Pricing
Models & pricing
Every model currently on sale, with its list price. Use the slug as the model parameter when calling the API.
These are list prices. Accounts on a custom pricing plan may have different unit prices — after logging in, see the prices that apply to you on the Models page in the dashboard.
93 models
anthropic/claude-fable-5
anthropic-claude-fable-5Chat- Input / 1M
- $10.00≈ $0.01 / 1K
- Output / 1M
- $50.00≈ $0.05 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-haiku-4-5
anthropic-claude-haiku-4-5Chat- Input / 1M
- $1.00≈ $0.001 / 1K
- Output / 1M
- $5.00≈ $0.005 / 1K
- Context
- 200K
- Max output
- —
anthropic/claude-opus-4-7
anthropic-claude-opus-4-7Chat- Input / 1M
- $5.00≈ $0.005 / 1K
- Output / 1M
- $25.00≈ $0.025 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-opus-4-8
anthropic-claude-opus-4-8Chat- Input / 1M
- $5.00≈ $0.005 / 1K
- Output / 1M
- $25.00≈ $0.025 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-opus-5
anthropic-claude-opus-5Chat- Input / 1M
- $5.00≈ $0.005 / 1K
- Output / 1M
- $25.00≈ $0.025 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-opus-5-5
anthropic-claude-opus-5-5Chat- Input / 1M
- $4.00≈ $0.004 / 1K
- Output / 1M
- $20.00≈ $0.02 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-sonnet-4-6
anthropic-claude-sonnet-4-6Chat- Input / 1M
- $3.00≈ $0.003 / 1K
- Output / 1M
- $15.00≈ $0.015 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-sonnet-5
anthropic-claude-sonnet-5Chat- Input / 1M
- $3.00≈ $0.003 / 1K
- Output / 1M
- $15.00≈ $0.015 / 1K
- Context
- 1M
- Max output
- —
anthropic/claude-sonnet-5-5
anthropic-claude-sonnet-5-5Chat- Input / 1M
- $2.00≈ $0.002 / 1K
- Output / 1M
- $10.00≈ $0.01 / 1K
- Context
- 1M
- Max output
- —
BAAI/bge-base-en-v1.5
baai-bge-base-en-v1-5Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
BAAI/bge-en-icl
baai-bge-en-iclEmbedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 8.2K
- Max output
- —
BAAI/bge-large-en-v1.5
baai-bge-large-en-v1-5Embedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
BAAI/bge-m3
baai-bge-m3Embedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 8.2K
- Max output
- —
BAAI/bge-m3-multi
baai-bge-m3-multiEmbedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
deepseek-ai/DeepSeek-R1-0528
deepseek-ai-deepseek-r1-0528Chat- Input / 1M
- $0.50≈ $0.0005 / 1K
- Output / 1M
- $2.15≈ $0.00215 / 1K
- Context
- —
- Max output
- —
deepseek-ai/DeepSeek-V3
deepseek-ai-deepseek-v3Chat- Input / 1M
- $0.32≈ $0.00032 / 1K
- Output / 1M
- $0.89≈ $0.00089 / 1K
- Context
- 163.8K
- Max output
- —
deepseek-ai/DeepSeek-V3.1
deepseek-ai-deepseek-v3-1Chat- Input / 1M
- $0.25≈ $0.00025 / 1K
- Output / 1M
- $0.95≈ $0.00095 / 1K
- Context
- 163.8K
- Max output
- —
deepseek-ai/DeepSeek-V3.2
deepseek-ai-deepseek-v3-2Chat- Input / 1M
- $0.26≈ $0.00026 / 1K
- Output / 1M
- $0.38≈ $0.00038 / 1K
- Context
- 163.8K
- Max output
- —
deepseek-ai/DeepSeek-V4-Flash
deepseek-ai-deepseek-v4-flashChat- Input / 1M
- $0.09≈ $0.00009 / 1K
- Output / 1M
- $0.18≈ $0.00018 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4-Flash-0731
