Skip to content
Rapid Router

Simple, usage-based pricing

You pay the provider's list price on every request, nothing added. Our flat      platform fee is charged once, when you buy credits. Top up in US dollars and get an invoice on every top-up, with no local tax added. No seats, no minimum spend, no monthly fee.

A top-up is billed in US dollars and invoiced as an export of service: zero-rated, no tax added to the invoice. The      covers the card and settlement costs and is the whole markup.

Free

$0.00

Enough to build a prototype and see if this fits.

  • ✓Sponsored :free models, on us
  • ✓50 free requests a day on free-eligible models
  • ✓60 requests per minute
  • ✓8 requests in flight
  • ✓Community support
Start free
Most popular

Pay as you go

    

Charged once when you buy credits. Usage bills at provider list price.

  • ✓Every model and provider
  • ✓Dollar top-ups, invoice included
  • ✓Budget caps on each key
  • ✓Usage logs and exports
  • ✓Email support
Add credits

Enterprise

Custom

For committed spend and invoicing.

  • ✓Bank-transfer invoicing
  • ✓Team accounts with roles
  • ✓Bring your own provider keys
  • ✓Dedicated support
See what is included

Work out what it would cost you

10,000
1001,000,000
1,500
100200,000
400
5032,000
Estimated per month
$97
Per request
$0.00032
Provider list price
$96.60
Our fee,     
$0.00
Total
$96.60
Start with a top-up

Every model, side by side

Per million tokens at the provider's list price. This is what your balance is debited: nothing is added when a request is billed. Our      is charged once, when you buy the credits.

