No provider description is available for this model yet.
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
No provider description is available for this model yet.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
No provider description is available for this model yet.
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the DeepSeek V4 Flash family.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
This model always redirects to the latest model in the OpenAI GPT Astra family.
No provider description is available for this model yet.
This model always redirects to the latest model in the OpenAI GPT Sol family.
No provider description is available for this model yet.
No provider description is available for this model yet.
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...
No provider description is available for this model yet.
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| us-east-1/moonshotai.kimi-k2-thinkingbedrock/us-east-1/moonshotai.kimi-k2-thinking | 262.144K | $0.6 | $2.5 | — | |||
| us-gov-east-1/openai.gpt-oss-120bbedrock_mantle/us-gov-east-1/openai.gpt-oss-120b | 131.072K | $0.18 | $0.72 | — | |||
| Tencent: Hy3 (free)tencent/hy3:free | Tencent |
262.144K | Free | Free | — | ||
| us-east-1/qwen.qwen3-coder-nextbedrock/us-east-1/qwen.qwen3-coder-next | 262.144K | $0.5 | $1.2 | — | |||
| us-gov-east-1/openai.gpt-oss-20bbedrock_mantle/us-gov-east-1/openai.gpt-oss-20b | 131.072K | $0.084 | $0.36 | — | |||
| meta-llama/Meta-Llama-3-70B-Instructmeta-llama/Meta-Llama-3-70B-Instruct | Meta |
Not documented | — | — | — | ||
| grok-4.20-multi-agent-0309xai/grok-4.20-multi-agent-0309 | xAI |
1M | $1.25 | $2.5 | — | ||
| microsoft/Dayhoff-3b-GR-HM-1000microsoft/Dayhoff-3b-GR-HM-1000 | Microsoft |
Not documented | — | — | — | ||
| us-gov-east-1/xai.grok-4.6bedrock_mantle/us-gov-east-1/xai.grok-4.6 | 500K | $2.64 | $7.92 | — | |||
| nvidia/Nemotron-3-Labs-Ultra-Math-RLnvidia/Nemotron-3-Labs-Ultra-Math-RL | NVIDIA |
Not documented | — | — | — | ||
| Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking | Alibaba Qwen |
262.144K | $0.78 | $3.9 | — | ||
| meta-llama/Llama-4-Maverick-17B-128E-Instructmeta-llama/Llama-4-Maverick-17B-128E-Instruct | Meta |
Not documented | — | — | — | ||
| Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Alibaba Qwen |
256K | $0.312 | $1.25 | — | ||
| labs-leanstral-1-5mistral/labs-leanstral-1-5 | Mistral |
262.144K | — | — | — | ||
| meta-llama/Llama-4-Scout-17B-16E-Instructmeta-llama/Llama-4-Scout-17B-16E-Instruct | Meta |
Not documented | — | — | — | ||
| meta-llama/Llama-Guard-4-12Bmeta-llama/Llama-Guard-4-12B | Meta |
Not documented | — | — | — | ||
| Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5 | 256K | $0.15 | $0.6 | — | |||
| OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro | OpenAI |
1.05M | $0.2 | $1.2 | — | ||
| meta-llama/Llama-4-Scout-17B-16Emeta-llama/Llama-4-Scout-17B-16E | Meta |
Not documented | — | — | — | ||
| meta-llama/Llama-3.2-90B-Vision-Instructmeta-llama/Llama-3.2-90B-Vision-Instruct | Meta |
Not documented | — | — | — | ||
| DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest | Deepseek |
1.04858M | $0.04 | $0.08 | — | ||
| meta-llama/Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instruct | Meta |
Not documented | — | — | — | ||
| gpt-4ogithub_copilot/gpt-4o | Github_Copilot |
64K | — | — | — | ||
| us-east-2/deepseek.v3.2bedrock/us-east-2/deepseek.v3.2 | 163.84K | $0.62 | $1.85 | — | |||
| us-gov-west-1/openai.gpt-oss-120bbedrock_mantle/us-gov-west-1/openai.gpt-oss-120b | 131.072K | $0.18 | $0.72 | — | |||
| gpt-4o-2024-08-06github_copilot/gpt-4o-2024-08-06 | Github_Copilot |
64K | — | — | — | ||
| meta-llama/Llama-3.1-70B-Instructmeta-llama/Llama-3.1-70B-Instruct | Meta |
Not documented | — | — | — | ||
| meta-llama/Llama-3.2-11B-Vision-Instructmeta-llama/Llama-3.2-11B-Vision-Instruct | Meta |
Not documented | — | — | — | ||
| us-gov-west-1/openai.gpt-oss-20bbedrock_mantle/us-gov-west-1/openai.gpt-oss-20b | 131.072K | $0.084 | $0.36 | — | |||
| ap-south-1/moonshotai.kimi-k2-thinkingbedrock/ap-south-1/moonshotai.kimi-k2-thinking | 262.144K | $0.71 | $2.94 | — | |||
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-14B | DeepSeek |
Not documented | — | — | — | ||
| microsoft/Fara1.5-27Bmicrosoft/Fara1.5-27B | Microsoft |
Not documented | — | — | — | ||
| us-gov-west-1/google.gemma-4-31bbedrock_mantle/us-gov-west-1/google.gemma-4-31b | 256K | $0.168 | $0.48 | — | |||
| OpenAI GPT Astra Latest~openai/gpt-astra-latest | OpenAI |
1.05M | $10 | $50 | — | ||
| bigcode/deepseekcoder-33b-codeqwen-align-subsetbigcode/deepseekcoder-33b-codeqwen-align-subset | Not documented | — | — | — | |||
| OpenAI GPT Sol Latest~openai/gpt-sol-latest | OpenAI |
1.05M | $2 | $10 | — | ||
| us-gov-west-1/google.gemma-4-26b-a4bbedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b | 256K | $0.156 | $0.48 | — | |||
| ap-south-1/minimax.minimax-m2.5bedrock/ap-south-1/minimax.minimax-m2.5 | 1M | $0.36 | $1.44 | — | |||
| OpenAI: o1 (batch)openai/o1:batch | OpenAI |
200K | $7.5 | $30 | — | ||
| llama3.3-70bsnowflake/llama3.3-70b | 128K | $0.72 | $0.72 | — | |||
| Mistral Largemistralai/mistral-large | Mistral AI |
128K | $2 | $6 | — | ||
| meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8meta-llama/Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 | Meta |
Not documented | — | — | — | ||
| meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8meta-llama/Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8 | Meta |
Not documented | — | — | — | ||
| mistral-largesnowflake/mistral-large | 32K | — | — | — | |||
| us-gov-west-1/google.gemma-4-e2bbedrock_mantle/us-gov-west-1/google.gemma-4-e2b | 128K | $0.048 | $0.096 | — | |||
| deepseek-ai/DeepSeek-V4-Pro-0813deepseek-ai/DeepSeek-V4-Pro-0813 | DeepSeek |
Not documented | — | — | — | ||
| accounts/fireworks/routers/kimi-k3-usfireworks_ai/accounts/fireworks/routers/kimi-k3-us | Fireworks_Ai |
1.04858M | $3.3 | $16.5 | — | ||
| meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 | Meta |
Not documented | — | — | — | ||
| Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbo | 128K | $0.03 | $0.15 | — | |||
| us-gov-west-1/xai.grok-4.6bedrock_mantle/us-gov-west-1/xai.grok-4.6 | 500K | $2.64 | $7.92 | — |