Models and pricing
Every model the API serves, what it costs and what it takes. Send its id as model; GET /v1/models lists the same models with everything below as data.
Chat and reasoning
| Model | Price | Context |
|---|---|---|
| deepseek-v4.1-flash-1017DeepSeek V4.1 Flash 1017 | $0.15 in, $0.60 out / 1M tokens | 1M tokens |
| glm-5.2GLM 5.2 | $0.75 in, $3.00 out / 1M tokensLimits: 30 a minute, 8 at once | 1M tokens |
| glm-5.3GLM 5.3 | $0.75 in, $3.00 out / 1M tokensLimits: 30 a minute, 8 at once | 1M tokens |
| glm-5.3-flashGLM 5.3 Flash | $0.10 in, $0.35 out / 1M tokens | 1M tokens |
| mimo-v2.6-flashMiMo V2.6 Flash | $0.10 in, $0.25 out / 1M tokens | 1M tokens |
| mimo-v2.6-proMiMo V2.6 Pro | $0.40 in, $0.80 out / 1M tokens | 1M tokens |
| minimax-m3.1-flashMiniMax M3.1 Flash | $0.20 in, $0.90 out / 1M tokens | 1M tokens |
| muse-glimmer-30bMuse Glimmer 30B | $0.25 in, $1.00 out / 1M tokens | 128K tokens |
| nemotron-3-nano-omni-30b-a3b-reasoningNemotron 3 Nano Omni | $0.10 in, $0.25 out / 1M tokens | 256K tokens |
| nemotron-3.5-content-safetyNemotron 3.5 Content Safety | $0.05 in, $0.15 out / 1M tokens | 128K tokens |
| qwen3.8-27bQwen 3.8 27B | $0.15 in, $1.00 out / 1M tokens | 256K tokens |
| qwen3.8-flash-nextQwen 3.8 Flash Next | $0.10 in, $0.20 out / 1M tokens | 256K tokens |
| raon-1-mini-previewRaon-1 mini (preview) | $0.10 in, $0.30 out / 1M tokens | 256K tokens |
Images
| Model | Price |
|---|---|
| qwen-image-2.1Qwen-Image 2.1 (evaluation) | FreeLimits: 10 a minute, 2 at once |
| minimax-h3MiniMax H3Also: Video | $0.02–$0.825 / megapixel4 quality tiers |
| moss-imageMOSS-Image | $0.02 / megapixelLimits: 10 a minute, 1 at once |
| z-image-turboZ-Image Turbo | $0.02 / megapixel |
Video
| Model | Price |
|---|---|
| minimax-h3MiniMax H3Also: Images | $0.06–$0.90 / second4 quality tiers |
Music
| Model | Price |
|---|---|
| ace-step-1.5ACE-Step 1.5 | $0.0002–$0.0015 / second2 quality tiers |
| minimax-music3MiniMax Music 3 | $0.001 / second |
Speech
| Model | Price |
|---|---|
| aukAuK (evaluation) | FreeLimits: 10 a minute, 1 at once |
| auk-flashAuK-Flash (evaluation) | FreeLimits: 10 a minute, 1 at once |
| chatterboxChatterbox | $0.00028 / second |
| qwen3-tts-12hz-1.7bQwen 3 TTS 12Hz 1.7B | $0.00028 / second |
Transcription
| Model | Price |
|---|---|
| granite-speech-5.0-2bGranite Speech 5.0 2B | $0.00000555 / second |
| qwen3-asr-1.7bQwen3-ASR 1.7B | $0.0000075 / second |
| voxtral-mini-4b-realtimeVoxtral Mini 4B Realtime | $0.000133 / second |
| whisper-large-v3-turboWhisper Large V3 Turbo | $0.0000111 / second |
Alignment
| Model | Price |
|---|---|
| aligner-1Aligner 1 | $0.0000333 / second |
Embeddings
| Model | Price | Context |
|---|---|---|
| qwen3-embedding-4bQwen 3 Embedding 4B | $0.05 / 1M tokens | 32K tokens |
Rerank
| Model | Price | Context |
|---|---|---|
| bge-reranker-v2-m3BGE M3 | $0.05 / 1M tokens | 8K tokens |
| vultron-retriever-core-qwen3.5-4.5bVultron Retriever Core 4.5B | $0.10 / 1M tokens | 256K tokens |
| vultron-retriever-flash-qwen3.5-0.8bVultron Retriever Flash 0.8B | $0.05 / 1M tokens | 256K tokens |
Decisions
| Model | Price | Context |
|---|---|---|
| clefClef | $0.10 / 1M tokens | 256K tokens |
| clef-flashClef Flash | $0.05 / 1M tokens | 256K tokens |
| d3 | $0.10 / 1M tokens | 256K tokens |
| pplx-decider-v1.2pplx-decider v1.2 | $0.10 / 1M tokens | 256K tokens |