ModelProviderInput / 1MOutput / 1M
qwen/qwen3.7-flash:freeAlibaba (Qwen)FreeFree
meta-llama/llama-3.3-70b-instruct:freeDeepInfraFreeFree
google/gemma-4-31b-it:freeGoogleFreeFree
qwen/qwen3.5-0.8b:freeDeepInfraFreeFree
qwen/qwen3.5-2b:freeDeepInfraFreeFree
qwen/qwen2-7b-instruct:freeDeepInfraFreeFree
qwen/qwen2.5-7b-instruct:freeDeepInfraFreeFree
qwen/qwen2.5-coder-7b:freeDeepInfraFreeFree
qwen/qwq-32b:freeDeepInfraFreeFree
google/gemma-4-e4b-it:freeDeepInfraFreeFree
meta-llama/llama-3.2-1b-instruct:freeDeepInfraFreeFree
meta-llama/llama-3.2-3b-instruct:freeDeepInfraFreeFree
microsoft/phi-4-reasoning-plus:freeDeepInfraFreeFree
microsoft/wizardlm-2-7b:freeDeepInfraFreeFree
stepfun/step-3.5-flash:freeDeepInfraFreeFree
z-ai/glm-4.7-flash:freeDeepInfraFreeFree
sao10k/l3-8b-lunaris-v1:freeDeepInfraFreeFree
google/codegemma-7b-it:freeDeepInfraFreeFree
google/gemma-1.1-7b-it:freeDeepInfraFreeFree
google/gemma-2-27b-it:freeDeepInfraFreeFree
meta-llama/meta-llama-3-8b-instruct:freeDeepInfraFreeFree
meta-llama/meta-llama-3.1-8b-instruct:freeDeepInfraFreeFree
openchat/openchat-3.6-8b:freeDeepInfraFreeFree
deepseek-ai/deepseek-r1-distill-qwen-32b:freeDeepInfraFreeFree
google/gemma-2-9b-it:freeDeepInfraFreeFree
microsoft/phi-4-multimodal-instruct:freeDeepInfraFreeFree
mistralai/mistral-7b-instruct-v0.3:freeDeepInfraFreeFree
mistralai/mistral-small-3.1-24b-instruct-2503:freeDeepInfraFreeFree
google/gemma-4-26b-a4b-it:freeGoogleFreeFree
audio8/audio8-tts-preview-0.6bDeepInfraFreeFree
black-forest-labs/flux-1-devDeepInfraFreeFree
black-forest-labs/flux-1-redux-devDeepInfraFreeFree
black-forest-labs/flux-2-klein-4bDeepInfraFreeFree
black-forest-labs/flux-2-klein-9bDeepInfraFreeFree
black-forest-labs/flux.1-kontext-devDeepInfraFreeFree
black-forest-labs/flux.1-kontext-maxTogether AIFreeFree
black-forest-labs/flux.1-kontext-proTogether AIFreeFree
black-forest-labs/flux.1-schnellDeepInfraFreeFree
black-forest-labs/flux.1.1-proTogether AIFreeFree
black-forest-labs/flux.2-devDeepInfraFreeFree
black-forest-labs/flux.2-flexTogether AIFreeFree
black-forest-labs/flux.2-maxTogether AIFreeFree
black-forest-labs/flux.2-proDeepInfraFreeFree
bosonai/higgsaudiov2.5DeepInfraFreeFree
bria/blur_backgroundDeepInfraFreeFree
bria/bria-3.2DeepInfraFreeFree
bria/bria-3.2-vectorDeepInfraFreeFree
bria/enhanceDeepInfraFreeFree
bria/eraseDeepInfraFreeFree
bria/erase_foregroundDeepInfraFreeFree
bria/expandDeepInfraFreeFree
bria/fiboDeepInfraFreeFree
bria/fibo_editDeepInfraFreeFree
bria/gen_fillDeepInfraFreeFree
bria/remove_backgroundDeepInfraFreeFree
bria/replace_backgroundDeepInfraFreeFree
bytedance/seedream-3.0Together AIFreeFree
bytedance/seedream-4DeepInfraFreeFree
bytedance/seedream-4.0Together AIFreeFree
bytedance/seedream-4.5DeepInfraFreeFree
bytedance/seedream-5.0-liteTogether AIFreeFree
canopylabs/orpheus-3bTogether AIFreeFree
canopylabs/orpheus-3b-0.1-ftDeepInfraFreeFree
cartesia/sonic-2Together AIFreeFree
cartesia/sonic-3Together AIFreeFree
clarityai/creativeDeepInfraFreeFree
clarityai/crystalDeepInfraFreeFree
clarityai/fluxDeepInfraFreeFree
elevenlabs/eleven-flash-v2ElevenLabsFreeFree
elevenlabs/eleven-flash-v2.5ElevenLabsFreeFree
elevenlabs/eleven-multilingual-v2ElevenLabsFreeFree
elevenlabs/eleven-turbo-v2ElevenLabsFreeFree
elevenlabs/eleven-turbo-v2.5ElevenLabsFreeFree
elevenlabs/eleven-v3ElevenLabsFreeFree
elevenlabs/eleven-v3-conversationalElevenLabsFreeFree
elevenlabs/eleven-v4ElevenLabsFreeFree
elevenlabs/eleven-v4-turboElevenLabsFreeFree
elevenlabs/scribe-v2ElevenLabsFreeFree
elevenlabs/scribe-v2-medicalElevenLabsFreeFree
fastvideo/fastwan-qad-fp8-1.3bDeepInfraFreeFree
google/flash-image-3.1-liteTogether AIFreeFree
google/gemini-2.5-flash-imageGoogleFreeFree
google/gemini-3-pro-imageGoogleFreeFree
google/gemini-3-pro-image-previewGoogleFreeFree
google/gemini-3.1-flash-imageGoogleFreeFree
google/gemini-3.1-flash-image-previewGoogleFreeFree
google/veo-3.0DeepInfraFreeFree
google/veo-3.0-fastDeepInfraFreeFree
google/veo-3.1GoogleFreeFree
google/veo-3.1-fastGoogleFreeFree
hexgrad/kokoro-82mTogether AIFreeFree
ideogram/ideogram-3.0Together AIFreeFree
ideogram/ideogram-4.0Together AIFreeFree
inworld-ai/inworld-tts-1.5-maxDeepInfraFreeFree
inworld-ai/inworld-tts-1.5-miniDeepInfraFreeFree
inworld-ai/realtime-tts-1.5-maxDeepInfraFreeFree
inworld-ai/realtime-tts-1.5-miniDeepInfraFreeFree
inworld-ai/realtime-tts-2DeepInfraFreeFree