deepseek-ai-deepseek-v4-flash-0731Chat- Input / 1M
- $0.06≈ $0.00006 / 1K
- Output / 1M
- $0.18≈ $0.00018 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
deepseek-ai-deepseek-v4-flash-vision-expChat- Input / 1M
- $0.2156≈ $0.000216 / 1K
- Output / 1M
- $0.6468≈ $0.000647 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4-Pro
deepseek-ai-deepseek-v4-proChat- Input / 1M
- $1.30≈ $0.0013 / 1K
- Output / 1M
- $2.60≈ $0.0026 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4-Pro-0813
deepseek-ai-deepseek-v4-pro-0813Chat- Input / 1M
- $1.30≈ $0.0013 / 1K
- Output / 1M
- $2.60≈ $0.0026 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4.1-Flash
deepseek-ai-deepseek-v4-1-flashChat- Input / 1M
- $0.14≈ $0.00014 / 1K
- Output / 1M
- $0.42≈ $0.00042 / 1K
- Context
- 1M
- Max output
- —
deepseek-ai/DeepSeek-V4.1-Flash-1017
deepseek-ai-deepseek-v4-1-flash-1017Chat- Input / 1M
- $0.098≈ $0.000098 / 1K
- Output / 1M
- $0.294≈ $0.000294 / 1K
- Context
- 1M
- Max output
- —
google/gemini-2.5-flash
google-gemini-2-5-flashChat- Input / 1M
- $0.30≈ $0.0003 / 1K
- Output / 1M
- $2.50≈ $0.0025 / 1K
- Context
- 1M
- Max output
- —
google/gemini-2.5-pro
google-gemini-2-5-proChat- Input / 1M
- $1.25≈ $0.00125 / 1K
- Output / 1M
- $10.00≈ $0.01 / 1K
- Context
- 1M
- Max output
- —
google/gemini-3.1-flash-lite
google-gemini-3-1-flash-liteChat- Input / 1M
- $0.25≈ $0.00025 / 1K
- Output / 1M
- $1.50≈ $0.0015 / 1K
- Context
- 1M
- Max output
- —
google/gemini-3.1-pro
google-gemini-3-1-proChat- Input / 1M
- $2.00≈ $0.002 / 1K
- Output / 1M
- $12.00≈ $0.012 / 1K
- Context
- 1M
- Max output
- —
google/gemini-3.5-flash
google-gemini-3-5-flashChat- Input / 1M
- $1.50≈ $0.0015 / 1K
- Output / 1M
- $9.00≈ $0.009 / 1K
- Context
- 1M
- Max output
- —
google/gemini-3.7-flash
google-gemini-3-7-flashChat- Input / 1M
- $0.75≈ $0.00075 / 1K
- Output / 1M
- $3.75≈ $0.00375 / 1K
- Context
- 1M
- Max output
- —
google/gemma-3-12b-it
google-gemma-3-12b-itChat- Input / 1M
- $0.05≈ $0.00005 / 1K
- Output / 1M
- $0.15≈ $0.00015 / 1K
- Context
- 131.1K
- Max output
- —
google/gemma-3-27b-it
google-gemma-3-27b-itChat- Input / 1M
- $0.08≈ $0.00008 / 1K
- Output / 1M
- $0.16≈ $0.00016 / 1K
- Context
- 131.1K
- Max output
- —
google/gemma-3-4b-it
google-gemma-3-4b-itChat- Input / 1M
- $0.05≈ $0.00005 / 1K
- Output / 1M
- $0.10≈ $0.0001 / 1K
- Context
- 131.1K
- Max output
- —
google/gemma-4-26B-A4B-it
google-gemma-4-26b-a4b-itChat- Input / 1M
- $0.07≈ $0.00007 / 1K
- Output / 1M
- $0.34≈ $0.00034 / 1K
- Context
- 262.1K
- Max output
- —
google/gemma-4-31B-it
google-gemma-4-31b-itChat- Input / 1M
- $0.20≈ $0.0002 / 1K
- Output / 1M
- $0.40≈ $0.0004 / 1K
- Context
- 262.1K
- Max output
- —
google/gemma-4-31B-it-turbo
google-gemma-4-31b-it-turboChat- Input / 1M
- $0.09≈ $0.00009 / 1K
- Output / 1M
- $0.34≈ $0.00034 / 1K
- Context
- 262.1K
- Max output
- —
google/gemma-4-31B-it-Ultra
google-gemma-4-31b-it-ultraChat- Input / 1M
- $0.27≈ $0.00027 / 1K
- Output / 1M
- $0.76≈ $0.00076 / 1K
- Context
- 131.1K
- Max output
