Models

Explore the active model market,from a local OpenRouter snapshot.

This page reads from a local JSON snapshot synced from OpenRouter, so the catalog stays fast, indexable, and stable. Use it to browse current model coverage by provider, modality, reasoning support, context window, and pricing metadata.

Request a model on ImaRouter View source endpoint

Modality

Provider

Sort

Reasoning only

All (683)Audio (23)Embeddings (26)File (71)Image (226)Rerank (3)Text (683)TTS (2)Video (47)

Results

Showing 48 of 683 matching models

Snapshot source: OpenRouter. Synced April 21, 2026 at 8:00 AM. Page 5 of 15.

This route is built from local JSON so the catalog stays stable for browsing and SEO. If you need a specific model on ImaRouter, treat this page as a discovery reference and then contact the team for availability.

Text

Google AI Studio

Google: Gemma 3n 4B (free)

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)

Text

Context

8.2K

Group

Other

Pricing preview

Input Price: $0 /M tokens

Output Price: $0 /M tokens

Slug

google/gemma-3n-e4b-it

Text

Together

Google: Gemma 3n 4B

Text

Context

32.8K

Group

Other

Pricing preview

Input Price: $0.06 /M tokens

Output Price: $0.12 /M tokens

Slug

google/gemma-3n-e4b-it

Text

Unknown provider

Meta: Llama 3.3 8B Instruct

A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.

Text

Context

128K

Group

Llama3

Pricing preview

No display pricing published in the current snapshot.

Slug

meta-llama/llama-3.3-8b-instruct

TextReasoning

Unknown provider

Nous: DeepHermes 3 Mistral 24B Preview

DeepHermes 3 (Mistral 24B Preview) is an instruction-tuned language model by Nous Research based on Mistral-Small-24B, designed for chat, function calling, and advanced multi-turn reasoning. It introduces a dual-mode system that toggles between intuitive chat responses and structured “deep reasoning” mode using special system prompts. Fine-tuned via distillation from R1, it supports structured output (JSON mode) and function call syntax for agent-based applications. DeepHermes 3 supports a **reasoning toggle via system prompt**, allowing users to switch between fast, intuitive responses and deliberate, multi-step reasoning. When activated with the following specific system instruction, the model enters a *"deep thinking"* mode—generating extended chains of thought wrapped in `<think></think>` tags before delivering a final answer. System Prompt: You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

nousresearch/deephermes-3-mistral-24b-preview

Text

Mistral

Mistral: Mistral Medium 3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases. The model excels in domains such as coding, STEM reasoning, and enterprise adaptation. It supports hybrid, on-prem, and in-VPC deployments and is optimized for integration into custom workflows. Mistral Medium 3 offers competitive accuracy relative to larger models like Claude Sonnet 3.5/3.7, Llama 4 Maverick, and Command R+, while maintaining broad compatibility across cloud environments.

TextImage

Context

131.1K

Group

Mistral

Pricing preview

Input Price: $0.4 /M tokens

Output Price: $2 /M tokens

Slug

mistralai/mistral-medium-3

TextReasoning

Google Vertex

Google: Gemini 2.5 Pro Preview 05-06

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

TextImageFileAudioVideo

Context

Group

Gemini

Pricing preview

Input Price: $1.25 /M tokens

Output Price: $10 /M tokens

Slug

google/gemini-2.5-pro-preview-05-06

Text

Unknown provider

Arcee AI: Caller Large

Caller Large is Arcee's specialist "function‑calling" SLM built to orchestrate external tools and APIs. Instead of maximizing next‑token accuracy, training focuses on structured JSON outputs, parameter extraction and multi‑step tool chains, making Caller a natural choice for retrieval‑augmented generation, robotic process automation or data‑pull chatbots. It incorporates a routing head that decides when (and how) to invoke a tool versus answering directly, reducing hallucinated calls. The model is already the backbone of Arcee Conductor's auto‑tool mode, where it parses user intent, emits clean function signatures and hands control back once the tool response is ready. Developers thus gain an OpenAI‑style function‑calling UX without handing requests to a frontier‑scale model.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

arcee-ai/caller-large

Text

Together

Arcee AI: Spotlight

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal conversations that combine lengthy documents with one or more images. Training emphasized fast inference on consumer GPUs while retaining strong captioning, visual‐question‑answering, and diagram‑analysis accuracy. As a result, Spotlight slots neatly into agent workflows where screenshots, charts or UI mock‑ups need to be interpreted on the fly. Early benchmarks show it matching or out‑scoring larger VLMs such as LLaVA‑1.6 13 B on popular VQA and POPE alignment tests.