mistralai/voxtral-mini-3b-2507DeepInfraFreeFree
mistralai/voxtral-small-24b-2507DeepInfraFreeFree
nvidia/nemotron-3.5-asr-streaming-multilingual-0.6bDeepInfraFreeFree
nvidia/parakeet-tdt-0.6bTogether AIFreeFree
openai/gpt-image-1OpenAIFreeFree
openai/gpt-image-1.5Together AIFreeFree
openai/gpt-image-1.5-directOpenAIFreeFree
openai/gpt-image-2Together AIFreeFree
openai/gpt-image-2-directOpenAIFreeFree
openai/sora-2OpenAIFreeFree
openai/sora-2-proOpenAIFreeFree
openai/tts-1OpenAIFreeFree
openai/tts-1-hdOpenAIFreeFree
openai/whisper-1OpenAIFreeFree
openai/whisper-baseDeepInfraFreeFree
openai/whisper-base.enDeepInfraFreeFree
openai/whisper-large-v3Together AIFreeFree
openai/whisper-large-v3-turboDeepInfraFreeFree
openai/whisper-medium.enDeepInfraFreeFree
openai/whisper-small.enDeepInfraFreeFree
openai/whisper-timestamped-mediumDeepInfraFreeFree
openai/whisper-timestamped-medium.enDeepInfraFreeFree
openai/whisper-tiny.enDeepInfraFreeFree
pixverse/pixverse-6-t2vDeepInfraFreeFree
prunaai/p-imageDeepInfraFreeFree
prunaai/p-image-editDeepInfraFreeFree
prunaai/p-image-ideogramTogether AIFreeFree
prunaai/p-videoDeepInfraFreeFree
qwen/qwen-imageTogether AIFreeFree
qwen/qwen-image-2.0Together AIFreeFree
qwen/qwen-image-2.0-proTogether AIFreeFree
qwen/qwen-image-editDeepInfraFreeFree
qwen/qwen-image-edit-maxDeepInfraFreeFree
qwen/qwen-image-maxDeepInfraFreeFree
qwen/qwen3-asr-0.6bDeepInfraFreeFree
qwen/qwen3-asr-1.7bDeepInfraFreeFree
qwen/qwen3-ttsDeepInfraFreeFree
qwen/qwen3-tts-voicedesignDeepInfraFreeFree
resembleai/chatterboxDeepInfraFreeFree
resembleai/chatterbox-multilingualDeepInfraFreeFree
resembleai/chatterbox-turboDeepInfraFreeFree
run-diffusion/juggernaut-fluxDeepInfraFreeFree
rundiffusion/juggernaut-lightning-fluxTogether AIFreeFree
rundiffusion/juggernaut-lightning-flux:freeTogether AIFreeFree
rundiffusion/juggernaut-pro-fluxTogether AIFreeFree
sarvam/bulbul-v3SarvamFreeFree
sarvam/mayuraSarvamFreeFree
sarvam/saarika-v2SarvamFreeFree
sesame/csm-1bDeepInfraFreeFree
stabilityai/sd3.5DeepInfraFreeFree
stabilityai/sd3.5-mediumDeepInfraFreeFree
stabilityai/sdxl-turboDeepInfraFreeFree
stabilityai/stable-diffusion-xlTogether AIFreeFree
stabilityai/stable-diffusion-xl:freeTogether AIFreeFree
wan-ai/wan2.2-t2v-a14bDeepInfraFreeFree
wan-ai/wan2.6-imageTogether AIFreeFree
wan-ai/wan2.6-image-editDeepInfraFreeFree
wan-ai/wan2.6-t2iDeepInfraFreeFree
wan-ai/wan2.6-t2vDeepInfraFreeFree
wan-ai/wan2.7-image-editDeepInfraFreeFree
x-ai/grok-imagine-imagexAIFreeFree
x-ai/grok-imagine-image-2.0xAIFreeFree
x-ai/grok-imagine-image-qualityxAIFreeFree
x-ai/grok-imagine-videoxAIFreeFree
x-ai/grok-imagine-video-1.5xAIFreeFree
xiaomimimo/mimo-v2.5-ttsDeepInfraFreeFree
xiaomimimo/mimo-v2.5-tts-voicedesignDeepInfraFreeFree
zyphra/zonos-v0.1-hybridDeepInfraFreeFree
zyphra/zonos-v0.1-transformerDeepInfraFreeFree
google/embeddinggemma-300mDeepInfra$0.002Free
meta-llama/llama-3.2-1b-instructDeepInfra$0.005$0.010
baai/bge-base-en-v1.5DeepInfra$0.005Free
intfloat/e5-base-v2DeepInfra$0.005Free
qwen/qwen3-embedding-0.6b-batchDeepInfra$0.005Free
sentence-transformers/all-minilm-l12-v2DeepInfra$0.005Free
sentence-transformers/all-minilm-l6-v2DeepInfra$0.005Free
sentence-transformers/all-mpnet-base-v2DeepInfra$0.005Free
sentence-transformers/clip-vit-b-32DeepInfra$0.005Free
sentence-transformers/clip-vit-b-32-multilingual-v1DeepInfra$0.005Free
sentence-transformers/multi-qa-mpnet-base-dot-v1DeepInfra$0.005Free
sentence-transformers/paraphrase-minilm-l6-v2DeepInfra$0.005Free
shibing624/text2vec-base-chineseDeepInfra$0.005Free
thenlper/gte-baseDeepInfra$0.005Free
qwen/qwen3.5-0.8bDeepInfra$0.010$0.050
baai/bge-en-iclDeepInfra$0.010Free
baai/bge-large-en-v1.5DeepInfra$0.010Free
baai/bge-m3DeepInfra$0.010Free
baai/bge-m3-multiDeepInfra$0.010Free
intfloat/e5-large-v2DeepInfra$0.010Free
intfloat/multilingual-e5-largeDeepInfra$0.010Free
nvidia/llama-nemotron-embed-vl-1b-v2DeepInfra$0.010Free
nvidia/nemotron-3-embed-1b-nvfp4DeepInfra$0.010Free
qwen/qwen3-embedding-0.6bDeepInfra$0.010Free
qwen/qwen3-embedding-4b-batchDeepInfra$0.010Free
qwen/qwen3-embedding-8bDeepInfra$0.010Free
qwen/qwen3-reranker-0.6bDeepInfra$0.010Free
thenlper/gte-largeDeepInfra$0.010Free
z-ai/glm-5.3-flashZ.ai$0.012$0.900
nvidia/nemotron-3-embed-1b-bf16DeepInfra$0.015Free
qwen/qwen3.5-2bDeepInfra$0.020$0.100
google/gemma-4-e4b-itDeepInfra$0.020$0.100
