amazon/nova-micro-v1text
tools
in $0.038 · out $0.15 /1M128K ctx
Amazon: Nova Premier 1.0
amazon/nova-premier-v1text
visiontools
in $2.75 · out $13.75 /1M1M ctx
Amazon: Nova Pro 1.0
amazon/nova-pro-v1text
visiontools
in $0.88 · out $3.52 /1M300K ctx
Magnum v4 72B
anthracite-org/magnum-v4-72btext
in $3.30 · out $5.50 /1M33K ctx
Anthropic: Claude 3 Haiku
anthropic/claude-3-haikutext
visiontools
in $0.28 · out $1.38 /1M200K ctx
Anthropic: Claude 3.5 Haiku
anthropic/claude-3.5-haikutext
visiontools
in $0.88 · out $4.40 /1M200K ctx
Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4.5text
visiontoolsreasoning
in $1.10 · out $5.50 /1M200K ctx
Anthropic: Claude Opus 4
anthropic/claude-opus-4text
visiontoolsreasoning
in $16.50 · out $82.50 /1M200K ctx
Anthropic: Claude Opus 4.1
anthropic/claude-opus-4.1text
visiontoolsreasoning
in $16.50 · out $82.50 /1M200K ctx
Anthropic: Claude Opus 4.5
anthropic/claude-opus-4.5text
visiontoolsreasoning
in $5.50 · out $27.50 /1M200K ctx
Anthropic: Claude Opus 4.6
anthropic/claude-opus-4.6text
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Opus 4.7
anthropic/claude-opus-4.7text
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Opus 4.8
anthropic/claude-opus-4.8text
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic: Claude Sonnet 4
anthropic/claude-sonnet-4text
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Anthropic: Claude Sonnet 4.5
anthropic/claude-sonnet-4.5text
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Anthropic: Claude Sonnet 4.6
anthropic/claude-sonnet-4.6text
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Arcee AI: Coder Large
arcee-ai/coder-largetext
in $0.55 · out $0.88 /1M33K ctx
Arcee AI: Maestro Reasoning
arcee-ai/maestro-reasoningtext
in $0.99 · out $3.63 /1M131K ctx
Arcee AI: Spotlight
arcee-ai/spotlighttext
vision
in $0.20 · out $0.20 /1M131K ctx
Arcee AI: Trinity Large Thinking
arcee-ai/trinity-large-thinkingtext
toolsreasoning
in $0.24 · out $0.94 /1M262K ctx
Arcee AI: Trinity Mini
arcee-ai/trinity-minitext
toolsreasoning
in $0.050 · out $0.17 /1M131K ctx
Arcee AI: Virtuoso Large
arcee-ai/virtuoso-largetext
tools
in $0.83 · out $1.32 /1M131K ctx
Baidu: ERNIE 4.5 VL 28B A3B
baidu/ernie-4.5-vl-28b-a3b↓ self-hosttext
visiontoolsreasoning
in $0.15 · out $0.62 /1M131K ctx
Baidu: ERNIE 4.5 VL 424B A47B
baidu/ernie-4.5-vl-424b-a47b↓ self-hosttext
visionreasoning
in $0.46 · out $1.38 /1M131K ctx
ByteDance: UI-TARS 7B
bytedance/ui-tars-1.5-7btext
vision
in $0.11 · out $0.22 /1M128K ctx
ByteDance Seed: Seed 1.6
bytedance-seed/seed-1.6text
visiontoolsreasoning
in $0.28 · out $2.20 /1M262K ctx
ByteDance Seed: Seed 1.6 Flash
bytedance-seed/seed-1.6-flashtext
visiontoolsreasoning
in $0.083 · out $0.33 /1M262K ctx
ByteDance Seed: Seed-2.0-Lite
bytedance-seed/seed-2.0-litetext
visiontoolsreasoning
in $0.28 · out $2.20 /1M262K ctx
ByteDance Seed: Seed-2.0-Mini
bytedance-seed/seed-2.0-minitext
visiontoolsreasoning
in $0.11 · out $0.44 /1M262K ctx
ai4bharat/indictrans2-en-indic-1B
cloudflare/ai4bharat/indictrans2-en-indic-1Btext
in $0.38 · out $0.38 /1M
aisingapore/gemma-sea-lion-v4-27b-it
cloudflare/aisingapore/gemma-sea-lion-v4-27b-it↓ self-hosttext
in $0.39 · out $0.61 /1M128K ctx
baai/bge-base-en-v1.5
cloudflare/baai/bge-base-en-v1.5embeddings
in $0.073 · out $0 /1M154K ctx
baai/bge-large-en-v1.5
cloudflare/baai/bge-large-en-v1.5embeddings
in $0.22 · out $0 /1M
baai/bge-m3
cloudflare/baai/bge-m3embeddings
in $0.013 · out $0 /1M60K ctx
baai/bge-reranker-base
cloudflare/baai/bge-reranker-baseother
in $0.003 · out $0 /1M
baai/bge-small-en-v1.5
cloudflare/baai/bge-small-en-v1.5embeddings
in $0.022 · out $0 /1M
black-forest-labs/flux-1-schnell
cloudflare/black-forest-labs/flux-1-schnellimage
image model
black-forest-labs/flux-2-dev
cloudflare/black-forest-labs/flux-2-devimage
image model
black-forest-labs/flux-2-klein-4b
cloudflare/black-forest-labs/flux-2-klein-4bimage
image model
black-forest-labs/flux-2-klein-9b
cloudflare/black-forest-labs/flux-2-klein-9bimage
image model
bytedance/stable-diffusion-xl-lightning
cloudflare/bytedance/stable-diffusion-xl-lightningimage
image model
deepgram/aura-1
cloudflare/deepgram/aura-1audio
audio model
deepgram/aura-2-en
cloudflare/deepgram/aura-2-enaudio
audio model
deepgram/aura-2-es
cloudflare/deepgram/aura-2-esaudio
audio model
deepgram/flux
cloudflare/deepgram/fluxaudio
audio model
deepgram/nova-3
cloudflare/deepgram/nova-3audio
audio model
deepseek-ai/deepseek-r1-distill-qwen-32b
cloudflare/deepseek-ai/deepseek-r1-distill-qwen-32b↓ self-hosttext
in $0.55 · out $5.37 /1M80K ctx
google/embeddinggemma-300m
cloudflare/google/embeddinggemma-300m↓ self-hostembeddings
embeddings model
google/gemma-4-26b-a4b-it
cloudflare/google/gemma-4-26b-a4b-it↓ self-hosttext
in $0.11 · out $0.33 /1M256K ctx
huggingface/distilbert-sst-2-int8
