Live model networkThe right model.
The right model.
Always within reach.
Explore the curated AIx catalog across chat, reasoning, image generation, speech and embeddings. One OpenAI-compatible key calls every model below.
80+CURATED MODELS
24/7AIx NETWORK
5MODALITIES
1API KEY
USD billing snapshot: October 21, 2026. Live prices load when available. Listing is not a guarantee of upstream availability.
| Model | Best for | Type | Price | Unit |
|---|---|---|---|---|
| Voxtral-Small-24B-2507mistralai/Voxtral-Small-24B-2507 | Evaluate for audio workloads using the documented endpoint | audio | $0.003 | / minute |
| Voxtral-Mini-3B-2507mistralai/Voxtral-Mini-3B-2507 | Evaluate for audio workloads using the documented endpoint | audio | $0.001 | / minute |
| Whisper Large V3openai/whisper-large-v3 | Accurate multilingual transcription | audio | $0.00045 | / minute |
| whisper-large-v3-turboopenai/whisper-large-v3-turbo | Evaluate for audio workloads using the documented endpoint | audio | $0.0002 | / minute |
| Nemotron-3.5-ASR-Streaming-Multilingual-0.6bnvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b | Evaluate for audio workloads using the documented endpoint | audio | $0.0002 | / minute |
| gpt-5.4-proopenai/gpt-5.4-pro | Evaluate for chat workloads using the documented endpoint | chat | $216 | / 1M billed tokens |
| gpt-5.5-proopenai/gpt-5.5-pro | Evaluate for chat workloads using the documented endpoint | chat | $216 | / 1M billed tokens |
| gpt-5.2-proopenai/gpt-5.2-pro | Evaluate for chat workloads using the documented endpoint | chat | $201.6 | / 1M billed tokens |
| gpt-5-proopenai/gpt-5-pro | Evaluate for chat workloads using the documented endpoint | chat | $144 | / 1M billed tokens |
| o3-proopenai/o3-pro | Evaluate for chat workloads using the documented endpoint | chat | $96 | / 1M billed tokens |
| claude-fable-5anthropic/claude-fable-5 | Evaluate for chat workloads using the documented endpoint | chat | $60 | / 1M billed tokens |
| gpt-6-astraopenai/gpt-6-astra | Evaluate for chat workloads using the documented endpoint | chat | $60 | / 1M billed tokens |
| gpt-6-astra-proopenai/gpt-6-astra-pro | Evaluate for chat workloads using the documented endpoint | chat | $60 | / 1M billed tokens |
| claude-fable-5.1anthropic/claude-fable-5.1 | Evaluate for chat workloads using the documented endpoint | chat | $60 | / 1M billed tokens |
| gpt-5.5openai/gpt-5.5 | Evaluate for chat workloads using the documented endpoint | chat | $36 | / 1M billed tokens |
| claude-opus-4-7anthropic/claude-opus-4-7 | Evaluate for chat workloads using the documented endpoint | chat | $30 | / 1M billed tokens |
| Claude Opus 4.8anthropic/claude-opus-4-8 | Hardest reasoning & long agentic sessions | chat | $30 | / 1M billed tokens |
| claude-opus-5anthropic/claude-opus-5 | Evaluate for chat workloads using the documented endpoint | chat | $30 | / 1M billed tokens |
| gpt-5.6-solopenai/gpt-5.6-sol | Evaluate for chat workloads using the documented endpoint | chat | $24 | / 1M billed tokens |
| gpt-5.6-sol-proopenai/gpt-5.6-sol-pro | Evaluate for chat workloads using the documented endpoint | chat | $24 | / 1M billed tokens |
| Kimi-K3moonshotai/Kimi-K3 | Evaluate for chat workloads using the documented endpoint | chat | $19.5 | / 1M billed tokens |
| gpt-5.4openai/gpt-5.4 | Evaluate for chat workloads using the documented endpoint | chat | $18 | / 1M billed tokens |
| gpt-5.4-image-2openai/gpt-5.4-image-2 | Evaluate for chat workloads using the documented endpoint | chat | $18 | / 1M billed tokens |
