Prompt caching

Mistral Large 3 675B Instruct is MistralAI's Mistral Large model. It offers a 128K-token context window and scores 70.2 on τ-bench.

$0.500 in / $1.50 out / 1M tokens

6 routes · 1 batch · 3 cache

Mistral Small 3 is a 24B-parameter, latency-optimized model that Mistral released on January 30, 2025, as both pretrained and instruction-tuned open-weight checkpoints. Mistral aims it at fast conversational assistants, low-latency function calling, fine-tuning for domain specialists, and local inference; once quantized, it can run on a single RTX 4090 or a MacBook with 32GB of RAM.

$0.150 in / $0.600 out / 1M tokens

2 routes · 1 cache

Tencent HunYuan's Hy3 Preview is a high-efficiency Mixture-of-Experts language model for agentic and production workflows. OpenRouter lists tencent/hy3-preview as released Apr 22, 2026 with 262,144 context, preview pricing, reasoning controls, and tool-use support. Hugging Face Transformers documents Hy3-preview as a Tencent HunYuan MoE model with a dense-MoE hybrid architecture, 192 routed experts, and one always-active shared expert per MoE layer. SCMP's Apr 23 coverage reports Tencent described HY3-Preview as a new flagship model developed by the HunYuan and Yuanbao teams with 295B parameters. Treat release metadata as high confidence for existence/context and medium confidence for exact parameter count until Tencent publishes a primary technical card.

$0.066 in / $0.260 out / 1M tokens

2 routes · 1 cache

Xiaomi MiMo-V2.5 is the lower-cost native omnimodal sibling in the MiMo-V2.5 series. OpenRouter describes it as supporting text, image, audio, and video inputs with text output, Pro-level agentic performance at roughly half the inference cost, and improved multimodal perception over MiMo-V2-Omni. Xiaomi's official April 22 release page highlights MiMo-V2.5 alongside MiMo-V2.5-Pro in benchmark data and says the V2.5 series will be open-sourced soon; no public weights/license were verified at research time.

$0.140 in / $0.280 out / 1M tokens

2 routes · 2 cache

Xiaomi's April 22, 2026 public-beta flagship in the MiMo-V2.5 series. The official Xiaomi MiMo page describes MiMo-V2.5-Pro as its most capable model to date, focused on general agentic capability, complex software engineering, long-horizon tasks, and ultra-long-context instruction following. OpenRouter lists it as text-to-text with 1,048,576 token context, 131,072 max completion tokens, reasoning controls, tool use, and response_format support. Xiaomi says the V2.5 series will be open-sourced soon, but no public weights/license were verified at research time.

$0.435 in / $0.870 out / 1M tokens

3 routes · 3 cache

Xiaomi MiMo-V2.6-Flash is Xiaomi MiMo's September 21, 2026 efficiency-balanced open-weights MoE (309B total / 15B active), sibling of MiMo-V2.6-Pro. First-party HF checkpoint XiaomiMiMo/MiMo-V2.6-Flash-RL (MIT; ungated; 1M context) is the released Flash RL weights; product/API id is mimo-v2.6-flash. First-party news: the series comprises two native fully multimodal models (Pro and Flash); Flash comprehensively outperformed MiMo-V2.5-Pro. Product card: full-modality high-intelligence low-cost reasoning for high-frequency and large-scale professional workflows; context 1M; max output 128K; input text, image, video, and audio. Overseas API pricing (pay-as-you-go): $0.0028 cache-hit / $0.14 cache-miss input and $0.28 output per 1M tokens; batch $0.0014 / $0.07 / $0.14. Sparse MoE MiMoV2ForCausalLM; 48 layers (39 SWA / 9 GA); 256 routed experts / 8 activated per token; hybrid SWA+GA backbone; native omnimodal (text/image/video/audio); 681M MiMo ViT vision encoder; 5-layer SWA MTP/DFlash speculative decoder.