TextImage

Context

131.1K

Group

Other

Pricing preview

Input Price: $0.18 /M tokens

Output Price: $0.18 /M tokens

Slug

arcee-ai/spotlight

Text

Together

Arcee AI: Maestro Reasoning

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B preview, the production 32 B release widens the context window to 128 k tokens and doubles pass‑rate on MATH and GSM‑8K, while also lifting code completion accuracy. Its instruction style encourages structured "thought → answer" traces that can be parsed or hidden according to user preference. That transparency pairs well with audit‑focused industries like finance or healthcare where seeing the reasoning path matters. In Arcee Conductor, Maestro is automatically selected for complex, multi‑constraint queries that smaller SLMs bounce.

Text

Context

131.1K

Group

Other

Pricing preview

Input Price: $0.9 /M tokens

Output Price: $3.3 /M tokens

Slug

arcee-ai/maestro-reasoning

Text

Together

Arcee AI: Virtuoso Large

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k context inherited from Qwen 2.5, letting it ingest books, codebases or financial filings wholesale. Training blended DeepSeek R1 distillation, multi‑epoch supervised fine‑tuning and a final DPO/RLHF alignment stage, yielding strong performance on BIG‑Bench‑Hard, GSM‑8K and long‑context Needle‑In‑Haystack tests. Enterprises use Virtuoso‑Large as the "fallback" brain in Conductor pipelines when other SLMs flag low confidence. Despite its size, aggressive KV‑cache optimizations keep first‑token latency in the low‑second range on 8× H100 nodes, making it a practical production‑grade powerhouse.

Text

Context

131.1K

Group

Other

Pricing preview

Input Price: $0.75 /M tokens

Output Price: $1.2 /M tokens

Slug

arcee-ai/virtuoso-large

Text

Together

Arcee AI: Coder Large

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file refactoring or long diff review in a single call, and understands 30‑plus programming languages with special attention to TypeScript, Go and Terraform. Internal benchmarks show 5–8 pt gains over CodeLlama‑34 B‑Python on HumanEval and competitive BugFix scores thanks to a reinforcement pass that rewards compilable output. The model emits structured explanations alongside code blocks by default, making it suitable for educational tooling as well as production copilot scenarios. Cost‑wise, Together AI prices it well below proprietary incumbents, so teams can scale interactive coding without runaway spend.

Text

Context

32.8K

Group

Other

Pricing preview

Input Price: $0.5 /M tokens

Output Price: $0.8 /M tokens

Slug

arcee-ai/coder-large

Text

Unknown provider

Arcee AI: Virtuoso Medium V2

Virtuoso‑Medium‑v2 is a 32 B model distilled from DeepSeek‑v3 logits and merged back onto a Qwen 2.5 backbone, yielding a sharper, more factual successor to the original Virtuoso Medium. The team harvested ~1.1 B logit tokens and applied "fusion‑merging" plus DPO alignment, which pushed scores past Arcee‑Nova 2024 and many 40 B‑plus peers on MMLU‑Pro, MATH and HumanEval. With a 128 k context and aggressive quantization options (from BF16 down to 4‑bit GGUF), it balances capability with deployability on single‑GPU nodes. Typical use cases include enterprise chat assistants, technical writing aids and medium‑complexity code drafting where Virtuoso‑Large would be overkill.

Text

Context

131.1K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

arcee-ai/virtuoso-medium-v2

Text

Unknown provider

Arcee AI: Arcee Blitz

Arcee Blitz is a 24 B‑parameter dense model distilled from DeepSeek and built on Mistral architecture for "everyday" chat. The distillation‑plus‑refinement pipeline trims compute while keeping DeepSeek‑style reasoning, so Blitz punches above its weight on MMLU, GSM‑8K and BBH compared with other mid‑size open models. With a default 128 k context window and competitive throughput, it serves as a cost‑efficient workhorse for summarization, brainstorming and light code help. Internally, Arcee uses Blitz as the default writer in Conductor pipelines when the heavier Virtuoso line is not required. Users therefore get near‑70 B quality at ~⅓ the latency and price.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