- —
intfloat/e5-base-v2
intfloat-e5-base-v2Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
intfloat/e5-large-v2
intfloat-e5-large-v2Embedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
intfloat/multilingual-e5-large
intfloat-multilingual-e5-largeEmbedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
intfloat/multilingual-e5-large-instruct
intfloat-multilingual-e5-large-instructEmbedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
meta-llama/Llama-3.3-70B-Instruct-Turbo
meta-llama-llama-3-3-70b-instruct-turboChat- Input / 1M
- $0.10≈ $0.0001 / 1K
- Output / 1M
- $0.32≈ $0.00032 / 1K
- Context
- 131.1K
- Max output
- —
meta-llama/Llama-4-Scout-17B-16E-Instruct
meta-llama-llama-4-scout-17b-16e-instructChat- Input / 1M
- $0.10≈ $0.0001 / 1K
- Output / 1M
- $0.30≈ $0.0003 / 1K
- Context
- 327.7K
- Max output
- —
meta-llama/Llama-Guard-4-12B
meta-llama-llama-guard-4-12bChat- Input / 1M
- $0.18≈ $0.00018 / 1K
- Output / 1M
- $0.18≈ $0.00018 / 1K
- Context
- 163.8K
- Max output
- —
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
meta-llama-meta-llama-3-1-8b-instruct-turboChat- Input / 1M
- $0.02≈ $0.00002 / 1K
- Output / 1M
- $0.04≈ $0.00004 / 1K
- Context
- 131.1K
- Max output
- —
microsoft/phi-4
microsoft-phi-4Chat- Input / 1M
- $0.07≈ $0.00007 / 1K
- Output / 1M
- $0.14≈ $0.00014 / 1K
- Context
- 16.4K
- Max output
- —
mistralai/Mistral-Nemo-Instruct-2407
mistralai-mistral-nemo-instruct-2407Chat- Input / 1M
- $0.029≈ $0.000029 / 1K
- Output / 1M
- $0.03≈ $0.00003 / 1K
- Context
- 131.1K
- Max output
- —
mistralai/Mistral-Small-24B-Instruct-2501
mistralai-mistral-small-24b-instruct-2501Chat- Input / 1M
- $0.05≈ $0.00005 / 1K
- Output / 1M
- $0.08≈ $0.00008 / 1K
- Context
- 32.8K
- Max output
- —
mistralai/Mistral-Small-3.2-24B-Instruct-2506
mistralai-mistral-small-3-2-24b-instruct-2506Chat- Input / 1M
- $0.075≈ $0.000075 / 1K
- Output / 1M
- $0.20≈ $0.0002 / 1K
- Context
- 128K
- Max output
- —
moonshotai/Kimi-K2.6
moonshotai-kimi-k2-6Chat- Input / 1M
- $0.75≈ $0.00075 / 1K
- Output / 1M
- $3.50≈ $0.0035 / 1K
- Context
- 262.1K
- Max output
- —
moonshotai/Kimi-K3
moonshotai-kimi-k3Chat- Input / 1M
- $2.85≈ $0.00285 / 1K
- Output / 1M
- $14.25≈ $0.01425 / 1K
- Context
- 1M
- Max output
- —
moonshotai/Kimi-K3.1-Pro
moonshotai-kimi-k3-1-proChat- Input / 1M
- $1.90≈ $0.0019 / 1K
- Output / 1M
- $9.50≈ $0.0095 / 1K
- Context
- 1M
- Max output
- —
nvidia/Nemotron-Content-Safety-3.5
nvidia-nemotron-content-safety-3-5Chat- Input / 1M
- $0.20≈ $0.0002 / 1K
- Output / 1M
- $0.20≈ $0.0002 / 1K
- Context
- 131.1K
- Max output
- —
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
nvidia-nvidia-nemotron-3-super-120b-a12bChat- Input / 1M
- $0.075≈ $0.000075 / 1K
- Output / 1M
- $0.40≈ $0.0004 / 1K
- Context
- 262.1K
- Max output
- —
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
nvidia-nvidia-nemotron-3-ultra-550b-a55bChat- Input / 1M
- $0.50≈ $0.0005 / 1K
- Output / 1M
- $2.20≈ $0.0022 / 1K
- Context
- 262.1K
- Max output
- —
nvidia/NVIDIA-Nemotron-3.5-Lightning
nvidia-nvidia-nemotron-3-5-lightningChat- Input / 1M