$0.140 in / $0.280 out / 1M tokens

2 routes · 1 batch · 2 cache

Xiaomi MiMo-V2.6-Pro is Xiaomi MiMo's September 21, 2026 flagship open-weights MoE (1.02T total / 42B active), succeeding proprietary MiMo-V2.5-Pro. First-party HF checkpoint XiaomiMiMo/MiMo-V2.6-Pro-RL (MIT; ungated; 1M context) is the released Pro RL weights; product/API id is mimo-v2.6-pro. HF README: native omnimodal + long-horizon agents; You Only RL Once mixed RL across coding/agents/visual/cybersecurity. Official product page (mimo.mi.com) and @XiaomiMiMo announce open-sourcing of Pro and Flash with tech report. Overseas API pricing matches V2.5-Pro: $0.0036 cache-hit / $0.435 cache-miss input and $0.87 output per 1M tokens (pay-as-you-go). Sparse MoE MiMoV2ForCausalLM; 70 layers (60 SWA / 10 GA); 384 routed experts / 8 activated per token; hybrid SWA+GA backbone; native omnimodal (text/image/video/audio); 681M MiMo ViT vision encoder; MTP blocks.

$0.435 in / $0.870 out / 1M tokens

2 routes · 1 batch · 2 cache

Kimi K3 is Moonshot AI's 2.8-trillion-parameter flagship multimodal model for long-horizon coding, knowledge work, deep reasoning, and agentic workflows. It uses Kimi Delta Attention, Attention Residuals, and a sparse MoE design (16 of 896 experts active), supports a 1,048,576-token context window, text/image/video input, always-on reasoning, ToolCalls, strict JSON Schema structured output, automatic context caching, and partial mode through Moonshot's OpenAI-compatible API.

$3.00 in / $15.00 out / 1M tokens

3 routes · 2 cache

GLM-5.3-Flash is Z.ai's first native multimodal model in the GLM-5 series. It is a 320B-total / 18B-active Mixture-of-Experts model with a 1M-token context window and 131,072 max output tokens, supporting image, video, and file input plus function calling, tool use, structured outputs, reasoning, and prompt caching. MIT open weights are ungated on Hugging Face at zai-org/GLM-5.3-Flash. Official API model ID: glm-5.3-flash. The same model was previously tested anonymously as ox-alpha; that name is not a separate catalog slug.

$0.150 in / $0.500 out / 1M tokens

2 routes · 2 cache

GLM-5.3 is Z.ai's August 2026 coding-first post-training release on the same GLM-5.2 base model, focused on complex software engineering, long-horizon agentic coding, and emergent cybersecurity evaluation. It is available through the GLM Coding Plan and Z.ai API; open weights are scheduled after safety hardening. Official API model ID: glm-5.3.

$1.40 in / $4.40 out / 1M tokens

3 routes · 2 cache

GLM-5.2 is Z.ai's coding-first successor to GLM-5.1 in the GLM-5 family, released June 13 2026. 753B parameters (40B active) in IndexShare MoE architecture; the IndexShare innovation reuses the same attention indexer across every four sparse layers, cutting per-token FLOPs by 2.9x at 1M context length. Trained on 28.5T tokens. Supports a 1M-token context window via the glm-5.2[1m] model ID, with 131,072-token maximum output and High/Max thinking-effort levels designed for extended agentic coding sessions. MIT license; open weights available on Hugging Face (zai-org/GLM-5.2 and zai-org/GLM-5.2-FP8). Self-reported HF card benchmarks: SWE-bench Pro 62.1, Terminal-Bench 2.1 82.7, MCP-Atlas 76.8, Tool-Decathlon 48.2, GPQA Diamond 91.2, AIME 2026 99.2, HLE 40.5. Available to GLM Coding Plan subscribers (Lite/Pro/Max/Team) directly, and via OpenRouter token API ($1.40/$4.40 per 1M tokens).

