Models
One name per model, however many providers serve it.
Thinking Machines: Inkling 2 Mini
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningInkling 2 Mini is an open-weight multimodal looped transformer from Thinking Machines Lab, with 3.4B active parameters out of 26.4B total (MoE).
thinkingmachines/inkling-2-miniNov 21, 20261M context27,328 Toman/M input tokens109,312 Toman/M output tokensRadixArk: DaisyRose 27B
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningDaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from Qwen3.8 27B using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation.
radixark/daisyrose-27bNov 21, 2026262K context54,656 Toman/M input tokens676,368 Toman/M output tokensPerplexity: Embed V2 Context 0.6B
Accepts- Text
Createspplx-embed-v2-context-0.6b is a compact multimodal contextual embedding model from Perplexity for retrieval over text, images, and visual documents.
perplexity/pplx-embed-v2-context-0.6bNov 20, 202632K context7,208 Toman/M tokensPerplexity: Embed V2 Context 9B
Accepts- Text
Createspplx-embed-v2-context-9b is a multimodal contextual embedding model from Perplexity for retrieval over text, images, and visual documents.
perplexity/pplx-embed-v2-context-9bNov 20, 202632K context43,247 Toman/M tokensQwen: Qwen3 TTS 1.7B
Accepts- Text
Creates- Audio
Qwen3 TTS is a multilingual text-to-speech model from Alibaba's Qwen team.
qwen/qwen3-tts-1.7bNov 20, 20264K context9 voicesMP3 · WAV7,208 Toman per 1,000 charactersGoogle: Gemini 2.5 Pro TTS
Accepts- Text
Creates- Audio
Gemini 2.5 Pro TTS is a text-to-speech model from Google.
google/gemini-2.5-pro-ttsNov 20, 20268K context30 voicesWAVabout 78,991 Toman per 1,000 charactersGoogle: Gemini 2.5 Flash TTS
Accepts- Text
Creates- Audio
Gemini 2.5 Flash TTS is a text-to-speech model from Google.
google/gemini-2.5-flash-ttsNov 20, 20268K context30 voicesWAVabout 39,495 Toman per 1,000 charactersMistral: Pixtral Large 2502
Accepts- Text
- Image
Creates- Text
Pixtral Large 2502 is the February 2025 version of Mistral AI's large multimodal model, following Pixtral Large 2411.
mistralai/pixtral-large-2502Nov 20, 2026128K context720,776 Toman/M input tokens2,162,328 Toman/M output tokensGoogle: Gemini 4 Neon
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
google/gemini-4-neonNov 18, 20261M context1,082,872 Toman/M input tokens5,407,528 Toman/M output tokensOpenAI: GPT-6.2 Astra Pro
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONReasoningGPT-6.2 Astra Pro is the same underlying model as GPT-6.2 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
openai/gpt-6.2-astra-proNov 17, 20261.1M context2,883,104 Toman/M input tokens14,415,520 Toman/M output tokensdearer above 272K tokensOpenAI: GPT-6.2 Astra
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONReasoningGPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.
openai/gpt-6.2-astraNov 17, 20261.1M context2,883,104 Toman/M input tokens14,415,520 Toman/M output tokensdearer above 272K tokensOpenAI: GPT-6.2 Sol Pro
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONReasoningGPT-6.2 Sol Pro is the same underlying model as GPT-6.2 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
openai/gpt-6.2-sol-proNov 17, 20261.1M context720,776 Toman/M input tokens3,603,880 Toman/M output tokensdearer above 272K tokensOpenAI: GPT-6.2 Sol
Accepts- Text
- Image
- File (PDF)
Creates- Text
ToolsJSONReasoningGPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.
openai/gpt-6.2-solNov 17, 20261.1M context720,776 Toman/M input tokens3,603,880 Toman/M output tokensdearer above 272K tokensMicrosoft AI: MAI-Image-2.7 Flash
Accepts- Text
- Image
Creates- Image
MAI-Image-2.7 Flash is the lower-latency, lower-cost member of the MAI-Image-2.7 family from Microsoft AI, built for latency-sensitive, high-throughput image generation and editing at comparable quality to the precision tier.
