Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
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...
The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...
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.
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.
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.
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | Google |
262.144K | Free | Free | — | ||
| Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | Google |
262.144K | Free | Free | — | ||
| OpenAI: GPT-5 Image Miniopenai/gpt-5-image-mini | OpenAI |
400K | $2.5 | $2 | — | ||
| Z.ai: GLM 5 Turboz-ai/glm-5-turbo | Z Ai |
202.752K | $1.2 | $4 | — | ||
| Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Alibaba Qwen |
1M | $0.065 | $0.26 | — | ||
| Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Alibaba Qwen |
262.144K | $0.55 | $3.5 | — | ||
| MiniMax: MiniMax M2.5minimax/minimax-m2.5 | MiniMax |
200K | $0.27 | $1.08 | — | ||
| Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next | Alibaba Qwen |
262.144K | $0.12 | $0.8 | — | ||
| Free Models Routeropenrouter/free | Openrouter |
200K | Free | Free | — | ||
| Anthropic: Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic |
1M | $5 | $25 | — | ||
| NVIDIA: Nemotron 3 Nano 30B A3B (free)nvidia/nemotron-3-nano-30b-a3b:free | NVIDIA |
256K | Free | Free | — | ||
| Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512 | Mistral AI |
262.144K | $0.2 | $0.2 | — | ||
| Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic |
200K | $5 | $25 | — | ||
| OpenAI: GPT-4 Turbo Previewopenai/gpt-4-turbo-preview | OpenAI |
128K | $10 | $30 | — | ||
| deepseek-ai/DeepSeek-V4-Flashnebius/deepseek-ai/deepseek-v4-flash | Nebius |
1.04858M | $0.14 | $0.28 | — | ||
| deepseek-ai/DeepSeek-V4-Flash-0731nebius/deepseek-ai/deepseek-v4-flash-0731 | Nebius |
1.024M | $0.14 | $0.28 | — | ||
| deepseek-ai/DeepSeek-V4-Pronebius/deepseek-ai/deepseek-v4-pro | Nebius |
1.04858M | $1.75 | $3.5 | — | ||
| MiniMaxAI/MiniMax-M2.5nebius/minimaxai/minimax-m2.5 | Nebius |
196.608K | $0.3 | $1.2 | — | ||
| MiniMaxAI/MiniMax-M3nebius/minimaxai/minimax-m3 | Nebius |
1.04858M | $0.3 | $1.2 | — | ||
| moonshotai/Kimi-K2.6nebius/moonshotai/kimi-k2.6 | Nebius |
262.144K | $0.95 | $4 | — | ||
| moonshotai/Kimi-K2.7-Codenebius/moonshotai/kimi-k2.7-code | Nebius |
262.144K | $0.95 | $4 | — | ||
| moonshotai/Kimi-K3nebius/moonshotai/kimi-k3 | Nebius |
1.024M | $3 | $15 | — | ||
| NousResearch/Hermes-4-405Bnebius/nousresearch/hermes-4-405b | Nebius |
131.072K | $1 | $3 | — | ||
| NousResearch/Hermes-4-70Bnebius/nousresearch/hermes-4-70b | Nebius |
131.072K | $0.13 | $0.4 | — | ||
| nvidia/Cosmos3-Super-Reasonernebius/nvidia/cosmos3-super-reasoner | Nebius |
262.144K | $0.1 | $0.3 | — | ||
| nvidia/Llama-3_1-Nemotron-Ultra-253B-v1nebius/nvidia/llama-3_1-nemotron-ultra-253b-v1 | Nebius |
131.072K | $0.6 | $1.8 | — | ||
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3Bnebius/nvidia/nvidia-nemotron-3-nano-30b-a3b | Nebius |
262.144K | $0.06 | $0.24 | — | ||
| nvidia/Nemotron-3-Nano-Omninebius/nvidia/nemotron-3-nano-omni | Nebius |
262.144K | $0.06 | $0.24 | — | ||
| nvidia/nemotron-3-super-120b-a12bnebius/nvidia/nemotron-3-super-120b-a12b | Nebius |
262.144K | $0.3 | $0.9 | — | ||
| nvidia/Nemotron-3-Ultra-550b-a55bnebius/nvidia/nemotron-3-ultra-550b-a55b | Nebius |
1.04858M | $1 | $3 | — | ||
| nvidia/Nemotron-3_5-Lightningnebius/nvidia/nemotron-3_5-lightning | Nebius |
1.04858M | $0.06 | $0.24 | — | ||
| openai/gpt-oss-120bnebius/openai/gpt-oss-120b | Nebius |
131.072K | $0.15 | $0.6 | — | ||
| openbmb/MiniCPM-V-4_5nebius/openbmb/minicpm-v-4_5 | Nebius |
32K | $0.658 | $1.11 | — | ||
| Qwen/Qwen3-235B-A22B-Instruct-2507nebius/qwen/qwen3-235b-a22b-instruct-2507 | Nebius |
262.144K | $0.2 | $0.6 | — | ||
| Qwen/Qwen3-30B-A3B-Instruct-2507nebius/qwen/qwen3-30b-a3b-instruct-2507 | Nebius |
262.144K | $0.1 | $0.3 | — | ||
| Qwen/Qwen3-Next-80B-A3B-Thinkingnebius/qwen/qwen3-next-80b-a3b-thinking | Nebius |
128K | $0.15 | $1.2 | — | ||
| Qwen/Qwen3.5-397B-A17Bnebius/qwen/qwen3.5-397b-a17b | Nebius |
262.144K | $0.6 | $3.6 | — | ||
| zai-org/GLM-5.1nebius/zai-org/glm-5.1 | Nebius |
202.752K | $1.4 | $4.4 | — | ||
| zai-org/GLM-5.2nebius/zai-org/glm-5.2 | Nebius |
1.04858M | $1.4 | $4.4 | — | ||
| zai-org/GLM-5.3-Flashnebius/zai-org/glm-5.3-flash | Nebius |
1.024M | $0.15 | $0.5 | — | ||
| bigscience/mt0-xxlwatsonx/bigscience/mt0-xxl | Watsonx |
4.096K | $1.908 | $1.908 | — | ||
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | Watsonx |
131.072K | $0.371 | $1.484 | — | ||
| claude-mythos-5-1anthropic/claude-mythos-5-1 | Anthropic |
1M | $10 | $50 | — | ||
| accounts/fireworks/models/deepseek-v4-flash-vision-expfireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp | Fireworks_Ai |
1.04858M | $0.22 | $0.66 | — | ||
| deepseek-v4-flash-vision-expfireworks_ai/deepseek-v4-flash-vision-exp | Fireworks_Ai |
1.04858M | $0.22 | $0.66 | — | ||
| lyria-3.5-clip-previewgemini/lyria-3.5-clip-preview | 131.072K | — | — | — | |||
| lyria-3.5-pro-previewgemini/lyria-3.5-pro-preview | 131.072K | — | — | — | |||
| anthropic/claude-fable-5openrouter/anthropic/claude-fable-5 | Openrouter |
1M | $10 | $50 | — | ||
| OpenAI: GPT-4 Turbo (batch)openai/gpt-4-turbo:batch | OpenAI |
128K | $5 | $15 | — | ||
| anthropic/claude-fable-5.1openrouter/anthropic/claude-fable-5.1 | Openrouter |
1M | $10 | $50 | — |