meta-llama/llama-3.2-3b-instructDeepInfra$0.020$0.020
meta-llama/meta-llama-3.1-8b-instructDeepInfra$0.020$0.050
meta-llama/meta-llama-3.1-8b-instruct-turbo:freeDeepInfra$0.020$0.040
meta-llama/meta-llama-3.1-8b-instruct-turboDeepInfra$0.020$0.040
novita/meta-llama/llama-3.1-8b-instructNovita$0.020$0.050
openai/text-embedding-3-smallOpenAI$0.020Free
qwen/qwen3-embedding-4bDeepInfra$0.020Free
qwen/qwen2.5-coder-7bDeepInfra$0.025$0.050
qwen/qwen3-reranker-4bDeepInfra$0.025Free
mistralai/mistral-7b-instruct-v0.3DeepInfra$0.028$0.054
mistralai/mistral-nemo-instruct-2407DeepInfra$0.029$0.030
mistralai/mistral-nemo-instruct-2407:freeDeepInfra$0.029$0.030
qwen/qwen3.7-flashAlibaba (Qwen)$0.030$0.130
openai/gpt-oss-20bDeepInfra$0.030$0.140
openai/gpt-oss-20b:freeDeepInfra$0.030$0.140
qwen/qwen3.5-4bDeepInfra$0.030$0.150
deepseek-ai/deepseek-ocrDeepInfra$0.030$0.100
qwen/qwen3.7-flash-2026-07-15Alibaba (Qwen)$0.030$0.130
sao10k/l3-8b-lunaris-v1DeepInfra$0.030$0.060
meta-llama/meta-llama-3-8b-instructDeepInfra$0.030$0.040
google/gemma-2-9b-itDeepInfra$0.030$0.060
novita/deepseek/deepseek-ocr-2Novita$0.030$0.030
novita/zai-org/autoglm-phone-9b-multilingualNovita$0.035$0.138
nvidia/nemotron-3-embed-8bDeepInfra$0.035Free
openai/gpt-oss-120bDeepInfra$0.037$0.170
nvidia/nvidia-nemotron-nano-9b-v2DeepInfra$0.040$0.160
qwen/qwen2.5-7b-instructDeepInfra$0.040$0.100
sao10k/l3-8b-lunaris-v1-turboDeepInfra$0.040$0.050
qwen/qwen3-embedding-8b-batchDeepInfra$0.040Free
mistralai/mistral-small-24b-instruct-2501DeepInfra$0.050$0.080
mistralai/mistral-small-24b-instruct-2501:freeDeepInfra$0.050$0.080
google/gemma-3-12b-itDeepInfra$0.050$0.150
nvidia/nemotron-3-nano-30b-a3bDeepInfra$0.050$0.200
openai/gpt-5-nanoOpenAI$0.050$0.400
openai/gpt-5-nano-2025-08-07OpenAI$0.050$0.400
google/gemma-3-4b-itDeepInfra$0.050$0.100
google/gemma-3-4b-it:freeDeepInfra$0.050$0.100
microsoft/phi-4-multimodal-instructDeepInfra$0.050$0.100
mistralai/mistral-small-3.1-24b-instruct-2503DeepInfra$0.050$0.100
novita/sao10k/l3-8b-stheno-v3.2Novita$0.050$0.050
qwen/qwen3-reranker-8bDeepInfra$0.050Free
meta-llama/llama-guard-3-8bDeepInfra$0.055$0.055
qwen/qwen2-7b-instructDeepInfra$0.055$0.055
microsoft/wizardlm-2-7bDeepInfra$0.055$0.055
openchat/openchat_3.5DeepInfra$0.055$0.055
openchat/openchat-3.6-8bDeepInfra$0.055$0.055
mistralai/mistral-7b-instruct-v0.1DeepInfra$0.055$0.055
mistralai/mistral-7b-instruct-v0.2DeepInfra$0.055$0.055
deepseek/deepseek-v4-flash-0731DeepInfra$0.060$0.180
inclusionai/ling-3.0-flashDeepInfra$0.060$0.180
deepinfra/deepseek-ai/deepseek-v4-flash-0731DeepInfra$0.060$0.180
nvidia/nvidia-nemotron-3.5-lightningDeepInfra$0.060$0.160
qwen/qwen2.5-coder-32b-instructDeepInfra$0.060$0.150
deepinfra/zai-org/glm-4.7-flashDeepInfra$0.060$0.400
z-ai/glm-4.7-flashDeepInfra$0.060$0.400
mistralai/devstral-small-2505DeepInfra$0.060$0.120
deepinfra/ibm-granite/granite-4.2-8bDeepInfra$0.060$0.250
deepinfra/inclusionai/ling-3.0-flash-vlDeepInfra$0.060$0.180
qwen/qwen3.5-flashAlibaba (Qwen)$0.065$0.260
qwen/qwen3.5-flash-2026-02-23Alibaba (Qwen)$0.065$0.260
qwen/qwen3-coder-30b-a3b-instructDeepInfra$0.070$0.260
microsoft/phi-4DeepInfra$0.070$0.140
google/gemma-4-26b-a4b-itGoogle$0.070$0.340
google/gemma-1.1-7b-itDeepInfra$0.070$0.070
google/codegemma-7b-itDeepInfra$0.070$0.070
microsoft/phi-4-reasoning-plusDeepInfra$0.070$0.350
qwen/qwen-vl-ocrAlibaba (Qwen)$0.070$0.160
mistralai/devstral-small-2507DeepInfra$0.070$0.280
novita/zai-org/glm-4.7-flashNovita$0.070$0.400
openai/gpt-oss-safeguard-20bGroq$0.075$0.300
mistralai/mistral-small-3.2-24b-instruct-2506DeepInfra$0.075$0.200
novita/inclusionai/ling-3.0-flash-finNovita$0.075$0.220
novita/inclusionai/ling-3.0-flash-santeNovita$0.075$0.220
novita/inclusionai/ling-3.0-flash-vlNovita$0.075$0.220
z-ai/glm-5.3Z.ai$0.079$4.80
qwen/qwen3-32bDeepInfra$0.080$0.280
qwen/qwen3-32b:freeDeepInfra$0.080$0.280
google/gemma-3-27b-itDeepInfra$0.080$0.160
nvidia/nvidia-nemotron-3-super-120b-a12bDeepInfra$0.085$0.400
nvidia/nvidia-nemotron-3-super-120b-a12b:freeDeepInfra$0.085$0.400
qwen/qwen3-235b-a22b-instruct-2507Alibaba (Qwen)$0.090$0.550
allenai/olmocr-2-7b-1025DeepInfra$0.090$0.190
deepinfra/deepseek-ai/deepseek-v4-flashDeepInfra$0.090$0.180
google/gemma-4-31b-it-turboDeepInfra$0.090$0.340
stepfun/step-3.5-flashDeepInfra$0.090$0.300
qwen/qwen3-next-80b-a3b-instructDeepInfra$0.090$1.10
deepseek/deepseek-v4-flashDeepInfra$0.090$0.180