cloudflare/huggingface/distilbert-sst-2-int8other
in $0.029 · out $0 /1M
ibm-granite/granite-4.0-h-micro
cloudflare/ibm-granite/granite-4.0-h-micro↓ self-hosttext
in $0.019 · out $0.12 /1M131K ctx
leonardo/lucid-origin
cloudflare/leonardo/lucid-originimage
image model
leonardo/phoenix-1.0
cloudflare/leonardo/phoenix-1.0image
image model
llava-hf/llava-1.5-7b-hf
cloudflare/llava-hf/llava-1.5-7b-hfmultimodal
vision
multimodal model
lykon/dreamshaper-8-lcm
cloudflare/lykon/dreamshaper-8-lcmimage
image model
meta/llama-3.1-8b-instruct-fp8
cloudflare/meta/llama-3.1-8b-instruct-fp8↓ self-hosttext
in $0.17 · out $0.32 /1M32K ctx
meta/llama-3.2-11b-vision-instruct
cloudflare/meta/llama-3.2-11b-vision-instruct↓ self-hosttext
in $0.053 · out $0.74 /1M128K ctx
meta/llama-3.2-1b-instruct
cloudflare/meta/llama-3.2-1b-instruct↓ self-hosttext
in $0.030 · out $0.22 /1M60K ctx
meta/llama-3.2-3b-instruct
cloudflare/meta/llama-3.2-3b-instruct↓ self-hosttext
in $0.056 · out $0.37 /1M80K ctx
meta/llama-3.3-70b-instruct-fp8-fast
cloudflare/meta/llama-3.3-70b-instruct-fp8-fast↓ self-hosttext
in $0.32 · out $2.48 /1M24K ctx
meta/llama-4-scout-17b-16e-instruct
cloudflare/meta/llama-4-scout-17b-16e-instruct↓ self-hosttext
in $0.30 · out $0.94 /1M131K ctx
meta/llama-guard-3-8b
cloudflare/meta/llama-guard-3-8b↓ self-hosttext
in $0.53 · out $0.033 /1M131K ctx
meta/m2m100-1.2b
cloudflare/meta/m2m100-1.2btext
in $0.38 · out $0.38 /1M
microsoft/resnet-50
cloudflare/microsoft/resnet-50other
other model
mistralai/mistral-small-3.1-24b-instruct
cloudflare/mistralai/mistral-small-3.1-24b-instruct↓ self-hosttext
in $0.39 · out $0.61 /1M128K ctx
moonshotai/kimi-k2.6
cloudflare/moonshotai/kimi-k2.6↓ self-hosttext
in $1.05 · out $4.40 /1M262K ctx
myshell-ai/melotts
cloudflare/myshell-ai/melottsaudio
audio model
nvidia/nemotron-3-120b-a12b
cloudflare/nvidia/nemotron-3-120b-a12b↓ self-hosttext
in $0.55 · out $1.65 /1M256K ctx
openai/gpt-oss-120b
cloudflare/openai/gpt-oss-120b↓ self-hosttext
in $0.39 · out $0.83 /1M128K ctx
openai/gpt-oss-20b
cloudflare/openai/gpt-oss-20b↓ self-hosttext
in $0.22 · out $0.33 /1M128K ctx
openai/whisper
cloudflare/openai/whisperaudio
audio model
openai/whisper-large-v3-turbo
cloudflare/openai/whisper-large-v3-turboaudio
audio model
openai/whisper-tiny-en
cloudflare/openai/whisper-tiny-enaudio
audio model
pfnet/plamo-embedding-1b
cloudflare/pfnet/plamo-embedding-1bembeddings
in $0.020 · out $0 /1M
qwen/qwen2.5-coder-32b-instruct
cloudflare/qwen/qwen2.5-coder-32b-instruct↓ self-hosttext
in $0.73 · out $1.10 /1M33K ctx
qwen/qwen3-30b-a3b-fp8
cloudflare/qwen/qwen3-30b-a3b-fp8↓ self-hosttext
in $0.056 · out $0.37 /1M33K ctx
qwen/qwen3-embedding-0.6b
cloudflare/qwen/qwen3-embedding-0.6b↓ self-hostembeddings
in $0.013 · out $0 /1M8K ctx
qwen/qwq-32b
cloudflare/qwen/qwq-32b↓ self-hosttext
in $0.73 · out $1.10 /1M24K ctx
runwayml/stable-diffusion-v1-5-img2img
cloudflare/runwayml/stable-diffusion-v1-5-img2imgimage
image model
runwayml/stable-diffusion-v1-5-inpainting
cloudflare/runwayml/stable-diffusion-v1-5-inpaintingimage
image model
stabilityai/stable-diffusion-xl-base-1.0
cloudflare/stabilityai/stable-diffusion-xl-base-1.0image
image model
zai-org/glm-4.7-flash
cloudflare/zai-org/glm-4.7-flash↓ self-hosttext
in $0.067 · out $0.44 /1M131K ctx
Cohere: Command A
cohere/command-a↓ self-hosttext
in $2.75 · out $11.00 /1M256K ctx
Cohere: Command R (08-2024)
cohere/command-r-08-2024↓ self-hosttext
tools
in $0.17 · out $0.66 /1M128K ctx
Cohere: Command R+ (08-2024)
cohere/command-r-plus-08-2024↓ self-hosttext
tools
in $2.75 · out $11.00 /1M128K ctx
Cohere: Command R7B (12-2024)
cohere/command-r7b-12-2024↓ self-hosttext
in $0.041 · out $0.17 /1M128K ctx
Deep Cogito: Cogito v2.1 671B
deepcogito/cogito-v2.1-671btext
reasoning
in $1.38 · out $1.38 /1M128K ctx
DeepSeek: DeepSeek V3
deepseek/deepseek-chat↓ self-hosttext
tools
in $0.22 · out $0.88 /1M131K ctx
DeepSeek: DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324↓ self-hosttext
tools
in $0.22 · out $0.85 /1M164K ctx
DeepSeek: DeepSeek V3.1
deepseek/deepseek-chat-v3.1↓ self-hosttext
toolsreasoning
in $0.23 · out $0.87 /1M164K ctx
DeepSeek: R1
deepseek/deepseek-r1↓ self-hosttext
toolsreasoning
in $0.77 · out $2.75 /1M164K ctx
DeepSeek: R1 0528
deepseek/deepseek-r1-0528↓ self-hosttext
toolsreasoning
in $0.55 · out $2.37 /1M164K ctx
DeepSeek: R1 Distill Llama 70B
deepseek/deepseek-r1-distill-llama-70b↓ self-hosttext
reasoning
in $0.77 · out $0.88 /1M131K ctx
DeepSeek: DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus↓ self-hosttext
toolsreasoning
in $0.30 · out $1.05 /1M164K ctx
DeepSeek: DeepSeek V3.2
deepseek/deepseek-v3.2↓ self-hosttext
toolsreasoning
in $0.25 · out $0.38 /1M131K ctx
DeepSeek: DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp↓ self-hosttext
toolsreasoning