| Claude Sonnet 4.6anthropic/claude-sonnet-4-6 | Balanced coding & agents — the default pick | chat | $18 | / 1M billed tokens |
| gpt-5.3-chatopenai/gpt-5.3-chat | Evaluate for chat workloads using the documented endpoint | chat | $17.4 | / 1M billed tokens |
| gpt-5.2-chatopenai/gpt-5.2-chat | Evaluate for chat workloads using the documented endpoint | chat | $16.8 | / 1M billed tokens |
| gpt-5.2openai/gpt-5.2 | Evaluate for chat workloads using the documented endpoint | chat | $16.8 | / 1M billed tokens |
| gpt-5.2-codexopenai/gpt-5.2-codex | Evaluate for chat workloads using the documented endpoint | chat | $16.8 | / 1M billed tokens |
| gpt-5.3-codexopenai/gpt-5.3-codex | Evaluate for chat workloads using the documented endpoint | chat | $16.8 | / 1M billed tokens |
| gpt-5.6-terra-proopenai/gpt-5.6-terra-pro | Evaluate for chat workloads using the documented endpoint | chat | $14.4 | / 1M billed tokens |
| gpt-5.6-terraopenai/gpt-5.6-terra | Evaluate for chat workloads using the documented endpoint | chat | $14.4 | / 1M billed tokens |
| gemini-3.1-progoogle/gemini-3.1-pro | Evaluate for chat workloads using the documented endpoint | chat | $14.4 | / 1M billed tokens |
| gpt-5.1-codexopenai/gpt-5.1-codex | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| gpt-4oopenai/gpt-4o | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| gpt-5openai/gpt-5 | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| gpt-5.1openai/gpt-5.1 | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| gpt-5.1-codex-maxopenai/gpt-5.1-codex-max | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| claude-sonnet-5anthropic/claude-sonnet-5 | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| Gemini 2.5 Progoogle/gemini-2.5-pro | Massive context & multimodal analysis | chat | $12 | / 1M billed tokens |
| gpt-5-codexopenai/gpt-5-codex | Evaluate for chat workloads using the documented endpoint | chat | $12 | / 1M billed tokens |
| gemini-3.5-flashgoogle/gemini-3.5-flash | Evaluate for chat workloads using the documented endpoint | chat | $10.8 | / 1M billed tokens |
| Qwen3.7-MaxQwen/Qwen3.7-Max | Evaluate for chat workloads using the documented endpoint | chat | $9.75 | / 1M billed tokens |
| gpt-4.1openai/gpt-4.1 | Evaluate for chat workloads using the documented endpoint | chat | $9.6 | / 1M billed tokens |
| o3openai/o3 | Evaluate for chat workloads using the documented endpoint | chat | $9.6 | / 1M billed tokens |
| Qwen3-Max-ThinkingQwen/Qwen3-Max-Thinking | Evaluate for chat workloads using the documented endpoint | chat | $7.8 | / 1M billed tokens |
| Qwen3.8-2.4T-A95BQwen/Qwen3.8-2.4T-A95B | Evaluate for chat workloads using the documented endpoint | chat | $7.8 | / 1M billed tokens |
| Qwen3-MaxQwen/Qwen3-Max | Evaluate for chat workloads using the documented endpoint | chat | $7.8 | / 1M billed tokens |
| Claude Haiku 4.5anthropic/claude-haiku-4-5 | Fast agent turns and high-volume coding support | chat | $6 | / 1M billed tokens |
| GLM-5.3zai-org/GLM-5.3 | Evaluate for chat workloads using the documented endpoint | chat | $5.72 | / 1M billed tokens |
| gpt-5.4-miniopenai/gpt-5.4-mini | Evaluate for chat workloads using the documented endpoint | chat | $5.4 | / 1M billed tokens |
| o4-miniopenai/o4-mini | Evaluate for chat workloads using the documented endpoint | chat | $5.28 | / 1M billed tokens |
| o4-mini-highopenai/o4-mini-high | Evaluate for chat workloads using the documented endpoint | chat | $5.28 | / 1M billed tokens |