google/gemma-4-31b-itGoogle$0.090$0.340
arize-ai/qwen-2-1.5b-instructTogether AI$0.100$0.100
deepinfra/meta-llama/llama-3.3-70b-instruct-turboDeepInfra$0.100$0.320
koboldai/llama2-13b-tiefighterDeepInfra$0.100$0.100
deepreinforce-ai/ornith-1.0-35bDeepInfra$0.100$0.750
qwen/qwen3.5-9bDeepInfra$0.100$0.150
qwen/qwen3.6-35b-a3bDeepInfra$0.100$0.950
meta-llama/llama-4-scout-17b-16e-instructDeepInfra$0.100$0.300
meta-llama/llama-4-scout-17b-16e-instruct:freeDeepInfra$0.100$0.300
qwen/qwen3-vl-4b-instructDeepInfra$0.100$0.600
qwen/qwen3-vl-4b-thinkingDeepInfra$0.100$1.00
openai/gpt-4.1-nanoOpenAI$0.100$0.400
openai/gpt-4.1-nano-2025-04-14OpenAI$0.100$0.400
mistralai/ministral-3b-2512Mistral$0.100$0.100
mistralai/ministral-3b-latestMistral$0.100$0.100
mistralai/voxtral-small-2507Mistral$0.100$0.400
mistralai/voxtral-small-latestMistral$0.100$0.400
anthropic/claude-haiku-5-5Anthropic$0.100$0.500
deepinfra/bytedance/seed-2.0-miniDeepInfra$0.100$0.400
mistralai/mistral-embedMistral$0.100Free
openai/gpt-6-lunaOpenAI$0.100$0.500
openai/text-embedding-ada-002OpenAI$0.100Free
deepinfra/qwen/qwen3.8-flashDeepInfra$0.113$0.382
novasky-ai/sky-t1-32b-previewDeepInfra$0.120$0.180
qwen/qwen3-14bDeepInfra$0.120$0.240
qwen/qwen3-14b:freeDeepInfra$0.120$0.240
qwen/qwen3-30b-a3bDeepInfra$0.120$0.500
qwen/qwen3-30b-a3b:freeDeepInfra$0.120$0.500
qwen/qwq-32b-previewDeepInfra$0.120$0.180
qwen/qwen-mt-liteAlibaba (Qwen)$0.120$0.360
qwen/qwen3-vl-flashAlibaba (Qwen)$0.120$0.960
austism/chronos-hermes-13b-v2DeepInfra$0.130$0.130
gryphe/mythomax-l2-13b-turboDeepInfra$0.130$0.130
meta-llama/llama-2-13b-chat-hfDeepInfra$0.130$0.130
qwen/qwen3-30b-a3b-instruct-2507Alibaba (Qwen)$0.130$0.520
novita/zai-org/glm-4.5-airNovita$0.130$0.850
openai/text-embedding-3-largeOpenAI$0.130Free
allenai/olmocr-2DeepInfra$0.140$0.800
allenai/olmocr-7b-0825DeepInfra$0.140$0.800
allenai/olmocr-7b-1025DeepInfra$0.140$0.800
tencent/hy3DeepInfra$0.140$0.580
qwen/qwen3.5-35b-a3bDeepInfra$0.140$1.00
paddlepaddle/paddleocr-vl-0.9bDeepInfra$0.140$0.800
microsoft/phi-3-medium-4k-instructDeepInfra$0.140$0.140
deepinfra/xiaomimimo/mimo-v2.6-flashDeepInfra$0.140$0.280
novita/xiaomimimo/mimo-v2.6-flashNovita$0.140$0.280
openai/gpt-4o-miniOpenAI$0.150$0.600
mistralai/ministral-8b-latestMistral$0.150$0.150
minimax/minimax-m2.5DeepInfra$0.150$1.15
qwen/qwen3-next-80b-a3b-thinkingAlibaba (Qwen)$0.150$1.20
openai/gpt-oss-120b-turboDeepInfra$0.150$0.600
bigcode/starcoder2-15b-instruct-v0.1DeepInfra$0.150$0.150
qwen/qwq-32bDeepInfra$0.150$0.400
qwen/qwen3-vl-30b-a3b-instructDeepInfra$0.150$0.600
openai/gpt-4o-mini-2024-07-18OpenAI$0.150$0.600
mistralai/ministral-8b-2512Mistral$0.150$0.150
deepinfra/zai-org/glm-5.3-flashDeepInfra$0.150$0.500
google/gemini-embedding-001Google$0.150Free
mistralai/codestral-embedMistral$0.150Free
mistralai/mistral-small-2603Mistral$0.150$0.600
mistralai/mistral-small-latestMistral$0.150$0.600
novita/qwen/qwen3.8-flashNovita$0.150$0.470
novita/zai-org/glm-5.3-flashNovita$0.150$0.500
qwen/qwen-mt-flashAlibaba (Qwen)$0.160$0.490
qwen/qwen-mt-turboAlibaba (Qwen)$0.160$0.490
novita/xiaomimimo/mimo-v2.5Novita$0.168$0.336
meta-llama/llama-guard-4-12bDeepInfra$0.180$0.180
qwen/qwen3-8bAlibaba (Qwen)$0.180$0.700
qwen/qwen3-235b-a22bDeepInfra$0.180$0.540
qwen/qwen3-vl-8b-instructDeepInfra$0.180$0.690
qwen/qwen3-vl-8b-thinkingDeepInfra$0.180$2.09
qwen/qwen3.6-flashAlibaba (Qwen)$0.188$1.13
qwen/qwen3.6-flash-2026-04-16Alibaba (Qwen)$0.188$1.13
qwen/qwen3.5-27bAlibaba (Qwen)$0.195$1.56
qwen/qwen3-coder-flashAlibaba (Qwen)$0.195$0.975
mistralai/ministral-14b-latestMistral$0.200$0.200
nvidia/nemotron-content-safety-3.5DeepInfra$0.200$0.200
qwen/qwen3-30b-a3b-thinking-2507Alibaba (Qwen)$0.200$2.40
mistralai/ministral-14b-2512Mistral$0.200$0.200
openai/gpt-5.6-lunaOpenAI$0.200$1.20
z-ai/glm-4.5-airDeepInfra$0.200$1.10
allenai/olmo-3.1-32b-instructDeepInfra$0.200$0.600
nvidia/nemotron-3-nano-omni-30b-a3b-reasoningDeepInfra$0.200$0.800
nvidia/nvidia-nemotron-nano-12b-v2-vlDeepInfra$0.200$0.600
deepinfra/stepfun-ai/step-3.7-flashDeepInfra$0.200$1.15
meta-llama/llama-4-maverick-17b-128e-instruct-fp8DeepInfra$0.200$0.800
pearl-ai/gemma-4-31b-itDeepInfra$0.200$0.400
stepfun/step-3.7-flashDeepInfra$0.200$1.15
qwen/qwen3.8-27bDeepInfra$0.200$2.50
openai/gpt-5.4-nanoOpenAI$0.200$1.25
openai/gpt-5.4-nano-2026-03-17OpenAI$0.200$1.25
