Chat models
If you’re not sure which chat model to use, check out our recommended models doc for which models to use for what use cases.| Organization | Model Name | API Model String | Context length | Input pricing (per 1M tokens) | Output pricing (per 1M tokens) | Quantization | Function Calling | Structured Outputs |
|---|---|---|---|---|---|---|---|---|
| Minimax | Minimax M2.5 | MiniMaxAI/MiniMax-M2.5 | 228700 | $0.30 | $1.20 | FP4 | Yes | Yes |
| Qwen | Qwen3.5 397B A17B | Qwen/Qwen3.5-397B-A17B | 262144 | $0.60 | $3.60 | BF16 | Yes | Yes |
| Moonshot | Kimi K2.5 | moonshotai/Kimi-K2.5 | 262144 | $0.50 | $2.80 | INT4 | Yes | Yes |
| Z.ai | GLM-5 | zai-org/GLM-5 | 202752 | $1.00 | $3.20 | FP4 | Yes | Yes |
| OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 128000 | $0.15 | $0.60 | MXFP4 | Yes | Yes |
| OpenAI | GPT-OSS 20B | openai/gpt-oss-20b | 128000 | $0.05 | $0.20 | MXFP4 | Yes | Yes |
| DeepSeek | DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.1 | 128000 | $0.60 | $1.70 | FP8 | Yes | Yes |
| Moonshot | Kimi K2 Instruct 0905 | moonshotai/Kimi-K2-Instruct-0905 | 262144 | $1.00 | $3.00 | FP8 | Yes | Yes |
| Moonshot | Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 262144 | $1.20 | $4.00 | INT4 | Yes | Yes |
| Z.ai | GLM 4.7 | zai-org/GLM-4.7 | 202752 | $0.45 | $2.00 | FP8 | Yes | Yes |
| Z.ai | GLM 4.5 Air | zai-org/GLM-4.5-Air-FP8 | 131072 | $0.20 | $1.10 | FP8 | Yes | Yes |
| Qwen | Qwen3-Coder-Next | Qwen/Qwen3-Coder-Next-FP8 | 262144 | $0.50 | $1.20 | FP8 | Yes | Yes |
| Qwen | Qwen3-Next-80B-A3B-Instruct | Qwen/Qwen3-Next-80B-A3B-Instruct | 262144 | $0.15 | $1.50 | BF16 | Yes | Yes |
| Qwen | Qwen3 235B-A22B Thinking 2507 | Qwen/Qwen3-235B-A22B-Thinking-2507 | 262144 | $0.65 | $3.00 | FP8 | Yes | Yes |
| Qwen | Qwen3-Coder 480B-A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | 256000 | $2.00 | $2.00 | FP8 | Yes | Yes |
| Qwen | Qwen3 235B-A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507-tput | 262144 | $0.20 | $0.60 | FP8 | Yes | Yes |
| DeepSeek | DeepSeek-R1-0528 | deepseek-ai/DeepSeek-R1 | 163839 | $3.00 | $7.00 | FP8 | Yes | Yes |
| Meta | Llama 4 Maverick (17Bx128E) | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1048576 | $0.27 | $0.85 | FP8 | Yes | Yes |
| Meta | Llama 3.3 70B Instruct Turbo | meta-llama/Llama-3.3-70B-Instruct-Turbo | 131072 | $0.88 | $0.88 | FP8 | Yes | Yes |
| Deep Cogito | Cogito v2.1 671B | deepcogito/cogito-v2-1-671b | 32768 | $1.25 | $1.25 | FP8 | - | Yes |
| Essential AI | Rnj-1 Instruct | essentialai/rnj-1-instruct | 32768 | $0.15 | $0.15 | BF16 | Yes | Yes |
| Mistral AI | Mistral Small 3 Instruct (24B) | mistralai/Mistral-Small-24B-Instruct-2501 | 32768 | $0.10 | $0.30 | FP16 | Yes | Yes |
| Meta | Llama 3.1 8B Instruct Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 131072 | $0.18 | $0.18 | FP8 | Yes | Yes |
| Qwen | Qwen 2.5 7B Instruct Turbo | Qwen/Qwen2.5-7B-Instruct-Turbo | 32768 | $0.30 | $0.30 | FP8 | Yes | Yes |
| Arcee | Arcee AI Trinity Mini | arcee-ai/trinity-mini | 32768 | $0.045 | $0.15 | - | Yes | Yes |
| Meta | Llama 3.2 3B Instruct Turbo | meta-llama/Llama-3.2-3B-Instruct-Turbo | 131072 | $0.06 | $0.06 | FP16 | Yes | Yes |
| Meta | Llama 3 8B Instruct Lite | meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8192 | $0.10 | $0.10 | INT4 | - | Yes |
| Gemma Instruct (2B) | google/gemma-2b-it* | 8192 | $0.00 | $0.00 | FP16 | - | - | |
| Gemma 3N E4B Instruct | google/gemma-3n-E4B-it | 32768 | $0.02 | $0.04 | FP8 | - | Yes | |
| Mistral AI | Mistral (7B) Instruct v0.2 | mistralai/Mistral-7B-Instruct-v0.2 | 32768 | $0.20 | $0.20 | FP16 | Yes | Yes |
- PDF to Chat App - Chat with your PDFs (blogs, textbooks, papers)
- Open Deep Research Notebook - Generate long form reports using a single prompt