in $0.30 · out $0.45 /1M164K ctx
DeepSeek: DeepSeek V4 Flash
deepseek/deepseek-v4-flash↓ self-hosttext
toolsreasoning
in $0.11 · out $0.22 /1M1.0M ctx
DeepSeek: DeepSeek V4 Pro
deepseek/deepseek-v4-pro↓ self-hosttext
toolsreasoning
in $0.48 · out $0.96 /1M1.0M ctx
EssentialAI: Rnj 1 Instruct
essentialai/rnj-1-instructtext
tools
in $0.17 · out $0.17 /1M33K ctx
Google: Nano Banana (Gemini 2.5 Flash Image)
google/gemini-2.5-flash-imageimage
vision
in $0.33 · out $2.75 /1M33K ctx
Google: Gemini 2.5 Flash Lite Preview 09-2025
google/gemini-2.5-flash-lite-preview-09-2025text
visionaudio-intoolsreasoning
in $0.11 · out $0.44 /1M1.0M ctx
Google: Gemini 2.5 Pro Preview 06-05
google/gemini-2.5-pro-previewtext
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
Google: Gemini 2.5 Pro Preview 05-06
google/gemini-2.5-pro-preview-05-06text
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
Google: Gemini 3 Flash Preview
google/gemini-3-flash-previewtext
visionaudio-intoolsreasoning
in $0.55 · out $3.30 /1M1.0M ctx
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
google/gemini-3-pro-image-previewimage
visionreasoning
in $2.20 · out $13.20 /1M66K ctx
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-image-previewimage
visionreasoning
in $0.55 · out $3.30 /1M131K ctx
Google: Gemini 3.1 Flash Lite
google/gemini-3.1-flash-litetext
visionaudio-intoolsreasoning
in $0.28 · out $1.65 /1M1.0M ctx
Google: Gemini 3.1 Flash Lite Preview
google/gemini-3.1-flash-lite-previewtext
visionaudio-intoolsreasoning
in $0.28 · out $1.65 /1M1.0M ctx
Google: Gemini 3.1 Pro Preview
google/gemini-3.1-pro-previewtext
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
Google: Gemini 3.1 Pro Preview Custom Tools
google/gemini-3.1-pro-preview-customtoolstext
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
Google: Gemini 3.5 Flash
google/gemini-3.5-flashtext
visionaudio-intoolsreasoning
in $1.65 · out $9.90 /1M1.0M ctx
Google: Gemma 2 27B
google/gemma-2-27b-it↓ self-hosttext
in $0.71 · out $0.71 /1M8K ctx
Google: Gemma 3 12B
google/gemma-3-12b-it↓ self-hosttext
visiontools
in $0.044 · out $0.14 /1M131K ctx
Google: Gemma 3 27B
google/gemma-3-27b-it↓ self-hosttext
visiontools
in $0.088 · out $0.18 /1M131K ctx
Google: Gemma 3 4B
google/gemma-3-4b-it↓ self-hosttext
vision
in $0.044 · out $0.088 /1M131K ctx
Google: Gemma 3n 4B
google/gemma-3n-e4b-it↓ self-hosttext
in $0.066 · out $0.13 /1M33K ctx
Google: Gemma 4 31B
google/gemma-4-31b-it↓ self-hosttext
visiontoolsreasoning
in $0.13 · out $0.41 /1M262K ctx
Imagen 4
google/imagen-4image
image model
Google: Lyria 3 Clip Preview
google/lyria-3-clip-previewaudio
vision
audio model1.0M ctx
Google: Lyria 3 Pro Preview
google/lyria-3-pro-previewaudio
vision
audio model1.0M ctx
Veo 3.1
google/veo-3.1video
video model
Veo 3.1 Lite
google/veo-3.1-litevideo
video model
Google: Gemini 2.5 Flash
google/gemini-2.5-flashtext
visionaudio-intoolsreasoning
in $0.33 · out $2.75 /1M1.0M ctx
Google: Gemini 2.5 Flash Lite
google/gemini-2.5-flash-litetext
visionaudio-intoolsreasoning
in $0.11 · out $0.44 /1M1.0M ctx
Google: Gemini 2.5 Pro
google/gemini-2.5-protext
visionaudio-intoolsreasoning
in $1.38 · out $11.00 /1M1.0M ctx
MythoMax 13B
gryphe/mythomax-l2-13btext
in $0.066 · out $0.066 /1M4K ctx
Cybersecurity BaronLLM Offensive Security LLM Q6 K
hf/AlicanKiraz0/Cybersecurity-BaronLLM_Offensive_Security_LLM_Q6_K_GGUF↓ self-hosttext
text model
HELVETE 3B
hf/HelpingAI/HELVETE-3B↓ self-hosttext
text model
Qwopus GLM 18B Merged
hf/Jackrong/Qwopus-GLM-18B-Merged-GGUF↓ self-hosttext
text model
LocoOperator 4B
hf/LocoreMind/LocoOperator-4B↓ self-hosttext
text model
Meta Llama 3 8B Instruct
hf/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF↓ self-hosttext
text model
Qwen2.5 Coder 7B Instruct
hf/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF↓ self-hosttext
text model
Triplex
hf/SciPhi/Triplex↓ self-hosttext
text model
Qwen3 14B Claude 4.5 Opus High Reasoning Distill
hf/TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF↓ self-hosttext
text model
UIGEN T1 7B q8 0
hf/Tesslate/UIGEN-T1-7B-q8_0-GGUF↓ self-hosttext
text model
Llama 2 13B chat
hf/TheBloke/Llama-2-13B-chat-GGUF↓ self-hosttext
text model
Llama 2 7B Chat
hf/TheBloke/Llama-2-7B-Chat-GGUF↓ self-hosttext
text model
Llama 2 7B
hf/TheBloke/Llama-2-7B-GGUF↓ self-hosttext
text model
Mistral 7B Instruct v0.1
hf/TheBloke/Mistral-7B-Instruct-v0.1-GGUF↓ self-hosttext
text model
Mistral 7B Instruct v0.2
hf/TheBloke/Mistral-7B-Instruct-v0.2-GGUF↓ self-hosttext
text model
Mistral 7B OpenOrca
hf/TheBloke/Mistral-7B-OpenOrca-GGUF↓ self-hosttext
text model
Mistral 7B v0.1
hf/TheBloke/Mistral-7B-v0.1-GGUF↓ self-hosttext
text model
phi 2
hf/TheBloke/phi-2-GGUF↓ self-hosttext
text model
deepseek v4
hf/antirez/deepseek-v4-gguf↓ self-hosttext
text model
