Перейти к содержимому

Каталог моделей

Просмотрите 500+ передовых AI-моделей, доступных через единый API. Только самые свежие модели 2026 года — GPT-5.4, Claude Opus 4.7, Gemini 3 Pro, DeepSeek V3.2, Grok 4, Llama 4. Все совместимы с OpenAI.

Показано 513 из 513 моделей

МодельПровайдерКонтекстВход / 1MВыход / 1M

CodeLlama 70B

airouter-cloud/codellama-70b-instruct

Self-Hosted
AI Router Cloud16K$0.40$0.40

Command R+

airouter-cloud/command-r-plus

Self-Hosted
AI Router Cloud131K$0.30$0.30

DBRX Instruct

airouter-cloud/dbrx-instruct

Self-Hosted
AI Router Cloud33K$0.30$0.30

DeepSeek R1

airouter-cloud/deepseek-r1

Self-Hosted
AI Router Cloud66K$0.50$0.50

DeepSeek V3

airouter-cloud/deepseek-v3

Self-Hosted
AI Router Cloud66K$0.30$0.30

Gemma 2 27B

airouter-cloud/gemma-2-27b-it

Self-Hosted
AI Router Cloud8K$0.15$0.15

Gemma 2 9B

airouter-cloud/gemma-2-9b-it

Self-Hosted
AI Router Cloud8K$0.05$0.05

Llama 3.2 90B Vision

airouter-cloud/llama-3.2-90b-vision

Self-Hosted
AI Router Cloud131K$0.50$0.50

Llama 3.3 70B Instruct

airouter-cloud/llama-3.3-70b-instruct

Self-Hosted
AI Router Cloud131K$0.40$0.40

Llama 3.3 8B Instruct

airouter-cloud/llama-3.3-8b-instruct

Self-Hosted
AI Router Cloud131K$0.05$0.05

Llama Guard 3

airouter-cloud/llama-guard-3-8b

Self-Hosted
AI Router Cloud131K$0.05$0.05

Mistral Large

airouter-cloud/mistral-large-instruct

Self-Hosted
AI Router Cloud131K$0.40$0.40

Mistral Small 24B

airouter-cloud/mistral-small-instruct

Self-Hosted
AI Router Cloud33K$0.10$0.10

Mixtral 8x22B

airouter-cloud/mixtral-8x22b-instruct

Self-Hosted
AI Router Cloud66K$0.30$0.30

Phi-4

airouter-cloud/phi-4

Self-Hosted
AI Router Cloud16K$0.05$0.05

Qwen 2.5 32B Instruct

airouter-cloud/qwen-2.5-32b-instruct

Self-Hosted
AI Router Cloud131K$0.20$0.20

Qwen 2.5 72B Instruct

airouter-cloud/qwen-2.5-72b-instruct

Self-Hosted
AI Router Cloud131K$0.40$0.40

Qwen 2.5 7B Instruct

airouter-cloud/qwen-2.5-7b-instruct

Self-Hosted
AI Router Cloud131K$0.05$0.05

StarCoder2 15B

airouter-cloud/starcoder2-15b

Self-Hosted
AI Router Cloud16K$0.10$0.10

Yi 1.5 34B

airouter-cloud/yi-1.5-34b-chat

Self-Hosted
AI Router Cloud4K$0.20$0.20

Jamba 1.5 Large

ai21/jamba-1.5-large

AI21256K$2.00$8.00

Jamba 1.5 Mini

ai21/jamba-1.5-mini

AI21256K$0.20$0.40

Jamba Large

ai21/jamba-large

AI21256K$2.00$8.00

Claude Fable 5.1

anthropic/claude-fable-5-1

Anthropic1.0M$10.00$50.00

Claude Haiku 4.5

anthropic/claude-haiku-4-5

Anthropic200K$1.00$5.00

Claude Opus 5

anthropic/claude-opus-5

Anthropic1.0M$5.00$25.00

Claude Sonnet 4.6

anthropic/claude-sonnet-4-6

Anthropic200K$3.00$15.00

Claude Sonnet 5

anthropic/claude-sonnet-5

Anthropic1.0M$2.00$10.00

Llama 3.1 70B Instruct

baseten/meta-llama/Meta-Llama-3.1-70B-Instruct

Baseten131K$0.60$0.80

Llama 3.1 8B Instruct

baseten/meta-llama/Meta-Llama-3.1-8B-Instruct

Baseten131K$0.10$0.20

Qwen 2.5 72B Instruct

baseten/Qwen/Qwen2.5-72B-Instruct

Baseten131K$0.60$0.80

Amazon Nova Lite

bedrock/nova-lite

Bedrock300K$0.06$0.24

Amazon Nova Micro

bedrock/nova-micro

Bedrock128K$0.04$0.14

Amazon Nova Pro

bedrock/nova-pro

Bedrock300K$0.80$3.20

Claude Haiku 4.5 (Bedrock)

bedrock/claude-haiku-4.5

Bedrock200K$1.00$5.00

Llama 3.3 70B Instruct (Bedrock)

bedrock/llama-3.3-70b

Bedrock128K$0.72$0.72

Mistral Large 3 (Bedrock)

bedrock/mistral-large-3

Bedrock128K$0.50$1.50

Seed 1.6 Flash

bytedance/seed-1.6-flash

Bytedance256K$0.07$0.30

Seed 1.8

bytedance/seed-1.8

Bytedance256K$0.25$2.00

Seed 2.0 Lite

bytedance/seed-2.0-lite

Bytedance256K$0.25$2.00

Seed 2.0 Mini

bytedance/seed-2.0-mini

Bytedance256K$0.10$0.40

Seed 2.0 Pro

bytedance/seed-2.0-pro

Bytedance256K$0.50$3.00

Llama 3.1 8B

cerebras/llama3.1-8b

Cerebras128K$0.10$0.20

Llama 3.3 70B

cerebras/llama3.3-70b

Cerebras128K$0.60$1.20

Llama 4 Scout

cerebras/llama-4-scout-17b-16e-instruct

Cerebras131K$0.20$0.60

Llama 3.3 70B Instruct

cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast

Cloudflare131K$0.34$0.40

Command R

cohere/command-r

Cohere128K$0.50$1.50

Command R+

cohere/command-r-plus

Cohere128K$3.00$15.00

Command R+ (Aug 2024)