$1.40 in / $4.40 out / 1M tokens

2 routes · 1 cache

Post-training variant of GLM-5 from Z.ai (Zhipu AI) with enhanced agentic coding capabilities. Released April 7, 2026. 754B parameters (40B active) in Mixture of Experts architecture, 200K token context, 128K max output. Supports autonomous plan–execute–test–fix–optimize loops for up to 8 hours without human intervention. Trained entirely on Huawei Ascend hardware (no Nvidia). Key benchmarks: SWE-bench Pro 58.4 (world #1 at release, surpassing GPT-5.4 57.7 and Claude Opus 4.6 57.3), GPQA Diamond 86.2, AIME 2026 95.3, Terminal-Bench 2.0 63.5, MCP-Atlas 71.8, Chatbot Arena Elo 1475 (June 16, 2026, arena.ai). Available via Z.ai API ($1.40/$4.40 per 1M input/output tokens) and open weights on Hugging Face under MIT license.

$1.38 in / $4.40 out / 1M tokens

5 routes · 3 cache

Amazon Nova Premier is Amazon's most capable standard Bedrock Nova understanding model for complex reasoning, agentic workflows, and model distillation. It supports a 1M-token context window, text/image/video inputs, text output, reasoning, tool calling, and prompt caching; use it as the standard Bedrock Nova frontier pick instead of Nova 2 Omni early-access Forge checkpoints.

$2.50 in / $12.50 out / 1M tokens

2 routes · 1 batch · 2 cache

Mistral Large 2 (version 24.07, API name mistral-large-2407) is a 123-billion-parameter dense model that Mistral released on July 24, 2024, designed for single-node inference in long-context applications. It has a 128K-token context window, up from 32K on the first Mistral Large, and supports dozens of languages, including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese and Korean, plus more than 80 coding languages such as Python, Java, C, C++, JavaScript and Bash. Mistral trained it on a large proportion of code and reports stronger code and reasoning than the first Mistral Large, and the model supports native function calling, including parallel and sequential calls, and JSON output. The instruct weights are on Hugging Face under the Mistral Research License, which allows research and non-commercial use; commercial self-deployment requires a Mistral Commercial License. Mistral retired mistral-large-2407 from its API on March 30, 2025, and lists Mistral Large 3 as the replacement.

$2.00 in / $6.00 out / 1M tokens

3 routes · 1 batch · 1 cache

Mistral NeMo Instruct (2407) is MistralAI's Mistral NeMo model. It offers a 128K-token context window and scores 57.1 on GPQA.

$0.029 in / $0.030 out / 1M tokens

9 routes · 1 cache

NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). 300+ tokens/second. 1M-token context. Announced at Computex 2026. Pricing: ~$0.60/$2.60 per 1M tokens (provider median); free tier on some providers.

$0.900 in / $1.70 out / 1M tokens

8 routes · 6 cache

Kimi K2.5 is Moonshot AI's Kimi model focused on code generation and software engineering. It offers a 256K-token context window and scores 87.9 on GPQA.

$0.440 in / $2.00 out / 1M tokens

7 routes · 1 cache

Flagship open-weight foundation model from Zhipu AI with 744B parameters (40B active per token) in Mixture of Experts architecture. Trained on 28.5T tokens using DeepSeek Sparse Attention on Huawei Ascend hardware. Achieves state-of-the-art performance on coding and agentic benchmarks (SWE-bench Verified: 77.8%). Supports autonomous planning, multi-step tool use, and self-correction.

$1.00 in / $3.20 out / 1M tokens

7 routes · 3 cache

Kimi K3.1 Pro is the first model in Moonshot AI's K3.1 series, a post-trained version of Kimi K3. It has a 1,048,576-token context window, always-on reasoning with low, high and max effort, image and video input, tool calling and strict JSON Schema structured output. Released 2026-10-23 on Kimi.ai, Kimi Work, Kimi Code and the Kimi API; Moonshot published the weights on Hugging Face under the Kimi K3.1 Pro License.