DeepSeek R1 Distill Qwen 14B
hf/bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF↓ self-hosttext
text model
gemma 2 9b it
hf/bartowski/gemma-2-9b-it-GGUF↓ self-hosttext
text model
sqlcoder 7b 2
hf/defog/sqlcoder-7b-2↓ self-hosttext
text model
gemma 2b
hf/google/gemma-2b↓ self-hosttext
text model
gemma 2b it
hf/google/gemma-2b-it↓ self-hosttext
text model
gemma 7b
hf/google/gemma-7b↓ self-hosttext
text model
gemma 7b it
hf/google/gemma-7b-it↓ self-hosttext
text model
Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled
hf/hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF↓ self-hosttext
text model
Meta Llama 3.1 8B Instruct
hf/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF↓ self-hosttext
text model
Phi 3 mini 4k instruct
hf/microsoft/Phi-3-mini-4k-instruct-gguf↓ self-hosttext
text model
bitnet b1.58 2B 4T
hf/microsoft/bitnet-b1.58-2B-4T-gguf↓ self-hosttext
text model
Biggie SmoLlm 0.15B Base
hf/nisten/Biggie-SmoLlm-0.15B-Base↓ self-hosttext
text model
Bonsai 8B
hf/prism-ml/Bonsai-8B-gguf↓ self-hosttext
text model
Llama3.1 8B Chinese Chat
hf/shenzhi-wang/Llama3.1-8B-Chinese-Chat↓ self-hosttext
text model
stable code 3b
hf/stabilityai/stable-code-3b↓ self-hosttext
text model
DeepSeek R1 0528 Qwen3 8B
hf/unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF↓ self-hosttext
text model
DeepSeek R1 Distill Llama 8B
hf/unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF↓ self-hosttext
text model
GLM 4.7 Flash REAP 23B A3B
hf/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF↓ self-hosttext
text model
Qwen3 4B
hf/unsloth/Qwen3-4B-GGUF↓ self-hosttext
text model
IBM: Granite 4.1 8B
ibm-granite/granite-4.1-8b↓ self-hosttext
tools
in $0.055 · out $0.11 /1M131K ctx
Inception: Mercury 2
inception/mercury-2text
toolsreasoning
in $0.28 · out $0.83 /1M128K ctx
inclusionAI: Ling-2.6-1T
inclusionai/ling-2.6-1ttext
tools
in $0.083 · out $0.69 /1M262K ctx
inclusionAI: Ling-2.6-flash
inclusionai/ling-2.6-flashtext
tools
in $0.011 · out $0.033 /1M262K ctx
inclusionAI: Ring-2.6-1T
inclusionai/ring-2.6-1ttext
toolsreasoning
in $0.083 · out $0.69 /1M262K ctx
Inflection: Inflection 3 Pi
inflection/inflection-3-pitext
in $2.75 · out $11.00 /1M8K ctx
Inflection: Inflection 3 Productivity
inflection/inflection-3-productivitytext
in $2.75 · out $11.00 /1M8K ctx
Kling
kuaishou/klingvideo
video model
Kwaipilot: KAT-Coder-Pro V2
kwaipilot/kat-coder-pro-v2text
tools
in $0.33 · out $1.32 /1M256K ctx
LiquidAI: LFM2-24B-A2B
liquid/lfm-2-24b-a2btext
in $0.033 · out $0.13 /1M128K ctx
Luma Dream Machine
lumalabs/dream-machinevideo
video model
Mancer: Weaver (alpha)
mancer/weavertext
in $0.83 · out $1.10 /1M8K ctx
Meta: Llama 3 70B Instruct
meta-llama/llama-3-70b-instruct↓ self-hosttext
in $0.56 · out $0.81 /1M8K ctx
Meta: Llama 3 8B Instruct
meta-llama/llama-3-8b-instruct↓ self-hosttext
in $0.044 · out $0.044 /1M8K ctx
Meta: Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instruct↓ self-hosttext
tools
in $0.44 · out $0.44 /1M131K ctx
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick↓ self-hosttext
visiontools
in $0.17 · out $0.66 /1M1.0M ctx
Meta: Llama 4 Scout
meta-llama/llama-4-scout↓ self-hosttext
visiontools
in $0.088 · out $0.33 /1M10M ctx
Meta: Llama Guard 4 12B
meta-llama/llama-guard-4-12b↓ self-hosttext
vision
in $0.20 · out $0.20 /1M164K ctx
Microsoft: Phi 4
microsoft/phi-4↓ self-hosttext
in $0.071 · out $0.15 /1M16K ctx
Microsoft: Phi 4 Mini Instruct
microsoft/phi-4-mini-instruct↓ self-hosttext
in $0.088 · out $0.39 /1M131K ctx
WizardLM-2 8x22B
microsoft/wizardlm-2-8x22b↓ self-hosttext
in $0.68 · out $0.68 /1M66K ctx
MiniMax: MiniMax-01
minimax/minimax-01text
vision
in $0.22 · out $1.21 /1M1.0M ctx
MiniMax: MiniMax M1
minimax/minimax-m1text
toolsreasoning
in $0.44 · out $2.42 /1M1M ctx
MiniMax: MiniMax M2
minimax/minimax-m2text
toolsreasoning
in $0.28 · out $1.10 /1M205K ctx
MiniMax: MiniMax M2-her
minimax/minimax-m2-hertext
in $0.33 · out $1.32 /1M66K ctx
MiniMax: MiniMax M2.1
minimax/minimax-m2.1text
toolsreasoning
in $0.32 · out $1.05 /1M205K ctx
MiniMax: MiniMax M2.5
minimax/minimax-m2.5↓ self-hosttext
toolsreasoning
in $0.17 · out $1.26 /1M205K ctx
MiniMax: MiniMax M2.7
minimax/minimax-m2.7text
toolsreasoning
in $0.31 · out $1.32 /1M205K ctx
MiniMax: MiniMax M3
minimax/minimax-m3text
visiontoolsreasoning
in $0.33 · out $1.32 /1M1.0M ctx
Mistral: Codestral 2508
mistralai/codestral-2508↓ self-hosttext
tools
in $0.33 · out $0.99 /1M256K ctx
Mistral: Devstral 2 2512
mistralai/devstral-2512↓ self-hosttext
tools
in $0.44 · out $2.20 /1M262K ctx
Mistral: Ministral 3 14B 2512
mistralai/ministral-14b-2512↓ self-hosttext
visiontools
in $0.22 · out $0.22 /1M262K ctx
Mistral: Ministral 3 3B 2512
mistralai/ministral-3b-2512↓ self-hosttext
visiontools
in $0.11 · out $0.11 /1M131K ctx
Mistral: Ministral 3 8B 2512