cohere/command-r-plus-08-2024

Cohere128K$2.50$10.00

anthropic/claude-fable-5

deepinfra/anthropic/claude-fable-5

DeepinfraN/AN/AN/A

anthropic/claude-haiku-4-5

deepinfra/anthropic/claude-haiku-4-5

DeepinfraN/AN/AN/A

anthropic/claude-opus-4-7

deepinfra/anthropic/claude-opus-4-7

DeepinfraN/AN/AN/A

anthropic/claude-opus-4-8

deepinfra/anthropic/claude-opus-4-8

DeepinfraN/AN/AN/A

anthropic/claude-opus-5

deepinfra/anthropic/claude-opus-5

DeepinfraN/AN/AN/A

anthropic/claude-sonnet-4-6

deepinfra/anthropic/claude-sonnet-4-6

DeepinfraN/AN/AN/A

anthropic/claude-sonnet-5

deepinfra/anthropic/claude-sonnet-5

DeepinfraN/AN/AN/A

Audio8/Audio8-TTS-Preview-0.6b

deepinfra/Audio8/Audio8-TTS-Preview-0.6b

DeepinfraN/AN/AN/A

BAAI/bge-base-en-v1.5

deepinfra/BAAI/bge-base-en-v1.5

DeepinfraN/AN/AN/A

BAAI/bge-en-icl

deepinfra/BAAI/bge-en-icl

DeepinfraN/AN/AN/A

BAAI/bge-large-en-v1.5

deepinfra/BAAI/bge-large-en-v1.5

DeepinfraN/AN/AN/A

BAAI/bge-m3

deepinfra/BAAI/bge-m3

DeepinfraN/AN/AN/A

BAAI/bge-m3-multi

deepinfra/BAAI/bge-m3-multi

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-1-dev

deepinfra/black-forest-labs/FLUX-1-dev

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-1-Redux-dev

deepinfra/black-forest-labs/FLUX-1-Redux-dev

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-1-schnell

deepinfra/black-forest-labs/FLUX-1-schnell

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-1.1-pro

deepinfra/black-forest-labs/FLUX-1.1-pro

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-2-dev

deepinfra/black-forest-labs/FLUX-2-dev

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-2-klein-4b

deepinfra/black-forest-labs/FLUX-2-klein-4b

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-2-klein-9b

deepinfra/black-forest-labs/FLUX-2-klein-9b

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-2-max

deepinfra/black-forest-labs/FLUX-2-max

DeepinfraN/AN/AN/A

black-forest-labs/FLUX-2-pro

deepinfra/black-forest-labs/FLUX-2-pro

DeepinfraN/AN/AN/A

black-forest-labs/FLUX.1-Kontext-dev

deepinfra/black-forest-labs/FLUX.1-Kontext-dev

DeepinfraN/AN/AN/A

bosonai/HiggsAudioV2.5

deepinfra/bosonai/HiggsAudioV2.5

DeepinfraN/AN/AN/A

Bria/blur_background

deepinfra/Bria/blur_background

DeepinfraN/AN/AN/A

Bria/Bria-3.2

deepinfra/Bria/Bria-3.2

DeepinfraN/AN/AN/A

Bria/Bria-3.2-vector

deepinfra/Bria/Bria-3.2-vector

DeepinfraN/AN/AN/A

Bria/erase_foreground

deepinfra/Bria/erase_foreground

DeepinfraN/AN/AN/A

Bria/expand

deepinfra/Bria/expand

DeepinfraN/AN/AN/A

Bria/fibo

deepinfra/Bria/fibo

DeepinfraN/AN/AN/A

Bria/fibo_edit

deepinfra/Bria/fibo_edit

DeepinfraN/AN/AN/A

Bria/remove_background

deepinfra/Bria/remove_background

DeepinfraN/AN/AN/A

ByteDance/Seed-1.8

deepinfra/ByteDance/Seed-1.8

DeepinfraN/AN/AN/A

ByteDance/Seed-2.0-code

deepinfra/ByteDance/Seed-2.0-code

DeepinfraN/AN/AN/A

ByteDance/Seed-2.0-mini

deepinfra/ByteDance/Seed-2.0-mini

DeepinfraN/AN/AN/A

ByteDance/Seed-2.0-pro

deepinfra/ByteDance/Seed-2.0-pro

DeepinfraN/AN/AN/A

ByteDance/Seedance-1.5-Pro

deepinfra/ByteDance/Seedance-1.5-Pro

DeepinfraN/AN/AN/A

ByteDance/Seedance-2.0

deepinfra/ByteDance/Seedance-2.0

DeepinfraN/AN/AN/A

ByteDance/Seedream-4

deepinfra/ByteDance/Seedream-4

DeepinfraN/AN/AN/A

DeepSeek V3

deepinfra/deepseek-ai/DeepSeek-V3

Deepinfra66K$0.27$1.10

deepseek-ai/DeepSeek-R1-0528

deepinfra/deepseek-ai/DeepSeek-R1-0528

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V3-0324

deepinfra/deepseek-ai/DeepSeek-V3-0324

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V3.1

deepinfra/deepseek-ai/DeepSeek-V3.1

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V3.2

deepinfra/deepseek-ai/DeepSeek-V3.2

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V4-Flash

deepinfra/deepseek-ai/DeepSeek-V4-Flash

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V4-Flash-0731

deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V4-Pro

deepinfra/deepseek-ai/DeepSeek-V4-Pro

DeepinfraN/AN/AN/A

deepseek-ai/DeepSeek-V4-Pro-0813

deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813

DeepinfraN/AN/AN/A

google/embeddinggemma-300m

deepinfra/google/embeddinggemma-300m

DeepinfraN/AN/AN/A

google/gemini-2.5-flash

deepinfra/google/gemini-2.5-flash

DeepinfraN/AN/AN/A

google/gemini-2.5-pro

deepinfra/google/gemini-2.5-pro

DeepinfraN/AN/AN/A

google/gemini-3-pro-image

deepinfra/google/gemini-3-pro-image

DeepinfraN/AN/AN/A

google/gemini-3.1-flash-lite

deepinfra/google/gemini-3.1-flash-lite

DeepinfraN/AN/AN/A

google/gemini-3.1-pro

deepinfra/google/gemini-3.1-pro

DeepinfraN/AN/AN/A

google/gemini-3.5-flash

deepinfra/google/gemini-3.5-flash

DeepinfraN/AN/AN/A

google/gemini-3.7-flash

deepinfra/google/gemini-3.7-flash

DeepinfraN/AN/AN/A

google/gemma-3-12b-it

deepinfra/google/gemma-3-12b-it

DeepinfraN/AN/AN/A

google/gemma-3-27b-it

deepinfra/google/gemma-3-27b-it

DeepinfraN/AN/AN/A

google/gemma-3-4b-it

deepinfra/google/gemma-3-4b-it

DeepinfraN/AN/AN/A

google/gemma-4-26B-A4B-it

deepinfra/google/gemma-4-26B-A4B-it

DeepinfraN/AN/AN/A

google/gemma-4-31B-it

deepinfra/google/gemma-4-31B-it

DeepinfraN/AN/AN/A

google/gemma-4-31B-it-turbo

deepinfra/google/gemma-4-31B-it-turbo

DeepinfraN/AN/AN/A

google/gemma-4-31B-it-Ultra

deepinfra/google/gemma-4-31B-it-Ultra

DeepinfraN/AN/AN/A

google/gemma-4-E4B-it

deepinfra/google/gemma-4-E4B-it

DeepinfraN/AN/AN/A

google/nano-banana-2

deepinfra/google/nano-banana-2

DeepinfraN/AN/AN/A

google/nano-banana-2-lite

deepinfra/google/nano-banana-2-lite

DeepinfraN/AN/AN/A

google/nano-banana-pro

deepinfra/google/nano-banana-pro

DeepinfraN/AN/AN/A

google/veo-3.1

deepinfra/google/veo-3.1

DeepinfraN/AN/AN/A

google/veo-3.1-fast

deepinfra/google/veo-3.1-fast

DeepinfraN/AN/AN/A

Gryphe/MythoMax-L2-13b

deepinfra/Gryphe/MythoMax-L2-13b

DeepinfraN/AN/AN/A

hexgrad/Kokoro-82M

deepinfra/hexgrad/Kokoro-82M

DeepinfraN/AN/AN/A

ibm-granite/granite-4.2-30b

deepinfra/ibm-granite/granite-4.2-30b

DeepinfraN/AN/AN/A