| o3-miniopenai/o3-mini | Evaluate for chat workloads using the documented endpoint | chat | $5.28 | / 1M billed tokens |
| Inklingthinkingmachines/Inkling | Evaluate for chat workloads using the documented endpoint | chat | $5.265 | / 1M billed tokens |
| Kimi K2.6moonshotai/Kimi-K2.6 | Agentic workflows & heavy tool use | chat | $5.2 | / 1M billed tokens |
| GLM-5.1zai-org/GLM-5.1 | Evaluate for chat workloads using the documented endpoint | chat | $4.55 | / 1M billed tokens |
| Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code | Agentic, tool-using software engineering | chat | $4.55 | / 1M billed tokens |
| Qwen3.5-397B-A17BQwen/Qwen3.5-397B-A17B | Evaluate for chat workloads using the documented endpoint | chat | $4.55 | / 1M billed tokens |
| gemini-3.6-flashgoogle/gemini-3.6-flash | Evaluate for chat workloads using the documented endpoint | chat | $4.5 | / 1M billed tokens |
| gemini-3.8-flashgoogle/gemini-3.8-flash | Evaluate for chat workloads using the documented endpoint | chat | $4.5 | / 1M billed tokens |
| gemini-3.7-flashgoogle/gemini-3.7-flash | Evaluate for chat workloads using the documented endpoint | chat | $4.5 | / 1M billed tokens |
| Qwen3.6-27BQwen/Qwen3.6-27B | Evaluate for chat workloads using the documented endpoint | chat | $4.16 | / 1M billed tokens |
| GLM-5.2zai-org/GLM-5.2 | Evaluate for chat workloads using the documented endpoint | chat | $3.9468 | / 1M billed tokens |
| MiMo-V2.5-ProXiaomiMiMo/MiMo-V2.5-Pro | Evaluate for chat workloads using the documented endpoint | chat | $3.9 | / 1M billed tokens |
| gemini-3-flashgoogle/gemini-3-flash | Evaluate for chat workloads using the documented endpoint | chat | $3.6 | / 1M billed tokens |
| DeepSeek-V4-Pro-0813deepseek-ai/DeepSeek-V4-Pro-0813 | Evaluate for chat workloads using the documented endpoint | chat | $3.38 | / 1M billed tokens |
| DeepSeek-V4-Prodeepseek-ai/DeepSeek-V4-Pro | Evaluate for chat workloads using the documented endpoint | chat | $3.38 | / 1M billed tokens |
| Qwen3.5-27BQwen/Qwen3.5-27B | Evaluate for chat workloads using the documented endpoint | chat | $3.38 | / 1M billed tokens |
| Kimi-K2-Instruct-0905moonshotai/Kimi-K2-Instruct-0905 | Evaluate for chat workloads using the documented endpoint | chat | $3.25 | / 1M billed tokens |
| DeepSeek-R1-Turbodeepseek-ai/DeepSeek-R1-Turbo | Evaluate for chat workloads using the documented endpoint | chat | $3.25 | / 1M billed tokens |
| Qwen3.5-122B-A10BQwen/Qwen3.5-122B-A10B | Evaluate for chat workloads using the documented endpoint | chat | $3.12 | / 1M billed tokens |
| gemini-3.5-flash-litegoogle/gemini-3.5-flash-lite | Evaluate for chat workloads using the documented endpoint | chat | $3 | / 1M billed tokens |
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | Fast, cheap, very long context | chat | $3 | / 1M billed tokens |
| gemini-2.5-flash-imagegoogle/gemini-2.5-flash-image | Evaluate for chat workloads using the documented endpoint | chat | $3 | / 1M billed tokens |
| Qwen3-235B-A22B-Thinking-2507Qwen/Qwen3-235B-A22B-Thinking-2507 | Evaluate for chat workloads using the documented endpoint | chat | $2.99 | / 1M billed tokens |
| Kimi-K2-Instructmoonshotai/Kimi-K2-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $2.99 | / 1M billed tokens |
| Kimi-K2.5moonshotai/Kimi-K2.5 | Evaluate for chat workloads using the documented endpoint | chat | $2.925 | / 1M billed tokens |
| DeepSeek R1 0528deepseek-ai/DeepSeek-R1-0528 | Open reasoning workloads | chat | $2.795 | / 1M billed tokens |