arcee-ai/arcee-blitz

TextReasoning

Unknown provider

Microsoft: Phi 4 Reasoning Plus

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer. While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

microsoft/phi-4-reasoning-plus

TextReasoning

Unknown provider

Microsoft: Phi 4 Reasoning

Phi-4-reasoning is a 14B parameter dense decoder-only transformer developed by Microsoft, fine-tuned from Phi-4 to enhance complex reasoning capabilities. It uses a combination of supervised fine-tuning on chain-of-thought traces and reinforcement learning, targeting math, science, and code reasoning tasks. With a 32k context window and high inference efficiency, it is optimized for structured responses in a two-part format: reasoning trace followed by a final solution. The model achieves strong results on specialized benchmarks such as AIME, OmniMath, and LiveCodeBench, outperforming many larger models in structured reasoning tasks. It is released under the MIT license and intended for use in latency-constrained, English-only environments requiring reliable step-by-step logic. Recommended usage includes ChatML prompts and structured reasoning format for best results.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

microsoft/phi-4-reasoning

TextReasoning

Unknown provider

Qwen: Qwen3 0.6B

Qwen3-0.6B is a lightweight, 0.6 billion parameter language model in the Qwen3 series, offering support for both general-purpose dialogue and structured reasoning through a dual-mode (thinking/non-thinking) architecture. Despite its small size, it supports long contexts up to 32,768 tokens and provides multilingual, tool-use, and instruction-following capabilities.

Text

Context

32K

Group

Qwen3

Pricing preview

No display pricing published in the current snapshot.

Slug

qwen/qwen3-0.6b-04-28

Text

Unknown provider

Inception: Mercury Coder

Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality. Read more in the [blog post here](https://www.inceptionlabs.ai/blog/introducing-mercury).

Text

Context

128K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

inception/mercury-coder

TextReasoning

Unknown provider

Qwen: Qwen3 1.7B

Qwen3-1.7B is a compact, 1.7 billion parameter dense language model from the Qwen3 series, featuring dual-mode operation for both efficient dialogue (non-thinking) and advanced reasoning (thinking). Despite its small size, it supports 32,768-token contexts and delivers strong multilingual, instruction-following, and agentic capabilities, including tool use and structured output.

Text

Context

32K

Group

Qwen3

Pricing preview

No display pricing published in the current snapshot.

Slug

qwen/qwen3-1.7b

TextReasoning

Unknown provider

Qwen: Qwen3 4B

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

Text

Context

128K

Group

Qwen3

Pricing preview

No display pricing published in the current snapshot.

Slug

qwen/qwen3-4b

Text

Unknown provider

OpenGVLab: InternVL3 14B

The 14b version of the InternVL3 series. An advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.

TextImage

Context

32K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

opengvlab/internvl3-14b

Text

Unknown provider

OpenGVLab: InternVL3 2B

The 2b version of the InternVL3 series, for an even higher inference speed and very reasonable performance. An advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.

TextImage

Context

32K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

opengvlab/internvl3-2b

Text

Unknown provider

DeepSeek: DeepSeek Prover V2

DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from [DeepSeek-Prover-V1.5](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL) Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.

Text

Context

163.8K

Group

DeepSeek

Pricing preview

No display pricing published in the current snapshot.

Slug

deepseek/deepseek-prover-v2

Text

DeepInfra

Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM—generating text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated. Llama Guard 4 was aligned to safeguard against the standardized MLCommons hazards taxonomy and designed to support multimodal Llama 4 capabilities. Specifically, it combines features from previous Llama Guard models, providing content moderation for English and multiple supported languages, along with enhanced capabilities to handle mixed text-and-image prompts, including multiple images. Additionally, Llama Guard 4 is integrated into the Llama Moderations API, extending robust safety classification to text and images.

TextImage

Context

163.8K

Group

Other

Pricing preview

Input Price: $0.18 /M tokens

Output Price: $0.18 /M tokens

Slug

meta-llama/llama-guard-4-12b

TextReasoning

DeepInfra

Qwen: Qwen3 30B A3B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance. Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

Text

Context

41K

Group

Qwen3

Pricing preview

Input Price: $0.08 /M tokens

Output Price: $0.28 /M tokens

Slug

qwen/qwen3-30b-a3b

TextReasoning

AtlasCloud

Qwen: Qwen3 8B

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math, coding, and logical inference, and "non-thinking" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.