ibm-granite/granite-4.2-3b

deepinfra/ibm-granite/granite-4.2-3b

DeepinfraN/AN/AN/A

ibm-granite/granite-4.2-8b

deepinfra/ibm-granite/granite-4.2-8b

DeepinfraN/AN/AN/A

inclusionAI/Ling-3.0-flash

deepinfra/inclusionAI/Ling-3.0-flash

DeepinfraN/AN/AN/A

intfloat/e5-base-v2

deepinfra/intfloat/e5-base-v2

DeepinfraN/AN/AN/A

intfloat/e5-large-v2

deepinfra/intfloat/e5-large-v2

DeepinfraN/AN/AN/A

intfloat/multilingual-e5-large

deepinfra/intfloat/multilingual-e5-large

DeepinfraN/AN/AN/A

intfloat/multilingual-e5-large-instruct

deepinfra/intfloat/multilingual-e5-large-instruct

DeepinfraN/AN/AN/A

inworld-ai/realtime-tts-1.5-max

deepinfra/inworld-ai/realtime-tts-1.5-max

DeepinfraN/AN/AN/A

inworld-ai/realtime-tts-1.5-mini

deepinfra/inworld-ai/realtime-tts-1.5-mini

DeepinfraN/AN/AN/A

inworld-ai/realtime-tts-2

deepinfra/inworld-ai/realtime-tts-2

DeepinfraN/AN/AN/A

Llama 3.1 70B Instruct

deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct

Deepinfra131K$0.35$0.40

Llama 3.1 8B Instruct

deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct

Deepinfra131K$0.06$0.06

Llama 3.3 70B Instruct

deepinfra/meta-llama/Llama-3.3-70B-Instruct

Deepinfra131K$0.35$0.40

meta-llama/Llama-3.3-70B-Instruct-Turbo

deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo

DeepinfraN/AN/AN/A

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

DeepinfraN/AN/AN/A

meta-llama/Llama-4-Scout-17B-16E-Instruct

deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct

DeepinfraN/AN/AN/A

meta-llama/Llama-Guard-4-12B

deepinfra/meta-llama/Llama-Guard-4-12B

DeepinfraN/AN/AN/A

meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo

deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo

DeepinfraN/AN/AN/A

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

DeepinfraN/AN/AN/A

meta-models/Muse-Glimmer-30B

deepinfra/meta-models/Muse-Glimmer-30B

DeepinfraN/AN/AN/A

microsoft/phi-4

deepinfra/microsoft/phi-4

DeepinfraN/AN/AN/A

MiniMaxAI/MiniMax-M2.7

deepinfra/MiniMaxAI/MiniMax-M2.7

DeepinfraN/AN/AN/A

MiniMaxAI/MiniMax-M2.7-Turbo

deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo

DeepinfraN/AN/AN/A

MiniMaxAI/MiniMax-M3

deepinfra/MiniMaxAI/MiniMax-M3

DeepinfraN/AN/AN/A

mistralai/Mistral-Nemo-Instruct-2407

deepinfra/mistralai/Mistral-Nemo-Instruct-2407

DeepinfraN/AN/AN/A

mistralai/Mistral-Small-24B-Instruct-2501

deepinfra/mistralai/Mistral-Small-24B-Instruct-2501

DeepinfraN/AN/AN/A

mistralai/Mistral-Small-3.2-24B-Instruct-2506

deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506

DeepinfraN/AN/AN/A

mistralai/Voxtral-Mini-3B-2507

deepinfra/mistralai/Voxtral-Mini-3B-2507

DeepinfraN/AN/AN/A

mistralai/Voxtral-Small-24B-2507

deepinfra/mistralai/Voxtral-Small-24B-2507

DeepinfraN/AN/AN/A

moonshotai/Kimi-K2.6

deepinfra/moonshotai/Kimi-K2.6

DeepinfraN/AN/AN/A

moonshotai/Kimi-K2.7-Code

deepinfra/moonshotai/Kimi-K2.7-Code

DeepinfraN/AN/AN/A

moonshotai/Kimi-K3

deepinfra/moonshotai/Kimi-K3

DeepinfraN/AN/AN/A

NousResearch/Hermes-3-Llama-3.1-405B

deepinfra/NousResearch/Hermes-3-Llama-3.1-405B

DeepinfraN/AN/AN/A

NousResearch/Hermes-3-Llama-3.1-70B

deepinfra/NousResearch/Hermes-3-Llama-3.1-70B

DeepinfraN/AN/AN/A

nvidia/Cosmos3-Nano

deepinfra/nvidia/Cosmos3-Nano

DeepinfraN/AN/AN/A

nvidia/Cosmos3-Super

deepinfra/nvidia/Cosmos3-Super

DeepinfraN/AN/AN/A

nvidia/llama-nemotron-embed-vl-1b-v2

deepinfra/nvidia/llama-nemotron-embed-vl-1b-v2

DeepinfraN/AN/AN/A

nvidia/Nemotron-3-Nano-30B-A3B

deepinfra/nvidia/Nemotron-3-Nano-30B-A3B

DeepinfraN/AN/AN/A

nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b

deepinfra/nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b

DeepinfraN/AN/AN/A

nvidia/Nemotron-Content-Safety-3.5

deepinfra/nvidia/Nemotron-Content-Safety-3.5

DeepinfraN/AN/AN/A

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

DeepinfraN/AN/AN/A

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B

DeepinfraN/AN/AN/A

nvidia/NVIDIA-Nemotron-3.5-Lightning

deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning

DeepinfraN/AN/AN/A

openai/gpt-oss-120b

deepinfra/openai/gpt-oss-120b

DeepinfraN/AN/AN/A

openai/gpt-oss-120b-Turbo

deepinfra/openai/gpt-oss-120b-Turbo

DeepinfraN/AN/AN/A

openai/gpt-oss-120b-Ultra

deepinfra/openai/gpt-oss-120b-Ultra

DeepinfraN/AN/AN/A

openai/gpt-oss-20b

deepinfra/openai/gpt-oss-20b

DeepinfraN/AN/AN/A

openai/whisper-large-v3

deepinfra/openai/whisper-large-v3

DeepinfraN/AN/AN/A

openai/whisper-large-v3-turbo

deepinfra/openai/whisper-large-v3-turbo

DeepinfraN/AN/AN/A

Pixverse/Pixverse-6-T2V

deepinfra/Pixverse/Pixverse-6-T2V

DeepinfraN/AN/AN/A

Pixverse/Pixverse-T2V

deepinfra/Pixverse/Pixverse-T2V

DeepinfraN/AN/AN/A

Pixverse/Pixverse-T2V-HD

deepinfra/Pixverse/Pixverse-T2V-HD

DeepinfraN/AN/AN/A

PrunaAI/p-image

deepinfra/PrunaAI/p-image

DeepinfraN/AN/AN/A

PrunaAI/p-video

deepinfra/PrunaAI/p-video

DeepinfraN/AN/AN/A

Qwen 2.5 72B Instruct

deepinfra/Qwen/Qwen2.5-72B-Instruct

Deepinfra131K$0.35$0.40

Qwen/Qwen-Image-Edit

deepinfra/Qwen/Qwen-Image-Edit

DeepinfraN/AN/AN/A

Qwen/Qwen-Image-Max

deepinfra/Qwen/Qwen-Image-Max

DeepinfraN/AN/AN/A

Qwen/Qwen3-14B

deepinfra/Qwen/Qwen3-14B

DeepinfraN/AN/AN/A

Qwen/Qwen3-235B-A22B-Instruct-2507

deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507

DeepinfraN/AN/AN/A

Qwen/Qwen3-30B-A3B

deepinfra/Qwen/Qwen3-30B-A3B

DeepinfraN/AN/AN/A

Qwen/Qwen3-32B

deepinfra/Qwen/Qwen3-32B

DeepinfraN/AN/AN/A

Qwen/Qwen3-ASR-0.6B

deepinfra/Qwen/Qwen3-ASR-0.6B

DeepinfraN/AN/AN/A

Qwen/Qwen3-ASR-1.7B

deepinfra/Qwen/Qwen3-ASR-1.7B

DeepinfraN/AN/AN/A

Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo

deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo

DeepinfraN/AN/AN/A

Qwen/Qwen3-Embedding-0.6B

deepinfra/Qwen/Qwen3-Embedding-0.6B

DeepinfraN/AN/AN/A

Qwen/Qwen3-Embedding-4B

deepinfra/Qwen/Qwen3-Embedding-4B

DeepinfraN/AN/AN/A

Qwen/Qwen3-Embedding-8B

deepinfra/Qwen/Qwen3-Embedding-8B

DeepinfraN/AN/AN/A

Qwen/Qwen3-Max

deepinfra/Qwen/Qwen3-Max

