Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
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.
No provider description is available for this model yet.
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
No provider description is available for this model yet.
No provider description is available for this model yet.
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
No provider description is available for this model yet.
No provider description is available for this model yet.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
No provider description is available for this model yet.
No provider description is available for this model yet.
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
No provider description is available for this model yet.
No provider description is available for this model yet.
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
No provider description is available for this model yet.
No provider description is available for this model yet.
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
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.
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
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.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905 | Moonshot AI |
262.144K | $0.6 | $2.5 | — | ||
| us-east-1/anthropic.claude-v1bedrock/us-east-1/anthropic.claude-v1 | 100K | $8 | $24 | — | |||
| global.xai.grok-4.6bedrock_converse/global.xai.grok-4.6 | 500K | $2 | $6 | — | |||
| DeepSeek: R1 0528deepseek/deepseek-r1-0528 | DeepSeek |
163.84K | $0.5 | $2.15 | — | ||
| us.xai.grok-4.6bedrock_converse/us.xai.grok-4.6 | 500K | $2.2 | $6.6 | — | |||
| us-east-1/anthropic.claude-instant-v1bedrock/us-east-1/anthropic.claude-instant-v1 | 100K | $0.8 | $2.4 | — | |||
| Baidu: ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47b | 123K | $0.42 | $1.25 | — | |||
| Morph: Morph V3 Fastmorph/morph-v3-fast | Morph |
81.92K | $0.8 | $1.2 | — | ||
| us-gov-west-1/amazon.nova-micro-v1:0bedrock/us-gov-west-1/amazon.nova-micro-v1:0 | 128K | $0.042 | $0.168 | — | |||
| us-gov-west-1/amazon.nova-lite-v1:0bedrock/us-gov-west-1/amazon.nova-lite-v1:0 | 300K | $0.072 | $0.288 | — | |||
| Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Alibaba Qwen |
262.144K | $0.087 | $0.35 | — | ||
| llama3.1ollama/llama3.1 | 8.192K | — | — | — | |||
| us-east-1/6-month-commitment/anthropic.claude-v2:1bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | 100K | — | — | — | |||
| Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | Alibaba Qwen |
262.144K | $0.07 | $0.28 | — | ||
| Z.ai: GLM 4.5z-ai/glm-4.5 | Z Ai |
131.072K | $0.6 | $2.2 | — | ||
| inclusionAI: Ling-2.6-1Tinclusionai/ling-2.6-1t | 262.144K | $0.075 | $0.625 | — | |||
| xai.grok-4.6bedrock_mantle/xai.grok-4.6 | 500K | $2.2 | $6.6 | — | |||
| deepseek/deepseek-v4-pro-0813openrouter/deepseek/deepseek-v4-pro-0813 | Openrouter |
1.04858M | $1.32 | $3.96 | — | ||
| Qwen: Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking | Alibaba Qwen |
131.072K | $0.18 | $2.1 | — | ||
| us-east-1/6-month-commitment/anthropic.claude-v1bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | 100K | — | — | — | |||
| deepseek/deepseek-v4-proopenrouter/deepseek/deepseek-v4-pro | Openrouter |
1.04858M | $1.32 | $3.96 | — | ||
| Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic |
200K | $1 | $5 | — | ||
| OpenAI: gpt-oss-20b (free)openai/gpt-oss-20b:free | OpenAI |
131.072K | Free | Free | — | ||
| anthropic/claude-opus-5openrouter/anthropic/claude-opus-5 | Openrouter |
1M | $5 | $25 | — | ||
| glm-5-2mistral/glm-5-2 | Mistral |
1.04858M | $1.4 | $4.4 | — | ||
| Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Alibaba Qwen |
262.144K | $0.09 | $1.1 | — | ||
| zai-glm-5-2mistral/zai-glm-5-2 | Mistral |
1.04858M | $1.4 | $4.4 | — | ||
| chat-latestopenai/chat-latest | OpenAI |
400K | $5 | $30 | — | ||
| IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro | IBM |
131K | $0.017 | $0.112 | — | ||
| DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek |
163.84K | $0.25 | $0.95 | — | ||
| SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1 | xAI |
256K | $1 | $2 | — | ||
| Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct | Meta |
131.072K | $0.05 | $0.33 | — | ||
| us-east-1/6-month-commitment/anthropic.claude-instant-v1bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | 100K | — | — | — | |||
| us-east-1/1-month-commitment/anthropic.claude-v2:1bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | 100K | — | — | — | |||
| NVIDIA: Nemotron Nano 12B 2 VL (free)nvidia/nemotron-nano-12b-v2-vl:free | NVIDIA |
128K | Free | Free | — | ||
| daybreak-blue-latestopenai/daybreak-blue-latest | OpenAI |
1.05M | $5 | $30 | — | ||
| daybreak-red-latestopenai/daybreak-red-latest | OpenAI |
400K | $12.5 | $75 | — | ||
| Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507 | Mistral AI |
32.768K | $0.1 | $0.3 | — | ||
| Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking | Alibaba Qwen |
131.072K | $0.2 | $2.4 | — | ||
| @cf/nvidia/nemotron-3-120b-a12bcloudflare/@cf/nvidia/nemotron-3-120b-a12b | Cloudflare |
256K | $0.5 | $1.5 | — | ||
| us-east-1/1-month-commitment/anthropic.claude-v1bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | 100K | — | — | — | |||
| global.openai.gpt-5.6-solbedrock_converse/global.openai.gpt-5.6-sol | 1M | $5 | $30 | — | |||
| deepseek-ai/ESFT-gate-intent-litedeepseek-ai/ESFT-gate-intent-lite | DeepSeek |
Not documented | — | — | — | ||
| us-east-1/1-month-commitment/anthropic.claude-instant-v1bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | 100K | — | — | — | |||
| Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic |
200K | $5 | $25 | — | ||
| us-gov-west-1/amazon.titan-text-premier-v1:0bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0 | 42K | $0.5 | $1.5 | — | |||
| nvidia/Cosmos3-Super-Text2Image-4Stepnvidia/Cosmos3-Super-Text2Image-4Step | NVIDIA |
Not documented | — | — | — | ||
| us.openai.gpt-5.6-terrabedrock_converse/us.openai.gpt-5.6-terra | 1M | $2.2 | $13.2 | — | |||
| deepseek-v4-flashdashscope/deepseek-v4-flash | 1M | $0.2 | $0.4 | — | |||
| OpenAI: gpt-oss-120b (free)openai/gpt-oss-120b:free | OpenAI |
131.072K | Free | Free | — |