mistralai/ministral-8b-2512↓ self-hosttext
visiontools
in $0.17 · out $0.17 /1M262K ctx
Mistral Large
mistralai/mistral-large↓ self-hosttext
tools
in $2.20 · out $6.60 /1M128K ctx
Mistral Large 2407
mistralai/mistral-large-2407↓ self-hosttext
tools
in $2.20 · out $6.60 /1M131K ctx
Mistral: Mistral Large 3 2512
mistralai/mistral-large-2512↓ self-hosttext
visiontools
in $0.55 · out $1.65 /1M262K ctx
Mistral: Mistral Medium 3
mistralai/mistral-medium-3↓ self-hosttext
visiontools
in $0.44 · out $2.20 /1M131K ctx
Mistral: Mistral Medium 3.5
mistralai/mistral-medium-3-5↓ self-hosttext
visiontoolsreasoning
in $1.65 · out $8.25 /1M262K ctx
Mistral: Mistral Medium 3.1
mistralai/mistral-medium-3.1↓ self-hosttext
visiontools
in $0.44 · out $2.20 /1M131K ctx
Mistral: Mistral Nemo
mistralai/mistral-nemo↓ self-hosttext
tools
in $0.022 · out $0.033 /1M131K ctx
Mistral: Saba
mistralai/mistral-saba↓ self-hosttext
tools
in $0.22 · out $0.66 /1M33K ctx
Mistral: Mistral Small 3
mistralai/mistral-small-24b-instruct-2501↓ self-hosttext
in $0.055 · out $0.088 /1M33K ctx
Mistral: Mistral Small 4
mistralai/mistral-small-2603↓ self-hosttext
visiontoolsreasoning
in $0.17 · out $0.66 /1M262K ctx
Mistral: Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct↓ self-hosttext
visiontools
in $0.083 · out $0.22 /1M128K ctx
Mistral: Mixtral 8x22B Instruct
mistralai/mixtral-8x22b-instruct↓ self-hosttext
tools
in $2.20 · out $6.60 /1M66K ctx
Mistral: Voxtral Small 24B 2507
mistralai/voxtral-small-24b-2507↓ self-hosttext
audio-intools
in $0.11 · out $0.33 /1M32K ctx
MoonshotAI: Kimi K2 0711
moonshotai/kimi-k2↓ self-hosttext
tools
in $0.63 · out $2.53 /1M131K ctx
MoonshotAI: Kimi K2 0905
moonshotai/kimi-k2-0905↓ self-hosttext
tools
in $0.66 · out $2.75 /1M262K ctx
MoonshotAI: Kimi K2 Thinking
moonshotai/kimi-k2-thinking↓ self-hosttext
toolsreasoning
in $0.66 · out $2.75 /1M262K ctx
MoonshotAI: Kimi K2.5
moonshotai/kimi-k2.5↓ self-hosttext
visiontoolsreasoning
in $0.44 · out $2.09 /1M262K ctx
Morph: Morph V3 Fast
morph/morph-v3-fasttext
in $0.88 · out $1.32 /1M82K ctx
Morph: Morph V3 Large
morph/morph-v3-largetext
in $0.99 · out $2.09 /1M262K ctx
Nex AGI: DeepSeek V3.1 Nex N1
nex-agi/deepseek-v3.1-nex-n1↓ self-hosttext
tools
in $0.15 · out $0.55 /1M131K ctx
NousResearch: Hermes 2 Pro - Llama-3 8B
nousresearch/hermes-2-pro-llama-3-8b↓ self-hosttext
in $0.15 · out $0.15 /1M8K ctx
Nous: Hermes 3 405B Instruct
nousresearch/hermes-3-llama-3.1-405b↓ self-hosttext
in $1.10 · out $1.10 /1M131K ctx
Nous: Hermes 3 70B Instruct
nousresearch/hermes-3-llama-3.1-70b↓ self-hosttext
in $0.33 · out $0.33 /1M131K ctx
Nous: Hermes 4 405B
nousresearch/hermes-4-405b↓ self-hosttext
reasoning
in $1.10 · out $3.30 /1M131K ctx
Nous: Hermes 4 70B
nousresearch/hermes-4-70b↓ self-hosttext
reasoning
in $0.14 · out $0.44 /1M131K ctx
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
nvidia/llama-3.3-nemotron-super-49b-v1.5↓ self-hosttext
toolsreasoning
in $0.11 · out $0.44 /1M131K ctx
NVIDIA: Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b↓ self-hosttext
toolsreasoning
in $0.055 · out $0.22 /1M262K ctx
NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b↓ self-hosttext
toolsreasoning
in $0.099 · out $0.50 /1M1M ctx
NVIDIA: Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b↓ self-hosttext
toolsreasoning
in $0.55 · out $2.75 /1M1M ctx
NVIDIA: Nemotron Nano 9B V2
nvidia/nemotron-nano-9b-v2↓ self-hosttext
toolsreasoning
in $0.044 · out $0.18 /1M131K ctx
OpenAI: GPT-3.5 Turbo
openai/gpt-3.5-turbotext
tools
in $0.55 · out $1.65 /1M16K ctx
OpenAI: GPT-3.5 Turbo (older v0613)
openai/gpt-3.5-turbo-0613text
tools
in $1.10 · out $2.20 /1M4K ctx
OpenAI: GPT-3.5 Turbo 16k
openai/gpt-3.5-turbo-16ktext
tools
in $3.30 · out $4.40 /1M16K ctx
OpenAI: GPT-3.5 Turbo Instruct
openai/gpt-3.5-turbo-instructtext
in $1.65 · out $2.20 /1M4K ctx
OpenAI: GPT-4
openai/gpt-4text
tools
in $33.00 · out $66.00 /1M8K ctx
OpenAI: GPT-4 Turbo (older v1106)
openai/gpt-4-1106-previewtext
tools
in $11.00 · out $33.00 /1M128K ctx
OpenAI: GPT-4 Turbo Preview
openai/gpt-4-turbo-previewtext
tools
in $11.00 · out $33.00 /1M128K ctx
OpenAI: GPT-4.1
openai/gpt-4.1text
visiontools
in $2.20 · out $8.80 /1M1.0M ctx
OpenAI: GPT-4.1 Mini
openai/gpt-4.1-minitext
visiontools
in $0.44 · out $1.76 /1M1.0M ctx
OpenAI: GPT-4.1 Nano
openai/gpt-4.1-nanotext
visiontools
in $0.11 · out $0.44 /1M1.0M ctx
OpenAI: GPT-4o
openai/gpt-4otext
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13text
visiontools
in $5.50 · out $16.50 /1M128K ctx
OpenAI: GPT-4o (2024-08-06)
openai/gpt-4o-2024-08-06text
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20text
visiontools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-4o-mini
openai/gpt-4o-minitext
visiontools
in $0.17 · out $0.66 /1M128K ctx
OpenAI: GPT-4o-mini (2024-07-18)
openai/gpt-4o-mini-2024-07-18text