DeepinfraN/AN/AN/A

Qwen/Qwen3-Max-Thinking

deepinfra/Qwen/Qwen3-Max-Thinking

DeepinfraN/AN/AN/A

Qwen/Qwen3-Next-80B-A3B-Instruct

deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct

DeepinfraN/AN/AN/A

Qwen/Qwen3-TTS

deepinfra/Qwen/Qwen3-TTS

DeepinfraN/AN/AN/A

Qwen/Qwen3-TTS-VoiceDesign

deepinfra/Qwen/Qwen3-TTS-VoiceDesign

DeepinfraN/AN/AN/A

Qwen/Qwen3-VL-235B-A22B-Instruct

deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct

DeepinfraN/AN/AN/A

Qwen/Qwen3-VL-30B-A3B-Instruct

deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct

DeepinfraN/AN/AN/A

Qwen/Qwen3.5-122B-A10B

deepinfra/Qwen/Qwen3.5-122B-A10B

DeepinfraN/AN/AN/A

Qwen/Qwen3.5-27B

deepinfra/Qwen/Qwen3.5-27B

DeepinfraN/AN/AN/A

Qwen/Qwen3.5-35B-A3B

deepinfra/Qwen/Qwen3.5-35B-A3B

DeepinfraN/AN/AN/A

Qwen/Qwen3.5-397B-A17B

deepinfra/Qwen/Qwen3.5-397B-A17B

DeepinfraN/AN/AN/A

Qwen/Qwen3.5-9B

deepinfra/Qwen/Qwen3.5-9B

DeepinfraN/AN/AN/A

Qwen/Qwen3.6-27B

deepinfra/Qwen/Qwen3.6-27B

DeepinfraN/AN/AN/A

Qwen/Qwen3.6-35B-A3B

deepinfra/Qwen/Qwen3.6-35B-A3B

DeepinfraN/AN/AN/A

Qwen/Qwen3.7-Max

deepinfra/Qwen/Qwen3.7-Max

DeepinfraN/AN/AN/A

Qwen/Qwen3.8-2.4T-A95B

deepinfra/Qwen/Qwen3.8-2.4T-A95B

DeepinfraN/AN/AN/A

Qwen/Qwen3.8-27B

deepinfra/Qwen/Qwen3.8-27B

DeepinfraN/AN/AN/A

Qwen/Qwen3.8-Max

deepinfra/Qwen/Qwen3.8-Max

DeepinfraN/AN/AN/A

ResembleAI/chatterbox-multilingual

deepinfra/ResembleAI/chatterbox-multilingual

DeepinfraN/AN/AN/A

ResembleAI/chatterbox-turbo

deepinfra/ResembleAI/chatterbox-turbo

DeepinfraN/AN/AN/A

Sao10K/L3-8B-Lunaris-v1-Turbo

deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo

DeepinfraN/AN/AN/A

Sao10K/L3.1-70B-Euryale-v2.2

deepinfra/Sao10K/L3.1-70B-Euryale-v2.2

DeepinfraN/AN/AN/A

sentence-transformers/all-MiniLM-L12-v2

deepinfra/sentence-transformers/all-MiniLM-L12-v2

DeepinfraN/AN/AN/A

sentence-transformers/all-MiniLM-L6-v2

deepinfra/sentence-transformers/all-MiniLM-L6-v2

DeepinfraN/AN/AN/A

sentence-transformers/all-mpnet-base-v2

deepinfra/sentence-transformers/all-mpnet-base-v2

DeepinfraN/AN/AN/A

sentence-transformers/clip-ViT-B-32

deepinfra/sentence-transformers/clip-ViT-B-32

DeepinfraN/AN/AN/A

sentence-transformers/clip-ViT-B-32-multilingual-v1

deepinfra/sentence-transformers/clip-ViT-B-32-multilingual-v1

DeepinfraN/AN/AN/A

sentence-transformers/multi-qa-mpnet-base-dot-v1

deepinfra/sentence-transformers/multi-qa-mpnet-base-dot-v1

DeepinfraN/AN/AN/A

sentence-transformers/paraphrase-MiniLM-L6-v2

deepinfra/sentence-transformers/paraphrase-MiniLM-L6-v2

DeepinfraN/AN/AN/A

sesame/csm-1b

deepinfra/sesame/csm-1b

DeepinfraN/AN/AN/A

shibing624/text2vec-base-chinese

deepinfra/shibing624/text2vec-base-chinese

DeepinfraN/AN/AN/A

stabilityai/sdxl-turbo

deepinfra/stabilityai/sdxl-turbo

DeepinfraN/AN/AN/A

stepfun-ai/Step-3.7-Flash

deepinfra/stepfun-ai/Step-3.7-Flash

DeepinfraN/AN/AN/A

tencent/Hy3

deepinfra/tencent/Hy3

DeepinfraN/AN/AN/A

thenlper/gte-base

deepinfra/thenlper/gte-base

DeepinfraN/AN/AN/A

thenlper/gte-large

deepinfra/thenlper/gte-large

DeepinfraN/AN/AN/A

thinkingmachines/Inkling

deepinfra/thinkingmachines/Inkling

DeepinfraN/AN/AN/A

thinkingmachines/Inkling-Small

deepinfra/thinkingmachines/Inkling-Small

DeepinfraN/AN/AN/A

Wan-AI/Wan2.2-T2V-A14B

deepinfra/Wan-AI/Wan2.2-T2V-A14B

DeepinfraN/AN/AN/A

Wan-AI/Wan2.6-T2I

deepinfra/Wan-AI/Wan2.6-T2I

DeepinfraN/AN/AN/A

Wan-AI/Wan2.6-T2V

deepinfra/Wan-AI/Wan2.6-T2V

DeepinfraN/AN/AN/A

XiaomiMiMo/MiMo-V2.5

deepinfra/XiaomiMiMo/MiMo-V2.5

DeepinfraN/AN/AN/A

XiaomiMiMo/MiMo-V2.5-Pro

deepinfra/XiaomiMiMo/MiMo-V2.5-Pro

DeepinfraN/AN/AN/A

XiaomiMiMo/MiMo-V2.5-tts

deepinfra/XiaomiMiMo/MiMo-V2.5-tts

DeepinfraN/AN/AN/A

XiaomiMiMo/MiMo-V2.5-tts-voicedesign

deepinfra/XiaomiMiMo/MiMo-V2.5-tts-voicedesign

DeepinfraN/AN/AN/A

zai-org/GLM-4.6

deepinfra/zai-org/GLM-4.6

DeepinfraN/AN/AN/A

zai-org/GLM-4.7

deepinfra/zai-org/GLM-4.7

DeepinfraN/AN/AN/A

zai-org/GLM-4.7-Flash

deepinfra/zai-org/GLM-4.7-Flash

DeepinfraN/AN/AN/A

zai-org/GLM-5

deepinfra/zai-org/GLM-5

DeepinfraN/AN/AN/A

zai-org/GLM-5.1

deepinfra/zai-org/GLM-5.1

DeepinfraN/AN/AN/A

zai-org/GLM-5.2

deepinfra/zai-org/GLM-5.2

DeepinfraN/AN/AN/A

zai-org/GLM-5.3

deepinfra/zai-org/GLM-5.3

DeepinfraN/AN/AN/A

zai-org/GLM-5.3-Flash

deepinfra/zai-org/GLM-5.3-Flash

DeepinfraN/AN/AN/A

DeepSeek V4 Flash

deepseek/deepseek-v4-flash

DeepSeek1.0M$0.44$1.32

DeepSeek V4 Pro

deepseek/deepseek-v4-pro

DeepSeek1.0M$1.32$3.96

DeepSeek V4 Flash

fireworks/accounts/fireworks/models/deepseek-v4-flash-0731

Fireworks1.0M$0.22$0.66

DeepSeek V4 Pro

fireworks/accounts/fireworks/models/deepseek-v4-pro-0813

Fireworks1.0M$1.32$3.96

GLM-5.3

fireworks/accounts/fireworks/models/glm-5p3

Fireworks1.0M$1.40$4.40

GPT-OSS 120B

fireworks/accounts/fireworks/models/gpt-oss-120b

Fireworks131K$0.15$0.60

Kimi K3

fireworks/accounts/fireworks/models/kimi-k3

Fireworks1.0M$3.00$15.00

MiniMax M3

fireworks/accounts/fireworks/models/minimax-m3

Fireworks1.0M$0.30$1.20

Nemotron 3 Ultra

fireworks/accounts/fireworks/models/nemotron-3-ultra-nvfp4

Fireworks131K$0.60$2.40

Qwen3.8 Max

fireworks/accounts/fireworks/models/qwen3p8-max

Fireworks1.0M$2.00$6.00

DeepSeek V3

friendli/deepseek-v3

Friendli66K$0.35$0.90

Llama 3.1 70B Instruct

friendli/meta-llama-3.1-70b-instruct

Friendli131K$0.50$0.70

Llama 3.1 8B Instruct

friendli/meta-llama-3.1-8b-instruct

Friendli131K$0.10$0.10

Gemini 2.5 Flash

google/gemini-2.5-flash

Google1.0M$0.30$2.50

Gemini 2.5 Flash-Lite

google/gemini-2.5-flash-lite

Google1.0M$0.10$0.40

Gemini 2.5 Pro

google/gemini-2.5-pro

Google1.0M$1.25$10.00

Gemini 3.5 Flash

google/gemini-3.5-flash

Google1.0M$1.50$9.00

Gemini 3.8 Flash

google/gemini-3.8-flash

Google1.0M$0.75$3.75

GPT-OSS 120B

groq/gpt-oss-120b

Groq131K$0.15$0.60

GPT-OSS 20B

groq/gpt-oss-20b

Groq131K$0.07$0.30

Qwen3.6 27B

groq/qwen3.6-27b

Groq131K$0.60$3.00

Qwen3.8 27B

groq/qwen3.8-27b

Groq131K$0.80$4.00

Whisper Large V3 (Groq)