- $0.06≈ $0.00006 / 1K
- Output / 1M
- $0.16≈ $0.00016 / 1K
- Context
- 262.1K
- Max output
- —
nvidia/NVIDIA-Nemotron-3.5-Super-VL
nvidia-nvidia-nemotron-3-5-super-vlChat- Input / 1M
- $0.15≈ $0.00015 / 1K
- Output / 1M
- $0.50≈ $0.0005 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen2.5-72B-Instruct
qwen-qwen2-5-72b-instructChat- Input / 1M
- $0.36≈ $0.00036 / 1K
- Output / 1M
- $0.40≈ $0.0004 / 1K
- Context
- 32.8K
- Max output
- —
Qwen/Qwen3-14B
qwen-qwen3-14bChat- Input / 1M
- $0.12≈ $0.00012 / 1K
- Output / 1M
- $0.24≈ $0.00024 / 1K
- Context
- 41K
- Max output
- —
Qwen/Qwen3-235B-A22B-Instruct-2507
qwen-qwen3-235b-a22b-instruct-2507Chat- Input / 1M
- $0.09≈ $0.00009 / 1K
- Output / 1M
- $0.55≈ $0.00055 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3-30B-A3B
qwen-qwen3-30b-a3bChat- Input / 1M
- $0.12≈ $0.00012 / 1K
- Output / 1M
- $0.50≈ $0.0005 / 1K
- Context
- 41K
- Max output
- —
Qwen/Qwen3-32B
qwen-qwen3-32bChat- Input / 1M
- $0.08≈ $0.00008 / 1K
- Output / 1M
- $0.28≈ $0.00028 / 1K
- Context
- 41K
- Max output
- —
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
qwen-qwen3-coder-480b-a35b-instruct-turboChat- Input / 1M
- $0.30≈ $0.0003 / 1K
- Output / 1M
- $1.00≈ $0.001 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3-Next-80B-A3B-Instruct
qwen-qwen3-next-80b-a3b-instructChat- Input / 1M
- $0.09≈ $0.00009 / 1K
- Output / 1M
- $1.10≈ $0.0011 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3-VL-235B-A22B-Instruct
qwen-qwen3-vl-235b-a22b-instructChat- Input / 1M
- $0.20≈ $0.0002 / 1K
- Output / 1M
- $0.88≈ $0.00088 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3-VL-30B-A3B-Instruct
qwen-qwen3-vl-30b-a3b-instructChat- Input / 1M
- $0.15≈ $0.00015 / 1K
- Output / 1M
- $0.60≈ $0.0006 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.5-27B
qwen-qwen3-5-27bChat- Input / 1M
- $0.26≈ $0.00026 / 1K
- Output / 1M
- $2.60≈ $0.0026 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.5-35B-A3B
qwen-qwen3-5-35b-a3bChat- Input / 1M
- $0.14≈ $0.00014 / 1K
- Output / 1M
- $1.00≈ $0.001 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.5-397B-A17B
qwen-qwen3-5-397b-a17bChat- Input / 1M
- $0.45≈ $0.00045 / 1K
- Output / 1M
- $3.00≈ $0.003 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.5-9B
qwen-qwen3-5-9bChat- Input / 1M
- $0.10≈ $0.0001 / 1K
- Output / 1M
- $0.15≈ $0.00015 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.6-27B
qwen-qwen3-6-27bChat- Input / 1M
- $0.32≈ $0.00032 / 1K
- Output / 1M
- $3.20≈ $0.0032 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.6-35B-A3B
qwen-qwen3-6-35b-a3bChat- Input / 1M
- $0.10≈ $0.0001 / 1K
- Output / 1M
- $0.95≈ $0.00095 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.7-Max
qwen-qwen3-7-maxChat- Input / 1M
- $2.50≈ $0.0025 / 1K
- Output / 1M
- $7.50≈ $0.0075 / 1K
- Context
- 256K
- Max output
- —
Qwen/Qwen3.8-27B
qwen-qwen3-8-27bChat- Input / 1M
- $0.15≈ $0.00015 / 1K
- Output / 1M
- $1.875≈ $0.001875 / 1K
- Context
- 262.1K
- Max output
- —
Qwen/Qwen3.8-Flash
qwen-qwen3-8-flashChat- Input / 1M