visiontools
in $0.17 · out $0.66 /1M128K ctx
OpenAI: GPT-4o-mini Search Preview
openai/gpt-4o-mini-search-previewtext
in $0.17 · out $0.66 /1M128K ctx
OpenAI: GPT-4o Search Preview
openai/gpt-4o-search-previewtext
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT-5
openai/gpt-5text
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Chat
openai/gpt-5-chattext
vision
in $1.38 · out $11.00 /1M128K ctx
OpenAI: GPT-5 Codex
openai/gpt-5-codextext
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Image
openai/gpt-5-imageimage
visionreasoning
in $11.00 · out $11.00 /1M400K ctx
OpenAI: GPT-5 Image Mini
openai/gpt-5-image-miniimage
visionreasoning
in $2.75 · out $2.20 /1M400K ctx
OpenAI: GPT-5 Mini
openai/gpt-5-minitext
visiontoolsreasoning
in $0.28 · out $2.20 /1M400K ctx
OpenAI: GPT-5 Nano
openai/gpt-5-nanotext
visiontoolsreasoning
in $0.055 · out $0.44 /1M400K ctx
OpenAI: GPT-5 Pro
openai/gpt-5-protext
visiontoolsreasoning
in $16.50 · out $132.00 /1M400K ctx
OpenAI: GPT-5.1
openai/gpt-5.1text
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1 Chat
openai/gpt-5.1-chattext
visiontools
in $1.38 · out $11.00 /1M128K ctx
OpenAI: GPT-5.1-Codex
openai/gpt-5.1-codextext
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1-Codex-Max
openai/gpt-5.1-codex-maxtext
visiontoolsreasoning
in $1.38 · out $11.00 /1M400K ctx
OpenAI: GPT-5.1-Codex-Mini
openai/gpt-5.1-codex-minitext
visiontoolsreasoning
in $0.28 · out $2.20 /1M400K ctx
OpenAI: GPT-5.2
openai/gpt-5.2text
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.2 Chat
openai/gpt-5.2-chattext
visiontools
in $1.93 · out $15.40 /1M128K ctx
OpenAI: GPT-5.2-Codex
openai/gpt-5.2-codextext
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.2 Pro
openai/gpt-5.2-protext
visiontoolsreasoning
in $23.10 · out $184.80 /1M400K ctx
OpenAI: GPT-5.3 Chat
openai/gpt-5.3-chattext
visiontools
in $1.93 · out $15.40 /1M128K ctx
OpenAI: GPT-5.3-Codex
openai/gpt-5.3-codextext
visiontoolsreasoning
in $1.93 · out $15.40 /1M400K ctx
OpenAI: GPT-5.4
openai/gpt-5.4text
visiontoolsreasoning
in $2.75 · out $16.50 /1M1.1M ctx
OpenAI: GPT-5.4 Image 2
openai/gpt-5.4-image-2image
visionreasoning
in $8.80 · out $16.50 /1M272K ctx
OpenAI: GPT-5.4 Mini
openai/gpt-5.4-minitext
visiontoolsreasoning
in $0.83 · out $4.95 /1M400K ctx
OpenAI: GPT-5.4 Nano
openai/gpt-5.4-nanotext
visiontoolsreasoning
in $0.22 · out $1.38 /1M400K ctx
OpenAI: GPT-5.4 Pro
openai/gpt-5.4-protext
visiontoolsreasoning
in $33.00 · out $198.00 /1M1.1M ctx
OpenAI: GPT-5.5
openai/gpt-5.5text
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI: GPT-5.5 Pro
openai/gpt-5.5-protext
visiontoolsreasoning
in $33.00 · out $198.00 /1M1.1M ctx
OpenAI: GPT Audio
openai/gpt-audioaudio
audio-intools
in $2.75 · out $11.00 /1M128K ctx
OpenAI: GPT Audio Mini
openai/gpt-audio-miniaudio
audio-intools
in $0.66 · out $2.64 /1M128K ctx
OpenAI: GPT Chat Latest
openai/gpt-chat-latesttext
visiontools
in $5.50 · out $33.00 /1M400K ctx
OpenAI: gpt-oss-safeguard-20b
openai/gpt-oss-safeguard-20b↓ self-hosttext
toolsreasoning
in $0.083 · out $0.33 /1M131K ctx
OpenAI: o1
openai/o1text
visiontoolsreasoning
in $16.50 · out $66.00 /1M200K ctx
OpenAI: o1-pro
openai/o1-protext
visionreasoning
in $165.00 · out $660.00 /1M200K ctx
OpenAI: o3
openai/o3text
visiontoolsreasoning
in $2.20 · out $8.80 /1M200K ctx
OpenAI: o3 Deep Research
openai/o3-deep-researchtext
visiontoolsreasoning
in $11.00 · out $44.00 /1M200K ctx
OpenAI: o3 Mini
openai/o3-minitext
toolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o3 Mini High
openai/o3-mini-hightext
toolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o3 Pro
openai/o3-protext
visiontoolsreasoning
in $22.00 · out $88.00 /1M200K ctx
OpenAI: o4 Mini
openai/o4-minitext
visiontoolsreasoning
in $1.21 · out $4.84 /1M200K ctx
OpenAI: o4 Mini Deep Research
openai/o4-mini-deep-researchtext
visiontoolsreasoning
in $2.20 · out $8.80 /1M200K ctx
OpenAI: o4 Mini High
openai/o4-mini-hightext
visiontoolsreasoning
in $1.21 · out $4.84 /1M200K ctx
Sora 2
openai/sora-2video
video model
Sora 2 Pro
openai/sora-2-provideo
video model
Text Embedding 3 Large
openai/text-embedding-3-largeembeddings
in $0.14 · out $0 /1M
Text Embedding 3 Small
openai/text-embedding-3-smallembeddings
in $0.022 · out $0 /1M
Auto Router
openrouter/autoimage
visionaudio-intoolsreasoning
image model2M ctx
Perceptron: Perceptron Mk1
perceptron/perceptron-mk1text
visionreasoning
in $0.17 · out $1.65 /1M33K ctx
Perplexity: Sonar
perplexity/sonartext
vision
in $1.10 · out $1.10 /1M127K ctx
Perplexity: Sonar Deep Research
perplexity/sonar-deep-researchtext
reasoning
in $2.20 · out $8.80 /1M128K ctx
Perplexity: Sonar Pro
perplexity/sonar-protext
vision
in $3.30 · out $16.50 /1M200K ctx
Perplexity: Sonar Pro Search
perplexity/sonar-pro-searchtext
visionreasoning