groq/whisper-large-v3

GroqN/A<$0.01N/A

MiniMax M2.5

minimax/minimax-m2.5

Minimax205K$0.30$1.20

MiniMax M2.7

minimax/minimax-m2.7

Minimax205K$0.30$1.20

MiniMax M2.7 Highspeed

minimax/minimax-m2.7-highspeed

Minimax205K$0.60$2.40

MiniMax M3

minimax/minimax-m3

Minimax1.0M$0.30$1.20

Codestral

mistral/codestral-latest

Mistral128K$0.30$0.90

Ministral 14B

mistral/ministral-14b

Mistral128K$0.20$0.20

Ministral 3B

mistral/ministral-3b

Mistral128K$0.10$0.10

Ministral 8B

mistral/ministral-8b

Mistral128K$0.15$0.15

Mistral Large

mistral/mistral-large-latest

Mistral256K$0.50$1.50

Mistral Medium 3.5

mistral/mistral-medium-latest

Mistral128K$1.50$7.50

Mistral Small

mistral/mistral-small-latest

Mistral32K$0.15$0.60

Kimi K2.6

moonshot/kimi-k2.6

Moonshot262K$0.95$4.00

Kimi K2.7 Code

moonshot/kimi-k2.7-code

Moonshot262K$0.95$4.00

Kimi K3

moonshot/kimi-k3

Moonshot1.0M$3.00$15.00

DeepSeek V3

nebius/deepseek-ai/DeepSeek-V3

Nebius66K$0.30$0.90

Llama 3.1 70B Instruct

nebius/meta-llama/Meta-Llama-3.1-70B-Instruct

Nebius131K$0.35$0.40

Llama 3.1 8B Instruct

nebius/meta-llama/Meta-Llama-3.1-8B-Instruct

Nebius131K$0.06$0.06

Qwen 2.5 72B Instruct

nebius/Qwen/Qwen2.5-72B-Instruct

Nebius131K$0.35$0.40

ai_infer_test_1

novita/ai_infer_test_1

NovitaN/AN/AN/A

ai_infer_test_2

novita/ai_infer_test_2

NovitaN/AN/AN/A

ai_infer_test_3

novita/ai_infer_test_3

NovitaN/AN/AN/A

baichuan/baichuan-m2-32b

novita/baichuan/baichuan-m2-32b

NovitaN/AN/AN/A

baidu/cobuddy

novita/baidu/cobuddy

NovitaN/AN/AN/A

baidu/ernie-4.5-21B-a3b

novita/baidu/ernie-4.5-21B-a3b

NovitaN/AN/AN/A

baidu/ernie-4.5-21B-a3b-thinking

novita/baidu/ernie-4.5-21B-a3b-thinking

NovitaN/AN/AN/A

baidu/ernie-4.5-300b-a47b-paddle

novita/baidu/ernie-4.5-300b-a47b-paddle

NovitaN/AN/AN/A

baidu/ernie-4.5-vl-28b-a3b

novita/baidu/ernie-4.5-vl-28b-a3b

NovitaN/AN/AN/A

baidu/ernie-4.5-vl-28b-a3b-thinking

novita/baidu/ernie-4.5-vl-28b-a3b-thinking

NovitaN/AN/AN/A

baidu/ernie-4.5-vl-424b-a47b

novita/baidu/ernie-4.5-vl-424b-a47b

NovitaN/AN/AN/A

bunny

novita/bunny

NovitaN/AN/AN/A

DeepSeek R1

novita/deepseek/deepseek-r1

Novita66K$0.55$2.19

DeepSeek V3

novita/deepseek/deepseek-v3

Novita66K$0.30$0.88

deepseek/deepseek_v3

novita/deepseek/deepseek_v3

NovitaN/AN/AN/A

deepseek/deepseek-ocr

novita/deepseek/deepseek-ocr

NovitaN/AN/AN/A

deepseek/deepseek-ocr-2

novita/deepseek/deepseek-ocr-2

NovitaN/AN/AN/A

deepseek/deepseek-prover-v2-671b

novita/deepseek/deepseek-prover-v2-671b

NovitaN/AN/AN/A

deepseek/deepseek-r1-0528

novita/deepseek/deepseek-r1-0528

NovitaN/AN/AN/A

deepseek/deepseek-r1-0528-qwen3-8b

novita/deepseek/deepseek-r1-0528-qwen3-8b

NovitaN/AN/AN/A

deepseek/deepseek-r1-distill-llama-70b

novita/deepseek/deepseek-r1-distill-llama-70b

NovitaN/AN/AN/A

deepseek/deepseek-r1-distill-qwen-14b

novita/deepseek/deepseek-r1-distill-qwen-14b

NovitaN/AN/AN/A

deepseek/deepseek-r1-distill-qwen-32b

novita/deepseek/deepseek-r1-distill-qwen-32b

NovitaN/AN/AN/A

deepseek/deepseek-r1-turbo

novita/deepseek/deepseek-r1-turbo

NovitaN/AN/AN/A

deepseek/deepseek-r1/community

novita/deepseek/deepseek-r1/community

NovitaN/AN/AN/A

deepseek/deepseek-v3-0324

novita/deepseek/deepseek-v3-0324

NovitaN/AN/AN/A

deepseek/deepseek-v3-turbo

novita/deepseek/deepseek-v3-turbo

NovitaN/AN/AN/A

deepseek/deepseek-v3.1

novita/deepseek/deepseek-v3.1

NovitaN/AN/AN/A

deepseek/deepseek-v3.1-terminus

novita/deepseek/deepseek-v3.1-terminus

NovitaN/AN/AN/A

deepseek/deepseek-v3.2

novita/deepseek/deepseek-v3.2

NovitaN/AN/AN/A

deepseek/deepseek-v3.2-exp

novita/deepseek/deepseek-v3.2-exp

NovitaN/AN/AN/A

deepseek/deepseek-v3/community

novita/deepseek/deepseek-v3/community

NovitaN/AN/AN/A

deepseek/deepseek-v4-flash

novita/deepseek/deepseek-v4-flash

NovitaN/AN/AN/A

deepseek/deepseek-v4-flash-0731

novita/deepseek/deepseek-v4-flash-0731

NovitaN/AN/AN/A

deepseek/deepseek-v4-flash-vision-exp

novita/deepseek/deepseek-v4-flash-vision-exp

NovitaN/AN/AN/A

deepseek/deepseek-v4-pro

novita/deepseek/deepseek-v4-pro

NovitaN/AN/AN/A

deepseek/deepseek-v4-pro-0813

novita/deepseek/deepseek-v4-pro-0813

NovitaN/AN/AN/A

dev/glm46

novita/dev/glm46

NovitaN/AN/AN/A

elephant

novita/elephant

NovitaN/AN/AN/A

google/gemma-3-12b-it

novita/google/gemma-3-12b-it

NovitaN/AN/AN/A

google/gemma-3-27b-it

novita/google/gemma-3-27b-it

NovitaN/AN/AN/A

google/gemma-4-26b-a4b-it

novita/google/gemma-4-26b-a4b-it

NovitaN/AN/AN/A