qwen/qwen2.5-vl-32b-instructDeepInfra$0.200$0.600
qwen/qwen3-vl-235b-a22b-instructDeepInfra$0.200$0.880
deepinfra/deepseek-ai/deepseek-v4.1-flashDeepInfra$0.200$0.600
deepinfra/nvidia/nvidia-nemotron-3.5-super-vlDeepInfra$0.200$1.00
deepinfra/openai/gpt-oss-120b-ultraDeepInfra$0.200$0.950
qwen/qwen-vl-plusAlibaba (Qwen)$0.210$0.630
meta-llama/llama-3.3-70b-instructDeepInfra$0.230$0.400
qwen/qwen3-235b-a22b-thinking-2507Alibaba (Qwen)$0.230$2.30
cognitivecomputations/dolphin-2.6-mixtral-8x7bDeepInfra$0.240$0.240
deepseek-ai/deepseek-v3-0324DeepInfra$0.240$0.900
novita/mindai/macaron-v1-tallNovita$0.247$1.43
deepinfra/minimaxai/minimax-m2.7DeepInfra$0.250$1.00
minimax/minimax-m2.7DeepInfra$0.250$1.00
openai/gpt-5-miniOpenAI$0.250$2.00
qwen/qvq-72b-previewDeepInfra$0.250$0.500
openai/gpt-5-mini-2025-08-07OpenAI$0.250$2.00
qwen/qwen-flashAlibaba (Qwen)$0.250$2.00
deepseek-ai/deepseek-v3.1DeepInfra$0.250$0.950
google/gemini-3.1-flash-liteGoogle$0.250$1.50
google/gemini-3.1-flash-lite-previewGoogle$0.250$1.50
deepinfra/bytedance/seed-1.8DeepInfra$0.250$2.00
novita/qwen/qwen3-omni-30b-a3b-thinkingNovita$0.250$0.970
minimax/minimax-m2DeepInfra$0.254$1.02
deepseek/deepseek-v3.2DeepInfra$0.260$0.380
qwen/qwen-plus-2025-04-28Alibaba (Qwen)$0.260$0.780
qwen/qwen3.5-122b-a10bAlibaba (Qwen)$0.260$2.08
qwen/qwen3.5-plus-2026-02-15Alibaba (Qwen)$0.260$1.56
qwen/qwen-plus-2025-07-14Alibaba (Qwen)$0.260$0.780
qwen/qwen-plus-2025-09-11Alibaba (Qwen)$0.260$0.780
qwen/qwen-plus-2025-12-01Alibaba (Qwen)$0.260$0.780
qwen/qwen-plus-latestAlibaba (Qwen)$0.260$0.780
deepinfra/deepseek-ai/deepseek-v3.2DeepInfra$0.260$0.380
minimax/minimax-m2.1DeepInfra$0.270$0.950
allenai/olmocr-7b-0725-fp8DeepInfra$0.270$1.50
google/gemma-2-27b-itDeepInfra$0.270$0.270
deepseek-ai/deepseek-r1-distill-qwen-32bDeepInfra$0.270$0.270
deepseek/deepseek-v3.1-terminusDeepInfra$0.270$0.950
deepinfra/google/gemma-4-31b-it-ultraDeepInfra$0.270$0.760
deepinfra/minimaxai/minimax-m3DeepInfra$0.280$1.10
minimax/minimax-m3DeepInfra$0.280$1.10
qwen/qwen3-vl-30b-a3b-thinkingDeepInfra$0.290$0.990
google/gemini-3.5-flash-liteGoogle$0.300$2.50
deepinfra/meta-models/muse-glimmer-30bDeepInfra$0.300$1.20
mistralai/codestral-latestMistral$0.300$0.900
meta/muse-glimmer-30bDeepInfra$0.300$1.20
z-ai/glm-4.6vDeepInfra$0.300$0.900
qwen/qwen3.5-plusAlibaba (Qwen)$0.300$1.80
qwen/qwen3.5-plus-2026-04-20Alibaba (Qwen)$0.300$1.80
meta-llama/meta-llama-3-70b-instructDeepInfra$0.300$0.400
qwen/qwen3-coder-480b-a35b-instruct-turboDeepInfra$0.300$1.00
qwen/qwen3-coder-nextAlibaba (Qwen)$0.300$1.50
qwen/qwen3-coder-480b-a35b-instructAlibaba (Qwen)$0.300$1.00
mistralai/codestral-2508Mistral$0.300$0.900
google/gemini-flash-lite-latestGoogle$0.300$2.50
deepinfra/google/gemini-2.5-flashDeepInfra$0.300$2.50
deepinfra/inclusionai/ling-3.1-flashDeepInfra$0.300$0.900
novita/deepseek/deepseek-v4.1-flashNovita$0.300$1.20
novita/deepseek/deepseek-v4.1-flash-dstNovita$0.300$1.20
novita/deepseek/deepseek-v4.1-flash-pNovita$0.300$1.20
novita/inclusionai/ling-3.1-flashNovita$0.300$0.900
novita/zai-org/glm-4.6vNovita$0.300$0.900
moonshotai/kimi-k3Moonshot$0.304$11.94
qwen/qwen3.7-plusTogether AI$0.320$1.28
qwen/qwen3.6-27bGroq$0.320$3.20
qwen/qwen3.7-plus-2026-05-26Alibaba (Qwen)$0.320$1.28
deepseek-ai/deepseek-v3DeepInfra$0.320$0.890
qwen/qwen3.6-plus-2026-04-02Alibaba (Qwen)$0.325$1.95
openbmb/minicpm-llama3-v-2_5DeepInfra$0.340$0.340
meta-llama/llama-3.2-11b-vision-instructDeepInfra$0.345$0.345
cognitivecomputations/dolphin-2.9.1-llama-3-70bDeepInfra$0.350$0.400
meta-llama/llama-3.2-90b-vision-instructDeepInfra$0.350$0.400
lizpreciatior/lzlv_70b_fp16_hfDeepInfra$0.350$0.400
mattshumer/reflection-llama-3.1-70bDeepInfra$0.350$0.400
qwen/qwen2-72b-instructDeepInfra$0.350$0.400
sarvam/sarvam-105bSarvam$0.360$0.900
sarvam/sarvam-105b-conversationsSarvam$0.360$0.900
qwen/qwen2.5-72b-instructDeepInfra$0.360$0.400
z-ai/glm-5.3-flashxZ.ai$0.370$1.25
google/gemini-3.7-flashGoogle$0.375$1.88
google/gemini-flash-latestGoogle$0.375$1.88
z-ai/glm-4.5DeepInfra$0.380$1.60
gryphe/mythomax-l2-13bDeepInfra$0.400$0.400
qwen/qwen3-vl-235b-a22b-thinkingAlibaba (Qwen)$0.400$4.00
openai/gpt-4.1-miniOpenAI$0.400$1.60
nvidia/llama-3.3-nemotron-super-49b-v1.5DeepInfra$0.400$0.400
moonshotai/kimi-k2-instruct-0905DeepInfra$0.400$2.00
deepinfra/xiaomimimo/mimo-v2.5DeepInfra$0.400$2.00
xiaomi/mimo-v2.5DeepInfra$0.400$2.00