Text

Context

41K

Group

Qwen3

Pricing preview

Input Price: $0.05 /M tokens

Output Price: $0.4 /M tokens

Slug

qwen/qwen3-8b

TextReasoning

NextBit

Qwen: Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, programming, and logical inference, and a "non-thinking" mode for general-purpose conversation. The model is fine-tuned for instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Text

Context

41K

Group

Qwen3

Pricing preview

Input Price: $0.06 /M tokens

Output Price: $0.24 /M tokens

Slug

qwen/qwen3-14b

TextReasoning

Chutes

Qwen: Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Text

Context

41K

Group

Qwen3

Pricing preview

Input Price: $0.08 /M tokens

Output Price: $0.24 /M tokens

Slug

qwen/qwen3-32b

TextReasoning

Alibaba Cloud Int.

Qwen: Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

Text

Context

131.1K

Group

Qwen3

Pricing preview

Input Price: $0.455 /M tokens

Output Price: $1.82 /M tokens

Slug

qwen/qwen3-235b-a22b

TextReasoning

Unknown provider

TNG: DeepSeek R1T Chimera

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

Text

Context

163.8K

Group

DeepSeek

Pricing preview

No display pricing published in the current snapshot.

Slug

tngtech/deepseek-r1t-chimera

TextReasoning

Unknown provider

THUDM: GLM Z1 Rumination 32B

THUDM: GLM Z1 Rumination 32B is a 32B-parameter deep reasoning model from the GLM-4-Z1 series, optimized for complex, open-ended tasks requiring prolonged deliberation. It builds upon glm-4-32b-0414 with additional reinforcement learning phases and multi-stage alignment strategies, introducing “rumination” capabilities designed to emulate extended cognitive processing. This includes iterative reasoning, multi-hop analysis, and tool-augmented workflows such as search, retrieval, and citation-aware synthesis. The model excels in research-style writing, comparative analysis, and intricate question answering. It supports function calling for search and navigation primitives (`search`, `click`, `open`, `finish`), enabling use in agent-style pipelines. Rumination behavior is governed by multi-turn loops with rule-based reward shaping and delayed decision mechanisms, benchmarked against Deep Research frameworks such as OpenAI’s internal alignment stacks. This variant is suitable for scenarios requiring depth over speed.

Text

Context

32K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

thudm/glm-z1-rumination-32b

TextReasoning

Unknown provider

THUDM: GLM Z1 9B

GLM-Z1-9B-0414 is a 9B-parameter language model developed by THUDM as part of the GLM-4 family. It incorporates techniques originally applied to larger GLM-Z1 models, including extended reinforcement learning, pairwise ranking alignment, and training on reasoning-intensive tasks such as mathematics, code, and logic. Despite its smaller size, it demonstrates strong performance on general-purpose reasoning tasks and outperforms many open-source models in its weight class.

Text

Context

32K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

thudm/glm-z1-9b

Text

Unknown provider

THUDM: GLM 4 9B

GLM-4-9B-0414 is a 9 billion parameter language model from the GLM-4 series developed by THUDM. Trained using the same reinforcement learning and alignment strategies as its larger 32B counterparts, GLM-4-9B-0414 achieves high performance relative to its size, making it suitable for resource-constrained deployments that still require robust language understanding and generation capabilities.

Text

Context

32K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

thudm/glm-4-9b

TextReasoning

Unknown provider

Microsoft: MAI DS R1

MAI-DS-R1 is a post-trained variant of DeepSeek-R1 developed by the Microsoft AI team to improve the model’s responsiveness on previously blocked topics while enhancing its safety profile. Built on top of DeepSeek-R1’s reasoning foundation, it integrates 110k examples from the Tulu-3 SFT dataset and 350k internally curated multilingual safety-alignment samples. The model retains strong reasoning, coding, and problem-solving capabilities, while unblocking a wide range of prompts previously restricted in R1. MAI-DS-R1 demonstrates improved performance on harm mitigation benchmarks and maintains competitive results across general reasoning tasks. It surpasses R1-1776 in satisfaction metrics for blocked queries and reduces leakage in harmful content categories. The model is based on a transformer MoE architecture and is suitable for general-purpose use cases, excluding high-stakes domains such as legal, medical, or autonomous systems.

Text

Context

163.8K

Group

DeepSeek

Pricing preview

No display pricing published in the current snapshot.