$2.00 in / $10.00 out / 1M tokens

6 routes · 5 cache

DeepSeek V4 Pro is DeepSeek's flagship open-weights model, released April 24 2026 under the MIT license. Architecture: 1.6T total / 49B active parameters, MoE with Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) hybrid — requiring only 27% of inference FLOPs vs standard 1M-context transformers — plus Manifold-Constrained Hyper-Connections (mHC) and Muon Optimizer. Context window: 1,000,000 tokens; max output: 384,000 tokens (Think Max mode requires >=384K context). Text-only (no vision/image input). Supports three reasoning modes: Non-Think, Think High, Think Max. Function calling, tool use, and structured outputs supported. Key benchmarks: SWE-bench Verified 80.6%, SWE-bench Pro 55.4%, LiveCodeBench 93.5%, GPQA Diamond 90.1%, MMLU-Pro 87.5% and Chatbot Arena 1456 (2026-06-16).

$0.3633 in / $0.7266 out / 1M tokens

6 routes · 4 cache

NVIDIA Nemotron 3 Super-120B-A12B is a 120B total / 12B active hybrid Latent MoE model with interleaved Mamba-2 and MoE layers for agentic, reasoning, and conversational tasks. Fireworks lists the NVFP4 variant for on-demand deployment with 262k context.

$0.085 in / $0.400 out / 1M tokens

6 routes · 2 cache

Alibaba's closed-weight flagship language model, announced at the 2026 Alibaba Cloud Summit (May 20). 1M-token context with prompt caching.

$1.25 in / $3.75 out / 1M tokens

4 routes · 2 cache

Mixtral 8x22B Instruct v0.1 is MistralAI's Mixtral model. It offers a 64K-token context window and scores 56.3 on MMLU PRO.

$0.650 in / $0.650 out / 1M tokens

4 routes · 1 cache

Muse Ember is Meta Superintelligence Labs' smallest and most efficient Muse model, introduced November 9, 2026, for the work agents repeat all day: tool calls, coding subtasks, routing, extraction and long-document parsing. Meta says it is the first model trained using Muse Wonder Full. It takes text, image, audio and video input and returns text, with a 1M-token context window and up to 512K output tokens, and supports the Responses API. It is available on Muse Code and the Meta Model API as muse-ember-1.0 at $0.10 per million input tokens, $0.004 per million cached input tokens and $0.50 per million output tokens.

$0.100 in / $0.500 out / 1M tokens

3 routes · 3 cache

Hy4 is Tencent Hy's flagship large language model, released November 4, 2026 as the successor to Hy4 preview. It is the first Hy model with vision input, and Tencent serves it on Tencent Cloud, OpenRouter and in its CodeBuddy, WorkBuddy, Yuanbao and ima products. Tencent says it plans to open-source the weights, with vLLM and SGLang support and a system card at that time; as of release the model is API-only.

$0.834 in / $2.50 out / 1M tokens

3 routes · 1 cache

joey-1 is a 2B open-weight decision model from Base Labs, Baseten's research lab, released October 29, 2026. It is a fine-tune of Qwen3.5-2B that turns a state and typed questions into calibrated probabilities for choice, yes/no and score answers in a single forward pass, without generating free-form text, for routing, classification and rubric scoring. It accepts text and images and has a 16,384-token context limit. It is the smallest of Base Labs' three decision models (with elephant-1 and mammoth-1). Weights are on Hugging Face at baselabs/joey-1 under MIT.

$0.010 in / Free out / 1M tokens

3 routes · 1 cache

Particle-1 is Particle AI's model for agentic coding and software engineering, post-trained on DeepSeek V4.1 Flash to finish tasks with fewer tokens. It takes text and images, supports reasoning and tool use, and has a 1,048,576-token context window with up to 131,072 output tokens. Available on the Particle API, OpenRouter and Vercel AI Gateway.