qwen/qwen3.5-omni-flashAlibaba (Qwen)$0.400$3.00
deepinfra/zai-org/glm-4.7DeepInfra$0.400$1.75
z-ai/glm-4.7DeepInfra$0.400$1.75
meta-llama/meta-llama-3.1-70b-instructDeepInfra$0.400$0.400
meta-llama/meta-llama-3.1-70b-instruct-turboDeepInfra$0.400$0.400
qwen/qwen3-omni-flashAlibaba (Qwen)$0.400$3.00
openai/gpt-4.1-mini-2025-04-14OpenAI$0.400$1.60
mistralai/mistral-medium-2505Mistral$0.400$2.00
mistralai/mistral-medium-2508Mistral$0.400$2.00
mistralai/mistral-medium-3Mistral$0.400$2.00
deepinfra/xiaomimimo/mimo-v2.6-proDeepInfra$0.430$0.870
novita/xiaomimimo/mimo-v2.6-proNovita$0.435$0.870
deepinfra/deepseek-ai/deepseek-v4-flash-vision-expDeepInfra$0.440$1.32
mistralai/devstral-2512Mistral$0.440$2.20
novita/deepseek/deepseek-v4-flash-0731-pNovita$0.440$1.32
thinkingmachines/inkling-smallDeepInfra$0.450$1.20
moonshotai/kimi-k2.5DeepInfra$0.450$2.25
qwen/qwen3.5-397b-a17bDeepInfra$0.450$3.00
moonshotai/kimi-k2-thinkingDeepInfra$0.470$2.00
nvidia/nvidia-nemotron-3-ultra-550b-a55bDeepInfra$0.500$2.20
deepinfra/deepseek-ai/deepseek-r1-0528DeepInfra$0.500$2.15
moonshotai/kimi-k2-instructDeepInfra$0.500$2.00
meta-llama/llama-4-maverick-17b-128e-instruct-turboDeepInfra$0.500$0.500
deepinfra/zai-org/glm-4.6DeepInfra$0.500$2.00
qwen/qwen3.6-plusTogether AI$0.500$3.00
z-ai/glm-4.6DeepInfra$0.500$2.00
deepseek/deepseek-r1-0528DeepInfra$0.500$2.15
openai/gpt-3.5-turboOpenAI$0.500$1.50
openai/gpt-3.5-turbo-0125OpenAI$0.500$1.50
deepseek-ai/deepseek-prover-v2-671bDeepInfra$0.500$2.18
google/gemini-3-flash-previewGoogle$0.500$3.00
deepinfra/bytedance/seed-2.0-codeDeepInfra$0.500$3.00
deepinfra/bytedance/seed-2.0-proDeepInfra$0.500$3.00
novita/xiaomimimo/mimo-v2.5-proNovita$0.522$1.04
mistralai/mixtral-8x7b-instruct-v0.1DeepInfra$0.540$0.540
minimax/minimax-m2.5-highspeedMiniMax$0.540$2.16
novita/minimaxai/minimax-m1-80kNovita$0.550$2.20
novita/zai-org/glm-4.6Novita$0.550$2.20
qwen/qwen3-vl-plusAlibaba (Qwen)$0.600$4.80
minimax/minimax-m2.7-highspeedMiniMax$0.600$2.40
minimax/minimax-m2.1-highspeedMiniMax$0.600$2.40
nvidia/nemotron-3-ultra-550b-a55bTogether AI$0.600$3.60
deepinfra/zai-org/glm-5DeepInfra$0.600$2.08
moonshotai/kimi-k2.5-turboDeepInfra$0.600$3.00
phind/phind-codellama-34b-v2DeepInfra$0.600$0.600
novita/moonshotai/kimi-k2-0905Novita$0.600$2.50
novita/zai-org/glm-4.5vNovita$0.600$1.80
novita/zai-org/glm-4.7Novita$0.600$2.20
novita/microsoft/wizardlm-2-8x22bNovita$0.620$0.620
meta-llama/llama-2-70b-chat-hfDeepInfra$0.640$0.800
qwen/qwen3-coder-plusAlibaba (Qwen)$0.650$3.25
qwen/qwen3-coder-plus-2025-07-22Alibaba (Qwen)$0.650$3.25
qwen/qwen3-coder-plus-2025-09-23Alibaba (Qwen)$0.650$3.25
moonshotai/kimi-k2.7-codeDeepInfra$0.680$3.40
deepinfra/airoboros-70bDeepInfra$0.700$0.900
sao10k/l3-70b-euryale-v2.1DeepInfra$0.700$0.800
deepseek/deepseek-r1DeepInfra$0.700$2.40
deepseek/deepseek-r1-distill-llama-70bDeepInfra$0.700$0.800
nousresearch/hermes-3-llama-3.1-70bDeepInfra$0.700$0.700
novita/deepseek/deepseek-r1-turboNovita$0.700$2.50
google/gemini-3.6-flashGoogle$0.750$3.75
deepinfra/zai-org/glm-5.2DeepInfra$0.750$2.40
z-ai/glm-5.2DeepInfra$0.750$2.40
moonshotai/kimi-k2.6DeepInfra$0.750$3.50
openai/gpt-5.4-miniOpenAI$0.750$4.50
openai/gpt-5.4-mini-2026-03-17OpenAI$0.750$4.50
qwen/qwen3-maxAlibaba (Qwen)$0.780$3.90
qwen/qwen3-max-2025-09-23Alibaba (Qwen)$0.780$3.90
qwen/qwen3-max-2026-01-23Alibaba (Qwen)$0.780$3.90
qwen/qwen3-max-previewAlibaba (Qwen)$0.780$3.90
qwen/qwq-plusAlibaba (Qwen)$0.800$2.40
meta-llama/meta-llama-3.1-405b-instructDeepInfra$0.800$0.800
qwen/qwen-vl-maxAlibaba (Qwen)$0.800$3.20
qwen/qwen-coder-plusAlibaba (Qwen)$0.800$4.00
novita/mindai/macaron-v1-ventiNovita$0.825$2.48
deepinfra/tencent/hy4-previewDeepInfra$0.834$2.50
novita/tencent/hy4-previewNovita$0.834$2.50
sao10k/l3.3-70b-euryale-v2.3DeepInfra$0.850$0.850
sao10k/l3.1-70b-euryale-v2.2DeepInfra$0.850$0.850
novita/deepseek/deepseek_v3Novita$0.890$0.890
deepinfra/zai-org/glm-5.3DeepInfra$0.900$4.00
thinkingmachines/inklingDeepInfra$0.950$4.05
z-ai/glm-5Z.ai$1.00$3.20
anthropic/claude-haiku-4-5Anthropic$1.00$5.00
x-ai/grok-build-0.1xAI$1.00$2.00
nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16DeepInfra$1.00$5.00
deepinfra/xiaomimimo/mimo-v2.5-proDeepInfra$1.00$3.00
xiaomi/mimo-v2.5-proDeepInfra$1.00$3.00
deepseek-ai/deepseek-r1-0528-turboDeepInfra$1.00$3.00
deepseek-ai/deepseek-r1-turboDeepInfra$1.00$3.00