in $3.30 · out $16.50 /1M200K ctx
Perplexity: Sonar Reasoning Pro
perplexity/sonar-reasoning-protext
visionreasoning
in $2.20 · out $8.80 /1M128K ctx
Prime Intellect: INTELLECT-3
prime-intellect/intellect-3text
toolsreasoning
in $0.22 · out $1.21 /1M131K ctx
Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct↓ self-hosttext
tools
in $0.40 · out $0.44 /1M131K ctx
Qwen: Qwen2.5 7B Instruct
qwen/qwen-2.5-7b-instruct↓ self-hosttext
in $0.044 · out $0.11 /1M131K ctx
Qwen: Qwen-Plus
qwen/qwen-plus↓ self-hosttext
tools
in $0.29 · out $0.86 /1M1M ctx
Qwen: Qwen Plus 0728
qwen/qwen-plus-2025-07-28↓ self-hosttext
tools
in $0.29 · out $0.86 /1M1M ctx
Qwen: Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct↓ self-hosttext
vision
in $0.28 · out $0.83 /1M131K ctx
Qwen: Qwen3 14B
qwen/qwen3-14b↓ self-hosttext
toolsreasoning
in $0.11 · out $0.26 /1M132K ctx
Qwen: Qwen3 235B A22B
qwen/qwen3-235b-a22b↓ self-hosttext
toolsreasoning
in $0.50 · out $2.00 /1M131K ctx
Qwen: Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-2507↓ self-hosttext
tools
in $0.078 · out $0.11 /1M262K ctx
Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507↓ self-hosttext
toolsreasoning
in $0.11 · out $0.11 /1M262K ctx
Qwen: Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507↓ self-hosttext
tools
in $0.053 · out $0.21 /1M131K ctx
Qwen: Qwen3 30B A3B Thinking 2507
qwen/qwen3-30b-a3b-thinking-2507↓ self-hosttext
toolsreasoning
in $0.088 · out $0.44 /1M131K ctx
Qwen: Qwen3 32B
qwen/qwen3-32b↓ self-hosttext
toolsreasoning
in $0.088 · out $0.31 /1M131K ctx
Qwen: Qwen3 8B
qwen/qwen3-8b↓ self-hosttext
toolsreasoning
in $0.055 · out $0.44 /1M131K ctx
Qwen: Qwen3 Coder 480B A35B
qwen/qwen3-coder↓ self-hosttext
tools
in $0.24 · out $1.98 /1M1.0M ctx
Qwen: Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct↓ self-hosttext
tools
in $0.077 · out $0.30 /1M160K ctx
Qwen: Qwen3 Coder Flash
qwen/qwen3-coder-flash↓ self-hosttext
tools
in $0.21 · out $1.07 /1M1M ctx
Qwen: Qwen3 Coder Next
qwen/qwen3-coder-next↓ self-hosttext
tools
in $0.12 · out $0.88 /1M262K ctx
Qwen: Qwen3 Coder Plus
qwen/qwen3-coder-plus↓ self-hosttext
tools
in $0.71 · out $3.58 /1M1M ctx
Qwen: Qwen3 Max
qwen/qwen3-max↓ self-hosttext
tools
in $0.86 · out $4.29 /1M262K ctx
Qwen: Qwen3 Max Thinking
qwen/qwen3-max-thinking↓ self-hosttext
toolsreasoning
in $0.86 · out $4.29 /1M262K ctx
Qwen: Qwen3 Next 80B A3B Instruct
qwen/qwen3-next-80b-a3b-instruct↓ self-hosttext
tools
in $0.099 · out $1.21 /1M262K ctx
Qwen: Qwen3 Next 80B A3B Thinking
qwen/qwen3-next-80b-a3b-thinking↓ self-hosttext
toolsreasoning
in $0.11 · out $0.86 /1M262K ctx
Qwen: Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct↓ self-hosttext
visiontools
in $0.22 · out $0.97 /1M262K ctx
Qwen: Qwen3 VL 235B A22B Thinking
qwen/qwen3-vl-235b-a22b-thinking↓ self-hosttext
visiontoolsreasoning
in $0.29 · out $2.86 /1M131K ctx
Qwen: Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instruct↓ self-hosttext
visiontools
in $0.14 · out $0.57 /1M262K ctx
Qwen: Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking↓ self-hosttext
visiontoolsreasoning
in $0.14 · out $1.72 /1M131K ctx
Qwen: Qwen3 VL 32B Instruct
qwen/qwen3-vl-32b-instruct↓ self-hosttext
visiontools
in $0.11 · out $0.46 /1M262K ctx
Qwen: Qwen3 VL 8B Instruct
qwen/qwen3-vl-8b-instruct↓ self-hosttext
visiontools
in $0.088 · out $0.55 /1M256K ctx
Qwen: Qwen3 VL 8B Thinking
qwen/qwen3-vl-8b-thinking↓ self-hosttext
visiontoolsreasoning
in $0.13 · out $1.50 /1M256K ctx
Qwen: Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b↓ self-hosttext
visiontoolsreasoning
in $0.29 · out $2.29 /1M262K ctx
Qwen: Qwen3.5-27B
qwen/qwen3.5-27b↓ self-hosttext
visiontoolsreasoning
in $0.21 · out $1.72 /1M262K ctx
Qwen: Qwen3.5-35B-A3B
qwen/qwen3.5-35b-a3b↓ self-hosttext
visiontoolsreasoning
in $0.15 · out $1.10 /1M262K ctx
Qwen: Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b↓ self-hosttext
visiontoolsreasoning
in $0.43 · out $2.57 /1M262K ctx
Qwen: Qwen3.5-9B
qwen/qwen3.5-9b↓ self-hosttext
visiontoolsreasoning
in $0.044 · out $0.17 /1M262K ctx
Qwen: Qwen3.5-Flash
qwen/qwen3.5-flash-02-23↓ self-hosttext
visiontoolsreasoning
in $0.071 · out $0.29 /1M1M ctx
Qwen: Qwen3.5 Plus 2026-02-15
qwen/qwen3.5-plus-02-15↓ self-hosttext
visiontoolsreasoning
in $0.29 · out $1.72 /1M1M ctx
Qwen: Qwen3.5 Plus 2026-04-20
qwen/qwen3.5-plus-20260420↓ self-hosttext
visiontoolsreasoning
in $0.33 · out $1.98 /1M1M ctx
Qwen: Qwen3.6 27B
qwen/qwen3.6-27b↓ self-hosttext
visiontoolsreasoning
in $0.32 · out $3.52 /1M262K ctx
Qwen: Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b↓ self-hosttext
visiontoolsreasoning
in $0.15 · out $1.10 /1M262K ctx
Qwen: Qwen3.6 Flash
qwen/qwen3.6-flash↓ self-hosttext
visiontoolsreasoning
in $0.21 · out $1.24 /1M1M ctx
Qwen: Qwen3.6 Max Preview
qwen/qwen3.6-max-preview↓ self-hosttext