$0.250 in / $1.00 out / 1M tokens

3 routes · 3 cache

GLM-Legal is Z.ai's legal-domain model, built on GLM-5.3-Flash with legal mid-training and reinforcement-learning post-training across legal agent environments. Z.ai reports a 19.2% all-pass rate on the Harvey Legal Agent Benchmark, 12.5 points above its base model, as evaluated by Vals.

$0.370 in / $1.25 out / 1M tokens

3 routes · 3 cache

Qwen3.6-Plus is Alibaba Cloud's GA Qwen3.6 flagship for long-context reasoning, coding, tool use, and multimodal workflows. DashScope lists it with a 1M-token context window, structured output support, and standard public token pricing.

$0.325 in / $1.95 out / 1M tokens

3 routes · 2 cache

SOLAR 10.7B is a robust large language model created by Upstage AI in South Korea, featuring 10.7 billion parameters. It is tailored for high efficiency and performance through its innovative "Depth Up-Scaling" (DUS) approach, which deepens the model's layers rather than widening them, allowing for enhanced capabilities without significantly increasing computational costs. This method distinguishes it from other models that utilize more complex techniques like Mixture of Experts. By integrating pre-trained weights from the Mistral 7B model with the Llama 2 framework, SOLAR 10.7B achieves notable performance, outpacing even some models with up to 30 billion parameters. Available under the Apache 2.0 license, it also includes a finely-tuned instruction-based variant under CC-BY-NC-4.0, optimized for single-turn conversations and diverse NLP tasks, albeit with limitations in handling multi-turn dialogue and complex context. The model is grounded in the transformer architecture, widely adopted in advanced language models.

$0.200 in / $0.200 out / 1M tokens

3 routes · 1 cache

Reflex is Morph's 27B decision model, built on Qwen 3.5 and announced November 4, 2026 on Morph's System One endpoint and OpenRouter. It answers questions about text, JSON and images with a probability for each option instead of generating text, so it produces no output tokens. It has a 64K (65,536-token) context.

$0.042 in / Free out / 1M tokens

2 routes · 2 cache

Ripple-65B Preview is Ricursive Intelligence's open-weight 65B-parameter dense Transformer, released November 4, 2026 under Apache 2.0. It is a general-purpose variant of the in-house model behind Ricursive's AI chip design platform, pretrained on 12 trillion tokens with support for up to 1M tokens of context. Weights are on Hugging Face.

$0.200 in / $0.600 out / 1M tokens

2 routes · 2 cache

LFM3-1.7B is Liquid AI's text model for local agents and specialized applications, the base of the LFM3 family. It uses the new tri-hybrid architecture (convolution, sliding-window and global attention layers), is post-trained for agentic harnesses, and has a 256K-token context window. At 4-bit precision it needs about 1 GB of memory. Open weights under the LFM Open License v1.0; also served on the Liquid AI API.

$0.080 in / $0.200 out / 1M tokens

2 routes · 2 cache

Kimi K3.1 Pro Highspeed is the high-speed variant of Moonshot AI's Kimi K3.1 Pro, offered on the Kimi API with the same 1,048,576-token context window. It keeps always-on reasoning with low, high and max effort, image and video input, tool calling and strict JSON Schema structured output, at double the K3.1 Pro token price. Released 2026-10-23 alongside K3.1 Pro.

$4.00 in / $20.00 out / 1M tokens

2 routes · 2 cache

Ampersand (v0.1, API id ampersand-v0.1) is humans&'s collaborator model, built on GLM 5.3 and trained with RL to understand the long-term consequences of its actions and help groups of people reach shared goals: reasoning together, asking questions, surfacing context and working through disagreements. Text in/out, 1M-token context, API-only.