nousresearch/hermes-3-llama-3.1-405bDeepInfra$1.00$1.00
deepseek-ai/deepseek-v3-0324-turboDeepInfra$1.00$3.00
anthropic/claude-haiku-4-5-20251001Anthropic$1.00$5.00
deepinfra/stepfun-ai/step-5-previewDeepInfra$1.00$2.70
novita/stepfun/step-5-previewNovita$1.00$2.70
novita/zai-org/glm-5Novita$1.00$3.20
qwen/qwen3.6-max-previewAlibaba (Qwen)$1.03$6.16
meta-llama/llama-3.3-70bTogether AI$1.04$1.04
deepinfra/zai-org/glm-5.1DeepInfra$1.05$3.50
z-ai/glm-5.1DeepInfra$1.05$3.50
openai/o3-miniOpenAI$1.10$4.40
openai/o3-mini-2025-01-31OpenAI$1.10$4.40
openai/o4-miniOpenAI$1.10$4.40
openai/o4-mini-2025-04-16OpenAI$1.10$4.40
nvidia/llama-3.1-nemotron-70b-instructDeepInfra$1.20$1.20
z-ai/glm-5-turboZ.ai$1.20$4.00
x-ai/grok-4.3xAI$1.25$2.50
x-ai/grok-4.20xAI$1.25$2.50
x-ai/grok-4.20-non-reasoningxAI$1.25$2.50
qwen/qwen3.7-maxTogether AI$1.25$3.75
openai/gpt-5.1OpenAI$1.25$10.00
openai/gpt-5OpenAI$1.25$10.00
openai/gpt-5-2025-08-07OpenAI$1.25$10.00
deepinfra/google/gemini-2.5-proDeepInfra$1.25$10.00
openai/gpt-5.1-2025-11-13OpenAI$1.25$10.00
deepinfra/deepseek-ai/deepseek-v4-proDeepInfra$1.30$2.60
deepinfra/deepseek-ai/deepseek-v4-pro-0813DeepInfra$1.30$2.60
deepseek/deepseek-v4-proDeepInfra$1.30$2.60
deepseek/deepseek-v4-pro-0813DeepInfra$1.30$2.60
novita/deepseek/deepseek-v4-pro-0813-pNovita$1.32$3.96
novita/zai-org/glm-5.1Novita$1.38$4.40
qwen/qwen3.5-omni-plusAlibaba (Qwen)$1.40$11.00
novita/zai-org/glm-5.2Novita$1.40$4.40
novita/zai-org/glm-5.3Novita$1.40$4.40
novita/zai-org/glm-5.3-pNovita$1.40$4.40
qwen/qwen3.7-max-previewAlibaba (Qwen)$1.48$4.42
qwen/qwen3.7-max-2026-05-20Alibaba (Qwen)$1.48$4.42
qwen/qwen3.7-max-2026-06-08Alibaba (Qwen)$1.48$4.42
qwen/qwen3.7-max-2026-05-17Alibaba (Qwen)$1.48$4.42
google/gemini-3.5-flashGoogle$1.50$9.00
mistralai/mistral-mediumMistral$1.50$7.50
mistralai/mistral-medium-2604Mistral$1.50$7.50
mistralai/mistral-medium-3-5Mistral$1.50$7.50
mistralai/mistral-medium-3.5Mistral$1.50$7.50
mistralai/mistral-medium-latestMistral$1.50$7.50
qwen/qwen-maxAlibaba (Qwen)$1.60$6.40
deepinfra/qwen/qwen3.8-maxDeepInfra$1.65$4.95
openai/gpt-5.2OpenAI$1.75$14.00
openai/gpt-5.2-2025-12-11OpenAI$1.75$14.00
moonshotai/kimi-k2.7-code-highspeedMoonshot$1.90$8.00
anthropic/claude-sonnet-5Anthropic$2.00$10.00
google/nano-banana-pro-previewGoogle$2.00$12.00
x-ai/grok-4.5xAI$2.00$6.00
x-ai/grok-4.6xAI$2.00$6.00
openai/gpt-6.1-solOpenAI$2.00$10.00
google/gemini-3.1-pro-previewGoogle$2.00$12.00
qwen/qwen3.8-2.4t-a95bDeepInfra$2.00$6.00
google/gemini-3.1-pro-preview-customtoolsGoogle$2.00$12.00
google/gemini-pro-latestGoogle$2.00$12.00
openai/o3OpenAI$2.00$8.00
openai/o3-2025-04-16OpenAI$2.00$8.00
openai/gpt-5.6-terraOpenAI$2.00$12.00
openai/gpt-4.1OpenAI$2.00$8.00
openai/gpt-4.1-2025-04-14OpenAI$2.00$8.00
anthropic/claude-sonnet-5-5Anthropic$2.00$10.00
deepinfra/google/gemini-3.1-proDeepInfra$2.00$12.00
novita/qwen/qwen3.8-maxNovita$2.00$6.00
openai/gpt-6-solOpenAI$2.00$10.00
x-ai/grok-4.7xAI$2.00$6.00
qwen/qwen-mt-plusAlibaba (Qwen)$2.46$7.37
openai/gpt-4oOpenAI$2.50$10.00
openai/gpt-5.4OpenAI$2.50$15.00
openai/gpt-5.4-2026-03-05OpenAI$2.50$15.00
openai/gpt-4o-2024-08-06OpenAI$2.50$10.00
openai/gpt-4o-2024-11-20OpenAI$2.50$10.00
anthropic/claude-sonnet-4-5Anthropic$3.00$15.00
anthropic/claude-sonnet-4-6Anthropic$3.00$15.00
openai/gpt-3.5-turbo-16kOpenAI$3.00$4.00
anthropic/claude-sonnet-4-5-20250929Anthropic$3.00$15.00
novita/moonshotai/kimi-k3-pNovita$3.00$15.00
anthropic/claude-opus-5-5Anthropic$4.00$20.00
google/gemini-4-argonGoogle$4.00$20.00
openai/gpt-5.6-solOpenAI$4.00$20.00
novita/deepseek/deepseek-r1/communityNovita$4.00$4.00
nvidia/nemotron-4-340b-instructDeepInfra$4.20$4.20
anthropic/claude-opus-4-7Anthropic$5.00$25.00
anthropic/claude-opus-4-8Anthropic$5.00$25.00
anthropic/claude-opus-5Anthropic$5.00$25.00
anthropic/claude-opus-4-5Anthropic$5.00$25.00
anthropic/claude-opus-4-6Anthropic$5.00$25.00
openai/gpt-5.5OpenAI$5.00$30.00
openai/gpt-5.5-2026-04-23OpenAI$5.00$30.00
openai/gpt-4o-2024-05-13OpenAI$5.00$15.00
anthropic/claude-opus-4-5-20251101Anthropic$5.00$25.00
anthropic/claude-fable-5Anthropic$10.00$50.00
openai/gpt-4-turboOpenAI$10.00$30.00
openai/gpt-4-turbo-2024-04-09OpenAI$10.00$30.00
anthropic/claude-fable-5-1Anthropic$10.00$50.00
openai/gpt-6-astraOpenAI$10.00$50.00
openai/o1OpenAI$15.00$60.00
openai/o1-2024-12-17OpenAI$15.00$60.00
openai/gpt-4OpenAI$30.00$60.00
openai/gpt-4-0613OpenAI$30.00$60.00