Catalog
Models
USD per 1M tokens. Use the ID in the model field.
Chat & reasoning
| Model | Provider | Context | Input | Output | Cached input |
|---|---|---|---|---|---|
|
DeepSeek | 1M | $0.39 | $1.56 | $0.008 |
|
|
DeepSeek | 1M | $0.39 | $1.56 | $0.008 |
|
|
DeepSeek | 1M | $2.26 | $4.52 | $0.45 |
|
|
DeepSeek | 1M | $1.72 | $5.15 | $0.057 |
|
|
DeepSeek | 1M | $0.18 | $0.36 | $0.036 |
|
|
DeepSeek | 1M | $0.18 | $0.36 | $0.036 |
|
DeepSeek V3.2 deepseek/deepseek-v3.2 |
DeepSeek | 164K | $0.65 | $2.08 | $0.20 |
|
Z.ai | 1M | $1.82 | $5.72 | $0.34 |
|
|
Z.ai | 1M | $0.20 | $0.65 | $0.039 |
|
GLM-5.2 z-ai/glm-5.2 |
Z.ai | 1M | $1.82 | $5.72 | $0.27 |
|
Moonshot AI | 262K | $3.90 | $19.50 | $0.39 |
|
|
Moonshot AI | 262K | $1.24 | $5.20 | $0.25 |
|
Alibaba | 1M | $2.60 | $7.80 | $0.26 |
|
Qwen 3.5 397B A17B qwen/qwen3.5-397b-a17b |
Alibaba | 131K | $0.71 | $4.55 | $0.14 |
|
256K | $0.23 | $0.65 | $0.047 | |
|
MiniMax | 1M | $0.20 | $0.78 | $0.019 |
|
MiniMax M2.5 minimax/minimax-m2.5 |
MiniMax | 66K | $0.39 | $1.56 | $0.078 |
Llama 4 Maverick meta-llama/llama-4-maverick |
Meta | 128K | $0.33 | $1.13 | $0.065 |
|
Mistral AI | 262K | $0.26 | $0.26 | $0.052 |
Nemotron 3 Ultra nvidia/nemotron-3-ultra |
NVIDIA | 131K | $1.17 | $2.21 | $0.23 |
|
|
NVIDIA | 1M | $0.39 | $0.84 | $0.078 |
|
|
NVIDIA | 66K | $0.65 | $1.17 | $0.13 |
|
|
NVIDIA | 128K | $0.26 | $0.78 | $0.052 |
MiMo V2.5 Pro xiaomi/mimo-v2.5-pro |
Xiaomi | 262K | $1.04 | $3.90 | $0.21 |
R
Reflection Beam reflection/beam |
Reflection AI | 1M | $0.52 | $1.56 | $0.052 |
|
Arcee AI | 128K | $0.33 | $1.17 | $0.078 |
Images
| Model | Provider | Price |
|---|---|---|
Stable Diffusion 3.5 Large stabilityai/stable-diffusion-3.5-large | Stability AI | $0.104 / image |
FLUX.1 [schnell] black-forest-labs/flux-schnell | Black Forest Labs | $0.0039 / megapixel |
|
Fast SDXL stabilityai/fast-sdxl | Stability AI | $0.0014 / GPU second |
Video
| Model | Provider | Price |
|---|---|---|
Wan 2.2 Text-to-Video alibaba/wan-2.2-t2v | Alibaba | $0.78 / video |
Text to speech
| Model | Provider | Price |
|---|---|---|
|
Qwen3 TTS (voice design) qwen/qwen3-tts | Alibaba | $0.026 / 1K characters |
ElevenLabs Multilingual v2 elevenlabs/multilingual-v2 | ElevenLabs | $0.130 / 1K characters |
Music & sound
| Model | Provider | Price |
|---|---|---|
|
Stable Audio 2.5 stabilityai/stable-audio-2.5 | Stability AI | $0.0008 / GPU second |
Reranking
| Model | Provider | Price |
|---|---|---|
BGE Reranker v2 M3 baai/bge-reranker-v2-m3 | BAAI | $0.013 / 1M tokens |
Embeddings
| Model | Provider | Input |
|---|---|---|
|
BGE-M3 baai/bge-m3 | BAAI | $0.0260 |
E5 Large v2 intfloat/e5-large-v2 | intfloat | $0.0260 |
|
GTE Large EN v1.5 alibaba/gte-large-en-v1.5 | Alibaba | $0.1170 |
|
Qwen3 Embedding 0.6B qwen/qwen3-embedding-0.6b | Alibaba | $0.0520 |
|
all-MiniLM-L6-v2 sentence-transformers/all-minilm-l6-v2 | Sentence Transformers | $0.0117 |
|
multi-qa-mpnet-base-dot-v1 sentence-transformers/multi-qa-mpnet-base-dot-v1 | Sentence Transformers | $0.0117 |
Prices can change when our upstream providers change theirs. The live list is always at GET /api/v1/models.