google/gemma-4-31b-it

novita/google/gemma-4-31b-it

NovitaN/AN/AN/A

gryphe/mythomax-l2-13b

novita/gryphe/mythomax-l2-13b

NovitaN/AN/AN/A

gt-4p

novita/gt-4p

NovitaN/AN/AN/A

inclusionai/ling-2.6-1t

novita/inclusionai/ling-2.6-1t

NovitaN/AN/AN/A

inclusionai/ling-2.6-flash

novita/inclusionai/ling-2.6-flash

NovitaN/AN/AN/A

inclusionai/ling-3.0-flash

novita/inclusionai/ling-3.0-flash

NovitaN/AN/AN/A

inclusionai/ling-3.0-flash-fast

novita/inclusionai/ling-3.0-flash-fast

NovitaN/AN/AN/A

inclusionai/ling-3.0-flash-fin

novita/inclusionai/ling-3.0-flash-fin

NovitaN/AN/AN/A

inclusionai/ling-3.0-flash-sante

novita/inclusionai/ling-3.0-flash-sante

NovitaN/AN/AN/A

inclusionai/ling-3.0-flash-vl

novita/inclusionai/ling-3.0-flash-vl

NovitaN/AN/AN/A

inclusionai/ling-3.0-tiny

novita/inclusionai/ling-3.0-tiny

NovitaN/AN/AN/A

inclusionai/ring-2.6-1t

novita/inclusionai/ring-2.6-1t

NovitaN/AN/AN/A

kwaipilot/kat-coder-pro

novita/kwaipilot/kat-coder-pro

NovitaN/AN/AN/A

Llama 3.1 70B Instruct

novita/meta-llama/llama-3.1-70b-instruct

Novita131K$0.35$0.40

Llama 3.1 8B Instruct

novita/meta-llama/llama-3.1-8b-instruct

Novita131K$0.06$0.06

meta-llama/llama-3-70b-instruct

novita/meta-llama/llama-3-70b-instruct

NovitaN/AN/AN/A

meta-llama/llama-3-8b-instruct

novita/meta-llama/llama-3-8b-instruct

NovitaN/AN/AN/A

meta-llama/llama-3.2-1b-instruct

novita/meta-llama/llama-3.2-1b-instruct

NovitaN/AN/AN/A

meta-llama/llama-3.2-3b-instruct

novita/meta-llama/llama-3.2-3b-instruct

NovitaN/AN/AN/A

meta-llama/llama-3.3-70b-instruct

novita/meta-llama/llama-3.3-70b-instruct

NovitaN/AN/AN/A

meta-llama/llama-4-maverick-17b-128e-instruct-fp8

novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8

NovitaN/AN/AN/A

meta-llama/llama-4-scout-17b-16e-instruct

novita/meta-llama/llama-4-scout-17b-16e-instruct

NovitaN/AN/AN/A

microsoft/wizardlm-2-8x22b

novita/microsoft/wizardlm-2-8x22b

NovitaN/AN/AN/A

mindai/macaron-v1-tall

novita/mindai/macaron-v1-tall

NovitaN/AN/AN/A

mindai/macaron-v1-venti

novita/mindai/macaron-v1-venti

NovitaN/AN/AN/A

minimax/minimax-m2

novita/minimax/minimax-m2

NovitaN/AN/AN/A

minimax/minimax-m2.1

novita/minimax/minimax-m2.1

NovitaN/AN/AN/A

minimax/minimax-m2.5

novita/minimax/minimax-m2.5

NovitaN/AN/AN/A

minimax/minimax-m2.5-highspeed

novita/minimax/minimax-m2.5-highspeed

NovitaN/AN/AN/A

minimax/minimax-m2.7

novita/minimax/minimax-m2.7

NovitaN/AN/AN/A

minimax/minimax-m2.7-highspeed

novita/minimax/minimax-m2.7-highspeed

NovitaN/AN/AN/A

minimax/minimax-m3

novita/minimax/minimax-m3

NovitaN/AN/AN/A

minimaxai/minimax-m1-80k

novita/minimaxai/minimax-m1-80k

NovitaN/AN/AN/A

mistralai/mistral-nemo

novita/mistralai/mistral-nemo

NovitaN/AN/AN/A

moonshotai/kimi-k2-0905

novita/moonshotai/kimi-k2-0905

NovitaN/AN/AN/A

moonshotai/kimi-k2-instruct

novita/moonshotai/kimi-k2-instruct

NovitaN/AN/AN/A

moonshotai/kimi-k2-thinking

novita/moonshotai/kimi-k2-thinking

NovitaN/AN/AN/A

moonshotai/kimi-k2.5

novita/moonshotai/kimi-k2.5

NovitaN/AN/AN/A

moonshotai/kimi-k2.6

novita/moonshotai/kimi-k2.6

NovitaN/AN/AN/A

moonshotai/kimi-k2.7-code

novita/moonshotai/kimi-k2.7-code

NovitaN/AN/AN/A

moonshotai/kimi-k3

novita/moonshotai/kimi-k3

NovitaN/AN/AN/A

nex-agi/nex-n2-pro

novita/nex-agi/nex-n2-pro

NovitaN/AN/AN/A

nousresearch/hermes-2-pro-llama-3-8b

novita/nousresearch/hermes-2-pro-llama-3-8b

NovitaN/AN/AN/A

nousresearch/nous-hermes-llama2-13b

novita/nousresearch/nous-hermes-llama2-13b

NovitaN/AN/AN/A

nvidia/nemotron-3-nano-30b-a3b

novita/nvidia/nemotron-3-nano-30b-a3b

NovitaN/AN/AN/A

openai/gpt-oss-120b

novita/openai/gpt-oss-120b

NovitaN/AN/AN/A

openai/gpt-oss-20b

novita/openai/gpt-oss-20b

NovitaN/AN/AN/A

openchat/openchat-7b

novita/openchat/openchat-7b

NovitaN/AN/AN/A

paddlepaddle/paddleocr-vl

novita/paddlepaddle/paddleocr-vl

NovitaN/AN/AN/A

qwen/qwen-2-7b-instruct

novita/qwen/qwen-2-7b-instruct

NovitaN/AN/AN/A

qwen/qwen-2-vl-72b-instruct

novita/qwen/qwen-2-vl-72b-instruct

NovitaN/AN/AN/A

qwen/qwen-2.5-72b-instruct

novita/qwen/qwen-2.5-72b-instruct

NovitaN/AN/AN/A

qwen/qwen-mt-plus

novita/qwen/qwen-mt-plus

NovitaN/AN/AN/A

qwen/qwen2.5-7b-instruct

novita/qwen/qwen2.5-7b-instruct

NovitaN/AN/AN/A

qwen/qwen2.5-vl-72b-instruct

novita/qwen/qwen2.5-vl-72b-instruct

NovitaN/AN/AN/A

qwen/qwen3-235b-a22b-fp8

novita/qwen/qwen3-235b-a22b-fp8

NovitaN/AN/AN/A

qwen/qwen3-235b-a22b-instruct-2507