toolsreasoning
in $1.14 · out $6.86 /1M262K ctx
Qwen: Qwen3.6 Plus
qwen/qwen3.6-plus↓ self-hosttext
visiontoolsreasoning
in $0.36 · out $2.15 /1M1M ctx
Qwen: Qwen3.7 Max
qwen/qwen3.7-max↓ self-hosttext
toolsreasoning
in $1.38 · out $4.13 /1M1M ctx
Qwen: Qwen3.7 Plus
qwen/qwen3.7-plus↓ self-hosttext
visiontoolsreasoning
in $0.44 · out $1.76 /1M1M ctx
Reka Edge
rekaai/reka-edgetext
visiontools
in $0.11 · out $0.11 /1M16K ctx
Reka Flash 3
rekaai/reka-flash-3text
reasoning
in $0.11 · out $0.22 /1M66K ctx
Relace: Relace Apply 3
relace/relace-apply-3text
in $0.94 · out $1.38 /1M256K ctx
Relace: Relace Search
relace/relace-searchtext
tools
in $1.10 · out $3.30 /1M256K ctx
Runway Gen-4
runwayml/gen-4video
video model
Sao10k: Llama 3 Euryale 70B v2.1
sao10k/l3-euryale-70btext
tools
in $1.63 · out $1.63 /1M8K ctx
Sao10K: Llama 3 8B Lunaris
sao10k/l3-lunaris-8btext
in $0.044 · out $0.055 /1M8K ctx
Sao10K: Llama 3.1 70B Hanami x1
sao10k/l3.1-70b-hanami-x1text
in $3.30 · out $3.30 /1M16K ctx
Sao10K: Llama 3.1 Euryale 70B v2.2
sao10k/l3.1-euryale-70btext
tools
in $0.94 · out $0.94 /1M131K ctx
Sao10K: Llama 3.3 Euryale 70B
sao10k/l3.3-euryale-70btext
in $0.71 · out $0.83 /1M131K ctx
StepFun: Step 3.5 Flash
stepfun/step-3.5-flashtext
toolsreasoning
in $0.099 · out $0.33 /1M262K ctx
StepFun: Step 3.7 Flash
stepfun/step-3.7-flashtext
visiontoolsreasoning
in $0.22 · out $1.26 /1M256K ctx
Switchpoint Router
switchpoint/routertext
reasoning
in $0.94 · out $3.74 /1M131K ctx
Tencent: Hunyuan A13B Instruct
tencent/hunyuan-a13b-instructtext
reasoning
in $0.15 · out $0.63 /1M131K ctx
Tencent: Hy3 preview
tencent/hy3-previewtext
toolsreasoning
in $0.069 · out $0.23 /1M262K ctx
TheDrummer: Cydonia 24B V4.1
thedrummer/cydonia-24b-v4.1text
in $0.33 · out $0.55 /1M131K ctx
TheDrummer: Rocinante 12B
thedrummer/rocinante-12btext
tools
in $0.19 · out $0.47 /1M33K ctx
TheDrummer: Skyfall 36B V2
thedrummer/skyfall-36b-v2text
in $0.60 · out $0.88 /1M33K ctx
TheDrummer: UnslopNemo 12B
thedrummer/unslopnemo-12btext
tools
in $0.44 · out $0.44 /1M33K ctx
ReMM SLERP 13B
undi95/remm-slerp-l2-13btext
in $0.50 · out $0.71 /1M6K ctx
Upstage: Solar Pro 3
upstage/solar-pro-3↓ self-hosttext
toolsreasoning
in $0.17 · out $0.66 /1M128K ctx
Writer: Palmyra X5
writer/palmyra-x5text
in $0.66 · out $6.60 /1M1.0M ctx
xAI: Grok 4.20
x-ai/grok-4.20text
visiontoolsreasoning
in $1.38 · out $2.75 /1M2M ctx
xAI: Grok 4.20 Multi-Agent
x-ai/grok-4.20-multi-agenttext
visionreasoning
in $2.20 · out $6.60 /1M2M ctx
xAI: Grok 4.3
x-ai/grok-4.3text
visiontoolsreasoning
in $1.38 · out $2.75 /1M1M ctx
xAI: Grok Build 0.1
x-ai/grok-build-0.1text
visiontoolsreasoning
in $1.10 · out $2.20 /1M256K ctx
Xiaomi: MiMo-V2-Flash
xiaomi/mimo-v2-flashtext
toolsreasoning
in $0.11 · out $0.33 /1M262K ctx
Xiaomi: MiMo-V2.5
xiaomi/mimo-v2.5text
visionaudio-intoolsreasoning
in $0.15 · out $0.31 /1M1.0M ctx
Xiaomi: MiMo-V2.5-Pro
xiaomi/mimo-v2.5-protext
toolsreasoning
in $0.48 · out $0.96 /1M1.0M ctx
Z.ai: GLM 4 32B
z-ai/glm-4-32b↓ self-hosttext
tools
in $0.11 · out $0.11 /1M128K ctx
Z.ai: GLM 4.5
z-ai/glm-4.5↓ self-hosttext
toolsreasoning
in $0.66 · out $2.42 /1M131K ctx
Z.ai: GLM 4.5 Air
z-ai/glm-4.5-air↓ self-hosttext
toolsreasoning
in $0.14 · out $0.94 /1M131K ctx
Z.ai: GLM 4.5V
z-ai/glm-4.5v↓ self-hosttext
visiontoolsreasoning
in $0.66 · out $1.98 /1M66K ctx
Z.ai: GLM 4.6
z-ai/glm-4.6↓ self-hosttext
toolsreasoning
in $0.47 · out $1.91 /1M203K ctx
Z.ai: GLM 4.6V
z-ai/glm-4.6v↓ self-hosttext
visiontoolsreasoning
in $0.33 · out $0.99 /1M131K ctx
Z.ai: GLM 4.7
z-ai/glm-4.7↓ self-hosttext
toolsreasoning
in $0.44 · out $1.93 /1M203K ctx
Z.ai: GLM 5
z-ai/glm-5↓ self-hosttext
toolsreasoning
in $0.66 · out $2.11 /1M203K ctx
Z.ai: GLM 5.1
z-ai/glm-5.1↓ self-hosttext
toolsreasoning
in $1.08 · out $3.39 /1M203K ctx
Z.ai: GLM 5V Turbo
z-ai/glm-5v-turbo↓ self-hosttext
visiontoolsreasoning
in $1.32 · out $4.40 /1M203K ctx
Anthropic Claude Haiku Latest
~anthropic/claude-haiku-latesttext
visiontoolsreasoning
in $1.10 · out $5.50 /1M200K ctx
Anthropic: Claude Opus Latest
~anthropic/claude-opus-latesttext
visiontoolsreasoning
in $5.50 · out $27.50 /1M1M ctx
Anthropic Claude Sonnet Latest
~anthropic/claude-sonnet-latesttext
visiontoolsreasoning
in $3.30 · out $16.50 /1M1M ctx
Google Gemini Flash Latest
~google/gemini-flash-latesttext
visionaudio-intoolsreasoning
in $1.65 · out $9.90 /1M1.0M ctx
Google Gemini Pro Latest
~google/gemini-pro-latesttext
visionaudio-intoolsreasoning
in $2.20 · out $13.20 /1M1.0M ctx
MoonshotAI Kimi Latest
~moonshotai/kimi-latest↓ self-hosttext
visiontoolsreasoning
in $0.75 · out $3.76 /1M262K ctx
OpenAI GPT Latest
~openai/gpt-latesttext
visiontoolsreasoning
in $5.50 · out $33.00 /1M1.1M ctx
OpenAI GPT Mini Latest
~openai/gpt-mini-latesttext
visiontoolsreasoning
in $0.83 · out $4.95 /1M400K ctx