- RAG with Reasoning Models Notebook - RAG with DeepSeek-R1
- Fine-tuning Chat Models Notebook - Tune Language models for conversation
- Building Agents - Agent workflows with language models
Image models
Use our Images endpoint for Image Models.| Organization | Model Name | Model String for API | Default steps |
|---|---|---|---|
| Imagen 4.0 Preview | google/imagen-4.0-preview | - | |
| Imagen 4.0 Fast | google/imagen-4.0-fast | - | |
| Imagen 4.0 Ultra | google/imagen-4.0-ultra | - | |
| Flash Image 2.5 (Nano Banana) | google/flash-image-2.5 | - | |
| Gemini 3 Pro Image (Nano Banana 2) | google/gemini-3-pro-image | - | |
| Black Forest Labs | Flux.1 [schnell] (Turbo) | black-forest-labs/FLUX.1-schnell | 4 |
| Black Forest Labs | Flux1.1 [pro] | black-forest-labs/FLUX.1.1-pro | - |
| Black Forest Labs | Flux.1 Kontext [pro] | black-forest-labs/FLUX.1-kontext-pro | 28 |
| Black Forest Labs | Flux.1 Kontext [max] | black-forest-labs/FLUX.1-kontext-max | 28 |
| Black Forest Labs | FLUX.1 Krea [dev] | black-forest-labs/FLUX.1-krea-dev | 28 |
| Black Forest Labs | FLUX.2 [pro] | black-forest-labs/FLUX.2-pro | - |
| Black Forest Labs | FLUX.2 [dev] | black-forest-labs/FLUX.2-dev | - |
| Black Forest Labs | FLUX.2 [flex] | black-forest-labs/FLUX.2-flex | - |
| ByteDance | Seedream 3.0 | ByteDance-Seed/Seedream-3.0 | - |
| ByteDance | Seedream 4.0 | ByteDance-Seed/Seedream-4.0 | - |
| Qwen | Qwen Image | Qwen/Qwen-Image | - |
| RunDiffusion | Juggernaut Pro Flux | RunDiffusion/Juggernaut-pro-flux | - |
| RunDiffusion | Juggernaut Lightning Flux | Rundiffusion/Juggernaut-Lightning-Flux | - |
| HiDream | HiDream-I1-Full | HiDream-ai/HiDream-I1-Full | - |
| HiDream | HiDream-I1-Dev | HiDream-ai/HiDream-I1-Dev | - |
| HiDream | HiDream-I1-Fast | HiDream-ai/HiDream-I1-Fast | - |
| Ideogram | Ideogram 3.0 | ideogram/ideogram-3.0 | - |
| Lykon | Dreamshaper | Lykon/DreamShaper | - |
| Stability AI | Stable Diffusion 3 | stabilityai/stable-diffusion-3-medium | - |
| Stability AI | SD XL | stabilityai/stable-diffusion-xl-base-1.0 | - |
- Blinkshot.io - A realtime AI image playground built with Flux Schnell
- Logo Creator - An logo generator that creates professional logos in seconds using Flux Pro 1.1
- PicMenu - A menu visualizer that takes a restaurant menu and generates nice images for each dish.
- Flux LoRA Inference Notebook - Using LoRA fine-tuned image generations models
- Default pricing: The listed per megapixel prices are for the default number of steps.
- Using more or fewer steps: Costs are adjusted based on the number of steps used only if you go above the default steps. If you use more steps, the cost increases proportionally using the formula below. If you use fewer steps, the cost does not decrease and is based on the default rate.
- MP = (Width × Height ÷ 1,000,000)
- Price per MP = Cost for generating one megapixel at the default steps
- Steps = The number of steps used for the image generation. This is only factored in if going above default steps.
- 1080p and 2K: $0.134/image
- 4K resolution: $0.24 /image
Vision models
If you’re not sure which vision model to use, we currently recommend Llama 4 Maverick (meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8) to get started. For model specific rate limits, navigate here.
| Organization | Model Name | API Model String | Context length |
|---|---|---|---|
| Meta | Llama 4 Maverick (17Bx128E) | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 524288 |
| Qwen | Qwen3-VL-8B-Instruct | Qwen/Qwen3-VL-8B-Instruct | 262100 |
- LlamaOCR - A tool that takes documents (like receipts) and outputs markdown
- Wireframe to Code - A wireframe to app tool that takes in a UI mockup of a site and give you React code.