| GLM-5zai-org/GLM-5 | Evaluate for chat workloads using the documented endpoint | chat | $2.704 | / 1M billed tokens |
| GLM 4.6zai-org/GLM-4.6 | Coding & agents with strong price/performance | chat | $2.6 | / 1M billed tokens |
| MiMo-V2.5XiaomiMiMo/MiMo-V2.5 | Evaluate for chat workloads using the documented endpoint | chat | $2.6 | / 1M billed tokens |
| Qwen3-VL-235B-A22B-InstructQwen/Qwen3-VL-235B-A22B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $2.47 | / 1M billed tokens |
| gpt-5-miniopenai/gpt-5-mini | Evaluate for chat workloads using the documented endpoint | chat | $2.4 | / 1M billed tokens |
| gpt-5.1-codex-miniopenai/gpt-5.1-codex-mini | Evaluate for chat workloads using the documented endpoint | chat | $2.4 | / 1M billed tokens |
| Qwen3-235B-A22BQwen/Qwen3-235B-A22B | Evaluate for chat workloads using the documented endpoint | chat | $2.366 | / 1M billed tokens |
| GLM-4.7zai-org/GLM-4.7 | Evaluate for chat workloads using the documented endpoint | chat | $2.275 | / 1M billed tokens |
| gpt-4.1-miniopenai/gpt-4.1-mini | Evaluate for chat workloads using the documented endpoint | chat | $1.92 | / 1M billed tokens |
| gemini-3.1-flash-litegoogle/gemini-3.1-flash-lite | Evaluate for chat workloads using the documented endpoint | chat | $1.8 | / 1M billed tokens |
| Qwen3.5-35B-A3BQwen/Qwen3.5-35B-A3B | Evaluate for chat workloads using the documented endpoint | chat | $1.625 | / 1M billed tokens |
| Muse-Glimmer-30Bmeta-models/Muse-Glimmer-30B | Evaluate for chat workloads using the documented endpoint | chat | $1.56 | / 1M billed tokens |
| MiniMax-M2.7-TurboMiniMaxAI/MiniMax-M2.7-Turbo | Evaluate for chat workloads using the documented endpoint | chat | $1.56 | / 1M billed tokens |
| Inkling-Smallthinkingmachines/Inkling-Small | Evaluate for chat workloads using the documented endpoint | chat | $1.56 | / 1M billed tokens |
| MiniMax-M2.7MiniMaxAI/MiniMax-M2.7 | Evaluate for chat workloads using the documented endpoint | chat | $1.56 | / 1M billed tokens |
| MiniMax-M3MiniMaxAI/MiniMax-M3 | Evaluate for chat workloads using the documented endpoint | chat | $1.56 | / 1M billed tokens |
| gpt-5.4-nanoopenai/gpt-5.4-nano | Evaluate for chat workloads using the documented endpoint | chat | $1.5 | / 1M billed tokens |
| Step-3.7-Flashstepfun-ai/Step-3.7-Flash | Evaluate for chat workloads using the documented endpoint | chat | $1.495 | / 1M billed tokens |
| MiniMax-M2.5MiniMaxAI/MiniMax-M2.5 | Evaluate for chat workloads using the documented endpoint | chat | $1.495 | / 1M billed tokens |
| gpt-5.6-luna-proopenai/gpt-5.6-luna-pro | Evaluate for chat workloads using the documented endpoint | chat | $1.44 | / 1M billed tokens |
| gpt-5.6-lunaopenai/gpt-5.6-luna | Evaluate for chat workloads using the documented endpoint | chat | $1.44 | / 1M billed tokens |
| Qwen3-Next-80B-A3B-InstructQwen/Qwen3-Next-80B-A3B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $1.43 | / 1M billed tokens |
| GLM-4.5-Airzai-org/GLM-4.5-Air | Evaluate for chat workloads using the documented endpoint | chat | $1.43 | / 1M billed tokens |
| DeepSeek-V3.1-Terminusdeepseek-ai/DeepSeek-V3.1-Terminus | Evaluate for chat workloads using the documented endpoint | chat | $1.3 | / 1M billed tokens |
| Hermes-3-Llama-3.1-405BNousResearch/Hermes-3-Llama-3.1-405B | Evaluate for chat workloads using the documented endpoint | chat | $1.3 | / 1M billed tokens |
| Qwen3.6-35B-A3BQwen/Qwen3.6-35B-A3B | Evaluate for chat workloads using the documented endpoint | chat | $1.235 | / 1M billed tokens |
| DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1 | Evaluate for chat workloads using the documented endpoint | chat | $1.235 | / 1M billed tokens |
| Qwen3-14BQwen/Qwen3-14B | Evaluate for chat workloads using the documented endpoint | chat | $1.183 | / 1M billed tokens |
| Qwen3-235B-A22B-Instruct-2507Qwen/Qwen3-235B-A22B-Instruct-2507 | Evaluate for chat workloads using the documented endpoint | chat | $1.144 | / 1M billed tokens |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoningnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | Evaluate for chat workloads using the documented endpoint | chat | $1.04 | / 1M billed tokens |
| Hermes-3-Llama-3.1-70BNousResearch/Hermes-3-Llama-3.1-70B | Evaluate for chat workloads using the documented endpoint | chat | $0.91 | / 1M billed tokens |
| gpt-oss-120b-Turboopenai/gpt-oss-120b-Turbo | Evaluate for chat workloads using the documented endpoint | chat | $0.78 | / 1M billed tokens |
| Qwen3-VL-30B-A3B-InstructQwen/Qwen3-VL-30B-A3B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $0.78 | / 1M billed tokens |
| GPT OSS 120Bopenai/gpt-oss-120b | Open general-purpose reasoning | chat | $0.78 | / 1M billed tokens |
| gpt-4o-miniopenai/gpt-4o-mini | Evaluate for chat workloads using the documented endpoint | chat | $0.72 | / 1M billed tokens |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash | Evaluate for chat workloads using the documented endpoint | chat | $0.65 | / 1M billed tokens |
| Qwen3-30B-A3BQwen/Qwen3-30B-A3B | Evaluate for chat workloads using the documented endpoint | chat | $0.65 | / 1M billed tokens |
| gemma-3-27b-itgoogle/gemma-3-27b-it | Evaluate for chat workloads using the documented endpoint | chat | $0.585 | / 1M billed tokens |
| DeepSeek V3.2deepseek-ai/DeepSeek-V3.2 | Strong open-model coding at very low cost | chat | $0.533 | / 1M billed tokens |
| Qwen2.5-72B-InstructQwen/Qwen2.5-72B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $0.52 | / 1M billed tokens |
| Llama-3.3-Nemotron-Super-49B-v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | Evaluate for chat workloads using the documented endpoint | chat | $0.52 | / 1M billed tokens |
| GLM-4.7-Flashzai-org/GLM-4.7-Flash | Evaluate for chat workloads using the documented endpoint | chat | $0.52 | / 1M billed tokens |
| gpt-5-nanoopenai/gpt-5-nano | Evaluate for chat workloads using the documented endpoint | chat | $0.48 | / 1M billed tokens |
| gpt-4.1-nanoopenai/gpt-4.1-nano | Evaluate for chat workloads using the documented endpoint | chat | $0.48 | / 1M billed tokens |
| gemini-2.5-flash-litegoogle/gemini-2.5-flash-lite | Evaluate for chat workloads using the documented endpoint | chat | $0.48 | / 1M billed tokens |
| Llama-3.2-11B-Vision-Instructmeta-llama/Llama-3.2-11B-Vision-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $0.4485 | / 1M billed tokens |
| gemma-4-31B-itgoogle/gemma-4-31B-it | Evaluate for chat workloads using the documented endpoint | chat | $0.442 | / 1M billed tokens |
| gemma-4-26B-A4B-itgoogle/gemma-4-26B-A4B-it | Evaluate for chat workloads using the documented endpoint | chat | $0.442 | / 1M billed tokens |
| gemma-4-31B-it-turbogoogle/gemma-4-31B-it-turbo | Evaluate for chat workloads using the documented endpoint | chat | $0.442 | / 1M billed tokens |
| Llama-3.2-3B-Instructmeta-llama/Llama-3.2-3B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $0.429 | / 1M billed tokens |
| Llama 3.3 70B Instruct Turbometa-llama/Llama-3.3-70B-Instruct-Turbo | Open general-purpose workhorse | chat | $0.416 | / 1M billed tokens |
| gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b | Evaluate for chat workloads using the documented endpoint | chat | $0.39 | / 1M billed tokens |
| Qwen3-32BQwen/Qwen3-32B | Evaluate for chat workloads using the documented endpoint | chat | $0.364 | / 1M billed tokens |
| Nemotron-3-Nano-30B-A3Bnvidia/Nemotron-3-Nano-30B-A3B | Evaluate for chat workloads using the documented endpoint | chat | $0.26 | / 1M billed tokens |
| Qwen2.5-7B-InstructQwen/Qwen2.5-7B-Instruct | Evaluate for chat workloads using the documented endpoint | chat | $0.26 | / 1M billed tokens |
| Llama-Guard-4-12Bmeta-llama/Llama-Guard-4-12B | Evaluate for chat workloads using the documented endpoint | chat | $0.234 | / 1M billed tokens |
| DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash | Fast general and coding workloads | chat | $0.234 | / 1M billed tokens |
| DeepSeek-V4-Flash-0731deepseek-ai/DeepSeek-V4-Flash-0731 | Evaluate for chat workloads using the documented endpoint | chat | $0.234 | / 1M billed tokens |
| gemma-3-12b-itgoogle/gemma-3-12b-it | Evaluate for chat workloads using the documented endpoint | chat | $0.195 | / 1M billed tokens |
| Qwen3.5-9BQwen/Qwen3.5-9B | Evaluate for chat workloads using the documented endpoint | chat | $0.195 | / 1M billed tokens |
| phi-4microsoft/phi-4 | Evaluate for chat workloads using the documented endpoint | chat | $0.182 | / 1M billed tokens |
| gpt-oss-20bopenai/gpt-oss-20b | Evaluate for chat workloads using the documented endpoint | chat | $0.182 | / 1M billed tokens |
| MythoMax-L2-13bGryphe/MythoMax-L2-13b | Evaluate for chat workloads using the documented endpoint | chat | $0.169 | / 1M billed tokens |
| gemma-3-4b-itgoogle/gemma-3-4b-it | Evaluate for chat workloads using the documented endpoint | chat | $0.13 | / 1M billed tokens |
| Mistral-Small-24B-Instruct-2501mistralai/Mistral-Small-24B-Instruct-2501 | Evaluate for chat workloads using the documented endpoint | chat | $0.104 | / 1M billed tokens |
| Qwen3-Embedding-4BQwen/Qwen3-Embedding-4B | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.02 | / 1M billed tokens |
| llama-nemotron-embed-vl-1b-v2nvidia/llama-nemotron-embed-vl-1b-v2 | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.01 | / 1M billed tokens |
| multilingual-e5-large-instructintfloat/multilingual-e5-large-instruct | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.01 | / 1M billed tokens |
| Qwen3-Embedding-8BQwen/Qwen3-Embedding-8B | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.01 | / 1M billed tokens |
| bge-m3BAAI/bge-m3 | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.01 | / 1M billed tokens |
| BGE Large EN v1.5BAAI/bge-large-en-v1.5 | General-purpose retrieval embeddings | embeddings | $0.01 | / 1M billed tokens |
| Qwen3-Embedding-0.6BQwen/Qwen3-Embedding-0.6B | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.01 | / 1M billed tokens |
| embeddinggemma-300mgoogle/embeddinggemma-300m | Evaluate for embeddings workloads using the documented endpoint | embeddings | $0.002 | / 1M billed tokens |
| gemini-3-pro-imagegoogle/gemini-3-pro-image | Evaluate for image workloads using the documented endpoint | image | $0.134 | / image |
| FLUX-2-maxblack-forest-labs/FLUX-2-max | Evaluate for image workloads using the documented endpoint | image | $0.1 | / image |
| Qwen-Image-MaxQwen/Qwen-Image-Max | Evaluate for image workloads using the documented endpoint | image | $0.075 | / image |