novita/qwen/qwen3-235b-a22b-instruct-2507

NovitaN/AN/AN/A

qwen/qwen3-235b-a22b-thinking-2507

novita/qwen/qwen3-235b-a22b-thinking-2507

NovitaN/AN/AN/A

qwen/qwen3-30b-a3b-fp8

novita/qwen/qwen3-30b-a3b-fp8

NovitaN/AN/AN/A

qwen/qwen3-32b-fp8

novita/qwen/qwen3-32b-fp8

NovitaN/AN/AN/A

qwen/qwen3-4b-fp8

novita/qwen/qwen3-4b-fp8

NovitaN/AN/AN/A

qwen/qwen3-8b-fp8

novita/qwen/qwen3-8b-fp8

NovitaN/AN/AN/A

qwen/qwen3-coder-30b-a3b-instruct

novita/qwen/qwen3-coder-30b-a3b-instruct

NovitaN/AN/AN/A

qwen/qwen3-coder-480b-a35b-instruct

novita/qwen/qwen3-coder-480b-a35b-instruct

NovitaN/AN/AN/A

qwen/qwen3-coder-next

novita/qwen/qwen3-coder-next

NovitaN/AN/AN/A

qwen/qwen3-max

novita/qwen/qwen3-max

NovitaN/AN/AN/A

qwen/qwen3-next-80b-a3b-instruct

novita/qwen/qwen3-next-80b-a3b-instruct

NovitaN/AN/AN/A

qwen/qwen3-next-80b-a3b-thinking

novita/qwen/qwen3-next-80b-a3b-thinking

NovitaN/AN/AN/A

qwen/qwen3-omni-30b-a3b-instruct

novita/qwen/qwen3-omni-30b-a3b-instruct

NovitaN/AN/AN/A

qwen/qwen3-omni-30b-a3b-thinking

novita/qwen/qwen3-omni-30b-a3b-thinking

NovitaN/AN/AN/A

qwen/qwen3-vl-235b-a22b-instruct

novita/qwen/qwen3-vl-235b-a22b-instruct

NovitaN/AN/AN/A

qwen/qwen3-vl-235b-a22b-thinking

novita/qwen/qwen3-vl-235b-a22b-thinking

NovitaN/AN/AN/A

qwen/qwen3-vl-30b-a3b-instruct

novita/qwen/qwen3-vl-30b-a3b-instruct

NovitaN/AN/AN/A

qwen/qwen3-vl-30b-a3b-thinking

novita/qwen/qwen3-vl-30b-a3b-thinking

NovitaN/AN/AN/A

qwen/qwen3-vl-8b-instruct

novita/qwen/qwen3-vl-8b-instruct

NovitaN/AN/AN/A

qwen/qwen3.5-122b-a10b

novita/qwen/qwen3.5-122b-a10b

NovitaN/AN/AN/A

qwen/qwen3.5-27b

novita/qwen/qwen3.5-27b

NovitaN/AN/AN/A

qwen/qwen3.5-35b-a3b

novita/qwen/qwen3.5-35b-a3b

NovitaN/AN/AN/A

qwen/qwen3.5-397b-a17b

novita/qwen/qwen3.5-397b-a17b

NovitaN/AN/AN/A

qwen/qwen3.5-plus

novita/qwen/qwen3.5-plus

NovitaN/AN/AN/A

qwen/qwen3.6-27b

novita/qwen/qwen3.6-27b

NovitaN/AN/AN/A

qwen/qwen3.6-35b-a3b

novita/qwen/qwen3.6-35b-a3b

NovitaN/AN/AN/A

qwen/qwen3.6-plus

novita/qwen/qwen3.6-plus

NovitaN/AN/AN/A

qwen/qwen3.7-max

novita/qwen/qwen3.7-max

NovitaN/AN/AN/A

qwen/qwen3.8-2.4t-a95b

novita/qwen/qwen3.8-2.4t-a95b

NovitaN/AN/AN/A

qwen/qwen3.8-27b

novita/qwen/qwen3.8-27b

NovitaN/AN/AN/A

qwen/qwen3.8-flash

novita/qwen/qwen3.8-flash

NovitaN/AN/AN/A

qwen/qwen3.8-max

novita/qwen/qwen3.8-max

NovitaN/AN/AN/A

sao10k/l3-70b-euryale-v2.1

novita/sao10k/l3-70b-euryale-v2.1

NovitaN/AN/AN/A

sao10k/l3-8b-lunaris

novita/sao10k/l3-8b-lunaris

NovitaN/AN/AN/A

Sao10K/L3-8B-Stheno-v3.2

novita/Sao10K/L3-8B-Stheno-v3.2

NovitaN/AN/AN/A

sao10k/l31-70b-euryale-v2.2

novita/sao10k/l31-70b-euryale-v2.2

NovitaN/AN/AN/A

stepfun/step-3.7-flash

novita/stepfun/step-3.7-flash

NovitaN/AN/AN/A

teknium/openhermes-2.5-mistral-7b

novita/teknium/openhermes-2.5-mistral-7b

NovitaN/AN/AN/A

tencent/hy3

novita/tencent/hy3

NovitaN/AN/AN/A

thudm/glm-4-32b-0414

novita/thudm/glm-4-32b-0414

NovitaN/AN/AN/A

xiaomimimo/mimo-v2-flash

novita/xiaomimimo/mimo-v2-flash

NovitaN/AN/AN/A

xiaomimimo/mimo-v2-pro

novita/xiaomimimo/mimo-v2-pro

NovitaN/AN/AN/A

xiaomimimo/mimo-v2.5

novita/xiaomimimo/mimo-v2.5

NovitaN/AN/AN/A

xiaomimimo/mimo-v2.5-pro

novita/xiaomimimo/mimo-v2.5-pro

NovitaN/AN/AN/A

zai-org/autoglm-phone-9b-multilingual

novita/zai-org/autoglm-phone-9b-multilingual

NovitaN/AN/AN/A

zai-org/glm-4.5

novita/zai-org/glm-4.5

NovitaN/AN/AN/A

zai-org/glm-4.5-air

novita/zai-org/glm-4.5-air

NovitaN/AN/AN/A

zai-org/glm-4.5v

novita/zai-org/glm-4.5v

NovitaN/AN/AN/A

zai-org/glm-4.6

novita/zai-org/glm-4.6

NovitaN/AN/AN/A

zai-org/glm-4.6v

novita/zai-org/glm-4.6v

NovitaN/AN/AN/A

zai-org/glm-4.7

novita/zai-org/glm-4.7

NovitaN/AN/AN/A

zai-org/glm-4.7-flash

novita/zai-org/glm-4.7-flash

NovitaN/AN/AN/A

zai-org/glm-4.7-h

novita/zai-org/glm-4.7-h

NovitaN/AN/AN/A

zai-org/glm-5

novita/zai-org/glm-5

NovitaN/AN/AN/A

zai-org/glm-5-turbo

novita/zai-org/glm-5-turbo

NovitaN/AN/AN/A

zai-org/glm-5.1

novita/zai-org/glm-5.1

NovitaN/AN/AN/A

zai-org/glm-5.2

novita/zai-org/glm-5.2

NovitaN/AN/AN/A

zai-org/glm-5.3

novita/zai-org/glm-5.3

NovitaN/AN/AN/A

zai-org/glm-5.3-flash

novita/zai-org/glm-5.3-flash

NovitaN/AN/AN/A

zai-org/glm-5v-turbo

novita/zai-org/glm-5v-turbo

NovitaN/AN/AN/A

DALL-E 2

openai/dall-e-2

OpenAIN/AN/A$0.02

DALL-E 3

openai/dall-e-3

OpenAIN/AN/A$0.04

GPT-4 Turbo

openai/gpt-4-turbo

OpenAI128K$10.00$30.00

GPT-4.1

openai/gpt-4.1

OpenAI1.0M$2.00$8.00