Slug

microsoft/mai-ds-r1

TextReasoning

Unknown provider

THUDM: GLM Z1 32B

GLM-Z1-32B-0414 is an enhanced reasoning variant of GLM-4-32B, built for deep mathematical, logical, and code-oriented problem solving. It applies extended reinforcement learning—both task-specific and general pairwise preference-based—to improve performance on complex multi-step tasks. Compared to the base GLM-4-32B model, Z1 significantly boosts capabilities in structured reasoning and formal domains. The model supports enforced “thinking” steps via prompt engineering and offers improved coherence for long-form outputs. It’s optimized for use in agentic workflows, and includes support for long context (via YaRN), JSON tool calling, and fine-grained sampling configuration for stable inference. Ideal for use cases requiring deliberate, multi-step reasoning or formal derivations.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

thudm/glm-z1-32b

Text

Unknown provider

THUDM: GLM 4 32B

GLM-4-32B-0414 is a 32B bilingual (Chinese-English) open-weight language model optimized for code generation, function calling, and agent-style tasks. Pretrained on 15T of high-quality and reasoning-heavy data, it was further refined using human preference alignment, rejection sampling, and reinforcement learning. The model excels in complex reasoning, artifact generation, and structured output tasks, achieving performance comparable to GPT-4o and DeepSeek-V3-0324 across several benchmarks.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

thudm/glm-4-32b

Text

Unknown provider

Qwen: Qwen2.5 Coder 7B Instruct

Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE, SwiGLU, RMSNorm, and GQA attention with support for up to 128K tokens using YaRN-based extrapolation. It is trained on a large corpus of source code, synthetic data, and text-code grounding, providing robust performance across programming languages and agentic coding workflows. This model is part of the Qwen2.5-Coder family and offers strong compatibility with tools like vLLM for efficient deployment. Released under the Apache 2.0 license.

Text

Context

131.1K

Group

Qwen

Pricing preview

No display pricing published in the current snapshot.

Slug

qwen/qwen2.5-coder-7b-instruct

Text

Featherless

AlfredPros: CodeLLaMa 7B Instruct Solidity

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.

Text

Context

4.1K

Group

Other

Pricing preview

Input Price: $0.8 /M tokens

Output Price: $1.2 /M tokens

Slug

alfredpros/codellama-7b-instruct-solidity

TextReasoning

Unknown provider

ArliAI: QwQ 32B RpR v1

QwQ-32B-ArliAI-RpR-v1 is a 32B parameter model fine-tuned from Qwen/QwQ-32B using a curated creative writing and roleplay dataset originally developed for the RPMax series. It is designed to maintain coherence and reasoning across long multi-turn conversations by introducing explicit reasoning steps per dialogue turn, generated and refined using the base model itself. The model was trained using RS-QLORA+ on 8K sequence lengths and supports up to 128K context windows (with practical performance around 32K). It is optimized for creative roleplay and dialogue generation, with an emphasis on minimizing cross-context repetition while preserving stylistic diversity.

Text

Context

32.8K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

arliai/qwq-32b-arliai-rpr-v1

TextReasoning

Unknown provider

Agentica: Deepcoder 14B Preview

DeepCoder-14B-Preview is a 14B parameter code generation model fine-tuned from DeepSeek-R1-Distill-Qwen-14B using reinforcement learning with GRPO+ and iterative context lengthening. It is optimized for long-context program synthesis and achieves strong performance across coding benchmarks, including 60.6% on LiveCodeBench v5, competitive with models like o3-Mini

Text

Context

96K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

agentica-org/deepcoder-14b-preview

TextReasoning

Unknown provider

MoonshotAI: Kimi VL A3B Thinking

Kimi-VL is a lightweight Mixture-of-Experts vision-language model that activates only 2.8B parameters per step while delivering strong performance on multimodal reasoning and long-context tasks. The Kimi-VL-A3B-Thinking variant, fine-tuned with chain-of-thought and reinforcement learning, excels in math and visual reasoning benchmarks like MathVision, MMMU, and MathVista, rivaling much larger models such as Qwen2.5-VL-7B and Gemma-3-12B. It supports 128K context and high-resolution input via its MoonViT encoder.