| FLUX 1.1 Problack-forest-labs/FLUX-1.1-pro | High-fidelity image generation | image | $0.04 | / image |
| Seedream-4.5ByteDance/Seedream-4.5 | Evaluate for image workloads using the documented endpoint | image | $0.04 | / image |
| Seedream-4ByteDance/Seedream-4 | Evaluate for image workloads using the documented endpoint | image | $0.04 | / image |
| Qwen-Image-EditQwen/Qwen-Image-Edit | Evaluate for image workloads using the documented endpoint | image | $0.025 | / image |
| FLUX-2-klein-9bblack-forest-labs/FLUX-2-klein-9b | Evaluate for image workloads using the documented endpoint | image | $0.015 | / image |
| FLUX-2-problack-forest-labs/FLUX-2-pro | Evaluate for image workloads using the documented endpoint | image | $0.015 | / image |
| FLUX.1-Kontext-devblack-forest-labs/FLUX.1-Kontext-dev | Evaluate for image workloads using the documented endpoint | image | $0.01 | / image |
| FLUX-2-devblack-forest-labs/FLUX-2-dev | Evaluate for image workloads using the documented endpoint | image | $0.01 | / image |
| FLUX-1-devblack-forest-labs/FLUX-1-dev | Evaluate for image workloads using the documented endpoint | image | $0.009 | / image |
| FLUX-1-schnellblack-forest-labs/FLUX-1-schnell | Evaluate for image workloads using the documented endpoint | image | $0.0005 | / image |
| sdxl-turbostabilityai/sdxl-turbo | Evaluate for image workloads using the documented endpoint | image | $0.0002 | / image |
| Qwen3-TTSQwen/Qwen3-TTS | Evaluate for tts workloads using the documented endpoint | tts | $20 | / 1M billed tokens |
| HiggsAudioV2.5bosonai/HiggsAudioV2.5 | Evaluate for tts workloads using the documented endpoint | tts | $20 | / 1M billed tokens |
| csm-1bsesame/csm-1b | Evaluate for tts workloads using the documented endpoint | tts | $7 | / 1M billed tokens |
| orpheus-3b-0.1-ftcanopylabs/orpheus-3b-0.1-ft | Evaluate for tts workloads using the documented endpoint | tts | $7 | / 1M billed tokens |
| chatterbox-multilingualResembleAI/chatterbox-multilingual | Evaluate for tts workloads using the documented endpoint | tts | $1 | / 1M billed tokens |
| Kokoro 82Mhexgrad/Kokoro-82M | Natural, low-cost text-to-speech | tts | $0.62 | / 1M billed tokens |
Choose with confidenceMatch the model
Match the model
to the workload.
Start from the outcome you need, then balance quality, context, latency and unit economics. AIx keeps the integration consistent when your model choice changes.
01 / BUILD
Coding & agents
Models selected for code generation, repository reasoning, tools and multi-step execution.
Build a coding agent →02 / REASONLong context
Understand context windows, output limits and cost before sending large documents.
Plan token usage →03 / CREATEImages & media
Generate visual assets, speech and transcripts with modality-specific endpoints.
Explore media APIs →04 / RETRIEVESearch & RAG
Create semantic search, retrieval pipelines and durable memory with embedding models.
Build retrieval →Model API FAQEverything you need
Everything you need
to choose and ship.
How do I call an AI model on AIx?+
Create one AIx API key, use the OpenAI-compatible base URL and send the canonical model id in your request.
Does every model use the same API key?+
Yes. The same scoped AIx key and prepaid balance work across supported chat, image, speech, transcription and embedding models.
How is AI model pricing calculated?+
Chat and embedding models are metered by tokens, image models per generated image and transcription models per minute. The live catalog is the pricing source of truth.