microsoft/mai-image-2.7-flashNov 17, 20264K contextEdits pictures4,685 Toman to 22,705 Toman an imageMicrosoft AI: MAI-Image-2.7
Accepts- Text
- Image
Creates- Image
MAI-Image-2.7 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.7 family alongside the faster MAI-Image-2.7 Flash.
microsoft/mai-image-2.7Nov 17, 20264K contextEdits pictures15,929 Toman to 77,195 Toman an imageByteDance: Seedance 2.5 Flash
Accepts- Text
- Image
Creates- Video
Seedance 2.5 Flash is a video generation model from ByteDance, the faster and lower-cost tier of Seedance 2.5.
bytedance/seedance-2.5-flashNov 17, 20264–30 s480p · 720pfrom 24,237 Toman/secondTencent: Hy4 flash
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningHy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost.
tencent/hy4-flashNov 16, 20261M context13,664 Toman/M input tokens51,240 Toman/M output tokensQwen: Qwen4 Max
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningQwen4 Max is the flagship model in Alibaba's Qwen4 series.
qwen/qwen4-maxNov 16, 20261M context515,816 Toman/M input tokens1,544,032 Toman/M output tokensRecraft: Recraft V4.1 Flash V2
Accepts- Text
Creates- Image
Recraft V4.1 Flash V2 is a text-to-image model from Recraft, an updated version of Recraft V4.1 Flash in the speed tier of the V4.1 family.
recraft/recraft-v4.1-flash-v2Nov 13, 202666K contextUp to 6 images a request2,523 Toman an imageTencent: HY-World 2.1 Panorama
Accepts- Text
Creates- Image
HY-World 2.1 Panorama is a 360-degree panorama generation model from Tencent, part of the Hunyuan World family.
tencent/hy-world-2.1-panoramaNov 13, 20264K context750 Toman to 3,633 Toman an imageinclusionAI: Ling 3.2 Flash (free)
FreeAccepts- Text
- Image
Creates- Text
ToolsJSONReasoningLing 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request.
inclusionai/ling-3.2-flash:freeNov 13, 20261M contextFreeByteDance Seed: Seedream 5.5
Accepts- Text
- Image
Creates- Image
Seedream 5.5 is an image generation and editing model from ByteDance Seed.
bytedance-seed/seedream-5-5Nov 12, 2026Edits pictures7,208 Toman to 12,614 Toman an imageGoogle: Gemini 4 Hydrogen
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than…
google/gemini-4-hydrogenNov 12, 20261M context543,144 Toman/M input tokens2,705,472 Toman/M output tokensSpeechify: Simba 3.5
Accepts- Text
Creates- Audio
Speechify's recommended streaming text-to-speech model, covering 48 languages including English under one model, with the language chosen per request.
speechify/simba-3.5Nov 11, 202620 voicesMP3 · WAV4,054 Toman per 1,000 charactersMiniMax: MiniMax H3 Image Highspeed
Accepts- Text
- Image
Creates- Image
MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 Image model.
minimax/minimax-h3-image-highspeedNov 11, 20264K contextUp to 10 images a requestEdits pictures3,561 Toman to 17,256 Toman an imageMiniMax: MiniMax H3 Image
Accepts- Text
- Image
Creates- Image
MiniMax H3 Image is MiniMax's image generation and editing model.
minimax/minimax-h3-imageNov 10, 20264K contextUp to 10 images a requestEdits pictures1,781 Toman to 8,628 Toman an imageBaidu: ERNIE-5.5-Flash-Preview (free)
FreeAccepts- Text
Creates- Text
ToolsJSONReasoningERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research.
baidu/ernie-5.5-flash-preview:freeNov 10, 20261M contextFreeBaidu: ERNIE-Light-DT-1.0
Accepts- Text
Creates- Text
ToolsJSONReasoningERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model.
baidu/ernie-light-dt-1.0-intlNov 10, 20261M context409,920 Toman/M input tokens1,421,056 Toman/M output tokensxAI: Grok STT 2.0
Accepts- Audio
Creates- Text
Grok STT 2.0 is a speech-to-text model from SpaceXSI and the successor to Grok STT 1.0.
x-ai/grok-stt-2.0Nov 10, 2026With segment and word times601 Toman a minute of audioGoogle: Gemini 4 Carbon
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.
google/gemini-4-carbonNov 10, 20261M context720,776 Toman/M input tokens3,603,880 Toman/M output tokens
581 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