GPT-4.1 Mini

openai/gpt-4.1-mini

OpenAI1.0M$0.40$1.60

GPT-4o

openai/gpt-4o

OpenAI128K$2.50$10.00

GPT-4o Mini

openai/gpt-4o-mini

OpenAI128K$0.15$0.60

GPT-5.1

openai/gpt-5.1

OpenAI1.1M$1.25$10.00

GPT-5.2

openai/gpt-5.2

OpenAI1.1M$1.75$14.00

GPT-5.4

openai/gpt-5.4

OpenAI1.1M$2.50$15.00

GPT-5.4 Mini

openai/gpt-5.4-mini

OpenAI1.1M$0.75$4.50

GPT-5.4 Nano

openai/gpt-5.4-nano

OpenAI1.1M$0.20$1.25

GPT-5.5

openai/gpt-5.5

OpenAI1.1M$5.00$30.00

GPT-5.6

openai/gpt-5.6

OpenAI1.1M$4.00$20.00

GPT-5.6 Luna

openai/gpt-5.6-luna

OpenAI1.1M$0.20$1.20

GPT-5.6 Terra

openai/gpt-5.6-terra

OpenAI1.1M$2.00$12.00

TTS-1

openai/tts-1

OpenAIN/A$15.00N/A

TTS-1 HD

openai/tts-1-hd

OpenAIN/A$30.00N/A

Whisper

openai/whisper-1

OpenAIN/A<$0.01N/A

DeepSeek R1

parasail/deepseek-ai/DeepSeek-R1

Parasail66K$0.50$2.00

Llama 3.3 70B Instruct

parasail/meta-llama/Llama-3.3-70B-Instruct

Parasail131K$0.35$0.40

Qwen 2.5 72B Instruct

parasail/Qwen/Qwen2.5-72B-Instruct

Parasail131K$0.35$0.40

Sonar

perplexity/sonar

Perplexity128K$1.00$1.00

Sonar Deep Research

perplexity/sonar-deep-research

Perplexity128K$2.00$8.00

Sonar Pro

perplexity/sonar-pro

Perplexity200K$3.00$15.00

Sonar Reasoning Pro

perplexity/sonar-reasoning-pro

Perplexity128K$2.00$8.00

Qwen Flash

qwen/qwen-flash

Qwen1.0M$0.05$0.40

Qwen Plus

qwen/qwen-plus

Qwen1.0M$0.40$1.20

Qwen-VL Max

qwen/qwen-vl-max

Qwen131K$0.80$3.20

Qwen3 235B A22B Instruct

qwen/qwen3-235b-a22b-instruct-2507

Qwen131K$0.23$0.92

Qwen3 235B A22B Thinking

qwen/qwen3-235b-a22b-thinking-2507

Qwen131K$0.23$2.30

Qwen3 Coder Plus

qwen/qwen3-coder-plus

Qwen1.0M$1.00$5.00

Qwen3 Max

qwen/qwen3-max

Qwen262K$1.20$6.00

Qwen3-VL Plus

qwen/qwen3-vl-plus

Qwen262K$0.20$1.60

Qwen3.8 Max

qwen/qwen3.8-max

Qwen1.0M$2.00$6.00

QwQ Plus

qwen/qwq-plus

Qwen131K$0.80$2.40

DeepSeek R1

sambanova/DeepSeek-R1

Sambanova131K$0.50$1.50

DeepSeek-V3.1

sambanova/DeepSeek-V3.1

SambanovaN/AN/AN/A

DeepSeek-V3.2

sambanova/DeepSeek-V3.2

SambanovaN/AN/AN/A

gemma-4-31B-it

sambanova/gemma-4-31B-it

SambanovaN/AN/AN/A

gpt-oss-120b

sambanova/gpt-oss-120b

SambanovaN/AN/AN/A

Llama 3.1 8B Instruct

sambanova/Meta-Llama-3.1-8B-Instruct

Sambanova131K$0.10$0.20

Llama 3.3 70B Instruct

sambanova/Meta-Llama-3.3-70B-Instruct

Sambanova131K$0.60$1.20

MiniMax-M2.7

sambanova/MiniMax-M2.7

SambanovaN/AN/AN/A

MiniMax-M3

sambanova/MiniMax-M3

SambanovaN/AN/AN/A

Qwen 2.5 72B Instruct

sambanova/Qwen2.5-72B-Instruct

Sambanova131K$0.60$1.20

DeepSeek R1

siliconflow/deepseek-ai/DeepSeek-R1

Siliconflow66K$0.14$0.56

DeepSeek V3

siliconflow/deepseek-ai/DeepSeek-V3

Siliconflow66K$0.14$0.28

Llama 3.1 70B Instruct

siliconflow/meta-llama/Meta-Llama-3.1-70B-Instruct

Siliconflow131K$0.14$0.28

Qwen 2.5 72B Instruct

siliconflow/Qwen/Qwen2.5-72B-Instruct

Siliconflow131K$0.14$0.28

DeepSeek V4 Flash

together/deepseek-ai/DeepSeek-V4-Flash-0731

Together1.0M$0.14$0.28

GLM-5.3

together/zai-org/GLM-5.3

Together1.0M$1.40$4.40

GPT-OSS 120B

together/openai/gpt-oss-120b

Together131K$0.15$0.60

Kimi K3

together/moonshotai/Kimi-K3

Together1.0M$3.00$15.00

Llama 3.3 70B Instruct Turbo

together/meta-llama/Llama-3.3-70B-Instruct-Turbo

Together128K$1.04$1.04

MiniMax M3

together/MiniMaxAI/MiniMax-M3

Together1.0M$0.30$1.20

Qwen3.7 Plus

together/Qwen/Qwen3.7-Plus

Together131K$0.32$1.28

Qwen3.8 Flash

together/Qwen/Qwen3.8-Flash

Together131K$0.15$0.47

Grok 4.3

xai/grok-4.3

xAI1.0M$1.25$2.50

Grok 4.5

xai/grok-4.5

xAI500K$2.00$6.00

Grok 4.6

xai/grok-4.6

xAI500K$2.00$6.00

Grok Build 0.1

xai/grok-build-0.1

xAI256K$1.00$2.00

GLM-4.5

zai/glm-4.5

Zai128K$0.60$2.20

GLM-4.5 Air

zai/glm-4.5-air

Zai128K$0.20$1.10

GLM-4.5V

zai/glm-4.5v

Zai64K$0.60$1.80

GLM-4.6

zai/glm-4.6

Zai200K$0.60$2.20

GLM-4.7

zai/glm-4.7

Zai200K$0.60$2.20

GLM-4.7 Flash

zai/glm-4.7-flash

Zai200KN/AN/A

GLM-4.7 FlashX

zai/glm-4.7-flashx

Zai200K$0.07$0.40

GLM-5

zai/glm-5

Zai200K$1.00$3.20

GLM-5.3

zai/glm-5.3

Zai1.0M$1.40$4.40

GLM-5.3 Flash

zai/glm-5.3-flash

Zai200K$0.15$0.50

Цены указаны в долларах США за 1M токенов и берутся из каталога API (GET /api/v1/models). Ставка, по которой тарифицируются ваши запросы, определяется договором вашей организации; потребление в панели и в GET /api/v1/generation отражается ровно так, как тарифицируется.

Не нашли нужную модель?

Мы добавляем новые модели в течение 24 часов после релиза провайдером. Свяжитесь с нами для приоритетного доступа.