- Extracting Structured Data from Images - Extract information from images as JSON
Video models
| Organization | Model Name | Model String for API | Resolution / Duration |
|---|---|---|---|
| MiniMax | MiniMax 01 Director | minimax/video-01-director | 720p / 5s |
| MiniMax | MiniMax Hailuo 02 | minimax/hailuo-02 | 768p / 10s |
| Veo 2.0 | google/veo-2.0 | 720p / 5s | |
| Veo 3.0 | google/veo-3.0 | 720p / 8s | |
| Veo 3.0 + Audio | google/veo-3.0-audio | 720p / 8s | |
| Veo 3.0 Fast | google/veo-3.0-fast | 1080p / 8s | |
| Veo 3.0 Fast + Audio | google/veo-3.0-fast-audio | 1080p / 8s | |
| ByteDance | Seedance 1.0 Lite | ByteDance/Seedance-1.0-lite | 720p / 5s |
| ByteDance | Seedance 1.0 Pro | ByteDance/Seedance-1.0-pro | 1080p / 5s |
| PixVerse | PixVerse v5 | pixverse/pixverse-v5 | 1080p / 5s |
| Kuaishou | Kling 2.1 Master | kwaivgI/kling-2.1-master | 1080p / 5s |
| Kuaishou | Kling 2.1 Standard | kwaivgI/kling-2.1-standard | 720p / 5s |
| Kuaishou | Kling 2.1 Pro | kwaivgI/kling-2.1-pro | 1080p / 5s |
| Kuaishou | Kling 2.0 Master | kwaivgI/kling-2.0-master | 1080p / 5s |
| Kuaishou | Kling 1.6 Standard | kwaivgI/kling-1.6-standard | 720p / 5s |
| Kuaishou | Kling 1.6 Pro | kwaivgI/kling-1.6-pro | 1080p / 5s |
| Wan-AI | Wan 2.2 I2V | Wan-AI/Wan2.2-I2V-A14B | - |
| Wan-AI | Wan 2.2 T2V | Wan-AI/Wan2.2-T2V-A14B | - |
| Vidu | Vidu 2.0 | vidu/vidu-2.0 | 720p / 8s |
| Vidu | Vidu Q1 | vidu/vidu-q1 | 1080p / 5s |
| OpenAI | Sora 2 | openai/sora-2 | 720p / 8s |
| OpenAI | Sora 2 Pro | openai/sora-2-pro | 1080p / 8s |
Audio models
Use our Audio endpoint for text-to-speech models. For speech-to-text models see Transcription and Translations| Organization | Modality | Model Name | Model String for API |
|---|---|---|---|
| Canopy Labs | Text-to-Speech | Orpheus 3B | canopylabs/orpheus-3b-0.1-ft |
| Kokoro | Text-to-Speech | Kokoro | hexgrad/Kokoro-82M |
| Cartesia | Text-to-Speech | Cartesia Sonic 2 | cartesia/sonic-2 |
| Cartesia | Text-to-Speech | Cartesia Sonic | cartesia/sonic |
| OpenAI | Speech-to-Text | Whisper Large v3 | openai/whisper-large-v3 |
| Mistral AI | Speech-to-Text | Voxtral Mini 3B | mistralai/Voxtral-Mini-3B-2507 |
- PDF to Podcast Notebook - Generate a NotebookLM style podcast given a PDF
- Audio Podcast Agent Workflow - Agent workflow to generate audio files given input content
Embedding models
| Model Name | Model String for API | Model Size | Embedding Dimension | Context Window |
|---|---|---|---|---|
| Multilingual-e5-large-instruct | intfloat/multilingual-e5-large-instruct | 560M | 1024 | 514 |
- Contextual RAG - An open source implementation of contextual RAG by Anthropic
- Code Generation Agent - An agent workflow to generate and iteratively improve code
- Multimodal Search and Image Generation - Search for images and generate more similar ones
- Visualizing Embeddings - Visualizing and clustering vector embeddings
Rerank models
Our Rerank API has built-in support for the following models, that we host via our serverless endpoints.| Organization | Model Name | Model Size | Model String for API | Max Doc Size (tokens) | Max Docs |
|---|---|---|---|---|---|
| MixedBread | Rerank Large | 1.6B | mixedbread-ai/Mxbai-Rerank-Large-V2 | 32768 | - |
- Search and Reranking - Simple semantic search pipeline improved using a reranker
- Implementing Hybrid Search Notebook - Implementing semantic + lexical search along with reranking
Moderation models
Use our Completions endpoint to run a moderation model as a standalone classifier, or use it alongside any of the other models above as a filter to safeguard responses from 100+ models, by specifying the parameter"safety_model": "MODEL_API_STRING"
| Organization | Model Name | Model String for API | Context length |
|---|---|---|---|
| Meta | Llama Guard 4 (12B) | meta-llama/Llama-Guard-4-12B | 1048576 |
| Virtue AI | Virtue Guard | VirtueAI/VirtueGuard-Text-Lite | 32768 |