- $0.113≈ $0.000113 / 1K
- Output / 1M
- $0.382≈ $0.000382 / 1K
- Context
- 1M
- Max output
- —
Qwen/Qwen3.8-Max
qwen-qwen3-8-maxChat- Input / 1M
- $1.65≈ $0.00165 / 1K
- Output / 1M
- $4.951≈ $0.004951 / 1K
- Context
- 256K
- Max output
- —
sentence-transformers/all-MiniLM-L12-v2
sentence-transformers-all-minilm-l12-v2Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
sentence-transformers/all-MiniLM-L6-v2
sentence-transformers-all-minilm-l6-v2Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
sentence-transformers/all-mpnet-base-v2
sentence-transformers-all-mpnet-base-v2Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
sentence-transformers/multi-qa-mpnet-base-dot-v1
sentence-transformers-multi-qa-mpnet-base-dot-v1Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
sentence-transformers/paraphrase-MiniLM-L6-v2
sentence-transformers-paraphrase-minilm-l6-v2Embedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
shibing624/text2vec-base-chinese
shibing624-text2vec-base-chineseEmbedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
tencent/Hy4-preview
tencent-hy4-previewChat- Input / 1M
- $0.834≈ $0.000834 / 1K
- Output / 1M
- $2.501≈ $0.002501 / 1K
- Context
- 1M
- Max output
- —
thenlper/gte-base
thenlper-gte-baseEmbedding- Input / 1M
- $0.005≈ $0.000005 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
thenlper/gte-large
thenlper-gte-largeEmbedding- Input / 1M
- $0.01≈ $0.00001 / 1K
- Output / 1M
- —
- Context
- 512
- Max output
- —
XiaomiMiMo/MiMo-V2.6-Flash
xiaomimimo-mimo-v2-6-flashChat- Input / 1M
- $0.14≈ $0.00014 / 1K
- Output / 1M
- $0.28≈ $0.00028 / 1K
- Context
- 1M
- Max output
- —
XiaomiMiMo/MiMo-V2.6-Pro
xiaomimimo-mimo-v2-6-proChat- Input / 1M
- $0.387≈ $0.000387 / 1K
- Output / 1M
- $0.783≈ $0.000783 / 1K
- Context
- 1M
- Max output
- —
zai-org/GLM-4.6
zai-org-glm-4-6Chat- Input / 1M
- $0.50≈ $0.0005 / 1K
- Output / 1M
- $2.00≈ $0.002 / 1K
- Context
- 202.8K
- Max output
- —
zai-org/GLM-4.7
zai-org-glm-4-7Chat- Input / 1M
- $0.40≈ $0.0004 / 1K
- Output / 1M
- $1.75≈ $0.00175 / 1K
- Context
- 202.8K
- Max output
- —
zai-org/GLM-5.2
zai-org-glm-5-2Chat- Input / 1M
- $0.5625≈ $0.000563 / 1K
- Output / 1M
- $1.80≈ $0.0018 / 1K
- Context
- 1M
- Max output
- —
zai-org/GLM-5.3
zai-org-glm-5-3Chat- Input / 1M
- $0.5625≈ $0.000563 / 1K
- Output / 1M
- $2.50≈ $0.0025 / 1K
- Context
- 1M
- Max output
- —
zai-org/GLM-5.3-Flash
zai-org-glm-5-3-flashChat- Input / 1M
- $0.15≈ $0.00015 / 1K
- Output / 1M
- $0.50≈ $0.0005 / 1K
- Context
- 1M
- Max output
- —
How billing works
- Prices are in USD per 1,000,000 tokens; input (prompt) and output (completion) are billed separately.
- Cost per request = tokens × unit price ÷ 1,000,000, rounded up to $0.000001. The “≈ / 1K” column is for quick reference only.
- Each request places a hold for its estimated maximum cost, then only the actual tokens used are charged.
- No monthly fees, no minimum commitment. Your wallet is in USD; top up by VND bank transfer via VietQR (converted at the rate when the QR code is created).
Details: Billing docs