TextImage

Context

131.1K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

moonshotai/kimi-vl-a3b-thinking

TextReasoning

xAI

xAI: Grok 3 Mini Beta

Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand extensive domain knowledge, and shines in math-specific and quantitative use cases, such as solving challenging puzzles or math problems. Transparent "thinking" traces accessible. Defaults to low reasoning, can boost with setting `reasoning: { effort: "high" }` Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead.

Text

Context

131.1K

Group

Grok

Pricing preview

Input Price: $0.3 /M tokens

Output Price: $0.5 /M tokens

Slug

x-ai/grok-3-mini-beta

Text

xAI

xAI: Grok 3 Beta

Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Excels in structured tasks and benchmarks like GPQA, LCB, and MMLU-Pro where it outperforms Grok 3 Mini even on high thinking. Note: That there are two xAI endpoints for this model. By default when using this model we will always route you to the base endpoint. If you want the fast endpoint you can add `provider: { sort: throughput}`, to sort by throughput instead.

Text

Context

131.1K

Group

Grok

Pricing preview

Input Price: $3 /M tokens

Output Price: $15 /M tokens

Slug

x-ai/grok-3-beta

Text

Unknown provider

NVIDIA: Llama 3.1 Nemotron Nano 8B v1

Llama-3.1-Nemotron-Nano-8B-v1 is a compact large language model (LLM) derived from Meta's Llama-3.1-8B-Instruct, specifically optimized for reasoning tasks, conversational interactions, retrieval-augmented generation (RAG), and tool-calling applications. It balances accuracy and efficiency, fitting comfortably onto a single consumer-grade RTX GPU for local deployment. The model supports extended context lengths of up to 128K tokens. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see [Usage Recommendations](https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1#quick-start-and-usage-recommendations) for more.

Text

Context

131.1K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

nvidia/llama-3.1-nemotron-nano-8b-v1

Text

Unknown provider

NVIDIA: Llama 3.3 Nemotron Super 49B v1

Llama-3.3-Nemotron-Super-49B-v1 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements. This allows the model to support a context length of up to 128K tokens and fit efficiently on single high-performance GPUs, such as NVIDIA H200. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see [Usage Recommendations](https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1#quick-start-and-usage-recommendations) for more.

Text

Context

131.1K

Group

Other

Pricing preview

No display pricing published in the current snapshot.

Slug

nvidia/llama-3.3-nemotron-super-49b-v1

TextReasoning

Unknown provider

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node. Note: you must include `detailed thinking on` in the system prompt to enable reasoning. Please see [Usage Recommendations](https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1#quick-start-and-usage-recommendations) for more.

Text

Context

131.1K

Group

Llama3

Pricing preview

No display pricing published in the current snapshot.

Slug

nvidia/llama-3.1-nemotron-ultra-253b-v1

Text

Unknown provider

Swallow: Llama 3.1 Swallow 8B Instruct V0.3

Llama 3.1 Swallow 8B is a large language model that was built by continual pre-training on the Meta Llama 3.1 8B. Llama 3.1 Swallow enhanced the Japanese language capabilities of the original Llama 3.1 while retaining the English language capabilities. Swallow used approximately 200 billion tokens that were sampled from a large Japanese web corpus (Swallow Corpus Version 2), Japanese and English Wikipedia articles, and mathematical and coding contents, etc (see the Training Datasets section of the base model) for continual pre-training. The instruction-tuned models (Instruct) were built by supervised fine-tuning (SFT) on the synthetic data specially built for Japanese.

Text

Context

16.4K

Group

Llama3

Pricing preview

No display pricing published in the current snapshot.

Slug

tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.3

Text

DeepInfra

Meta: Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction. Maverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.

TextImage

Context

Group

Llama4

Pricing preview

Input Price: $0.15 /M tokens

Output Price: $0.6 /M tokens

Slug

meta-llama/llama-4-maverick

Text

DeepInfra

Meta: Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

TextImage

Context

327.7K

Group

Llama4

Pricing preview

Input Price: $0.08 /M tokens

Output Price: $0.3 /M tokens

Slug

meta-llama/llama-4-scout

Page 5 of 15

Previous Next

Need a model request?

Use the market snapshot for discovery, then ask ImaRouter for rollout.

If a model matters for your product, send the slug, expected traffic, target region, and latency expectations. The team can confirm support status, onboarding priority, or a migration path to an equivalent route on ImaRouter.

Contact

support@imarouter.com

Best for model availability questions, onboarding priority, routing strategy, and enterprise rollout planning.

Contact ImaRouter Email the slug