$1.00 in / $5.20 out / 1M tokens

2 routes · 1 cache

Qwen3.8-Max is a 2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. It autonomously codes and delivers complete projects spanning 10+ days, handles hundreds of specialized tasks across legal, financial, design, and other professional domains, and produces production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. The public Hugging Face checkpoint (Qwen3.8-2.4T-A95B) is text-only under the Qwen3.8-Max License; the hosted qwen3.8-max API adds vision, optional non-thinking mode, 1M context, tools, structured outputs, and prompt caching on the same model ID.

$2.00 in / $6.00 out / 1M tokens

2 routes · 2 cache

Ampersand Tutor (&Tutor) is humans&'s tutoring model, released October 30, 2026 through the Ampersand API as ampersand-tutor-v0.1. Built on GLM 5.3, it learns to teach by training against Persimmon, humans&'s large-scale model of how students learn, and aims to maximize a student's understanding rather than just give answers. It is a mixture-of-experts transformer (78 layers, 256 routed experts plus 1 shared, 8 active per token) served in NVFP4, with text input and output.

$1.00 in / $5.20 out / 1M tokens

1 route · 1 cache

GPT-5 Image Mini is a cost-effective image generation model that combines GPT-5 Mini's language capabilities with image generation at 400K context.

$2.50 in / $2.00 out / 1M tokens

1 route · 1 cache

OpenAI's previous intelligent reasoning model with configurable reasoning effort. Released August 2025. Supports minimal, low, medium, and high reasoning levels. Succeeded by GPT-5.1 and later models.

$1.25 in / $10.00 out / 1M tokens

5 routes · 1 batch · 3 cache

Near-frontier intelligence for cost-sensitive, low-latency, high-volume workloads. Released August 2025. Replaces o4-mini (shutting down Oct 2026).

$0.250 in / $2.00 out / 1M tokens

4 routes · 1 batch · 3 cache

OpenAI open-weight model with 120 billion parameters. Text-only model supporting reasoning, function calling, and structured outputs. Free for self-hosting. Released August 5, 2025.

Free in / Free out / 1M tokens

13 routes · 1 cache

Gemini 3 Flash is Google's speed-optimized Gemini 3 model, available in public preview via the Gemini API and Vertex AI. It supports text, image, audio, and video inputs with a 1M token context window and is priced at $0.50 per 1M input tokens and $3.00 per 1M output tokens.

$0.500 in / $3.00 out / 1M tokens

4 routes · 1 cache

Fastest, cheapest GPT-5 variant for summarization and classification tasks. Also available via Realtime API.

$0.050 in / $0.400 out / 1M tokens

4 routes · 1 batch · 3 cache

GPT OSS Safeguard 20B is OpenAI's GPT-OSS model focused on content moderation and safety classification. It offers a 128K-token context window with weights openly available for self-hosting.

$0.070 in / $0.200 out / 1M tokens

4 routes · 1 cache

GLM-4.5V is a vision-language MoE model from Z.ai designed for multimodal agent applications, handling both image understanding and text generation at 64K context.

$0.600 in / $1.80 out / 1M tokens

4 routes · 3 cache

Frontier-class performance rivaling larger models at a fraction of the cost. Most intelligent Gemini model built for speed, combining frontier intelligence with superior search and grounding. $0.50 input / $3.00 output per 1M tokens.

$0.500 in / $3.00 out / 1M tokens

3 routes · 1 cache

GPT-5 Image combines OpenAI's GPT-5 language model with state-of-the-art image generation, enabling both text understanding and image creation within a single 400K context model.

$10.00 in / $10.00 out / 1M tokens

1 route · 1 cache

LFM2.5-24B-A2B is Liquid AI's largest LFM2.5 model: a 24B-parameter mixture-of-experts reasoning model with about 2B active parameters per token, built for fast on-device agents. It keeps the LFM2 hybrid of gated short convolutions and GQA (40 layers, 64 experts, top-4 routing), extends context from 32,768 to 131,072 tokens, doubles the vocabulary to 128K, and scales pre-training from 17T to 33T tokens. Unlike LFM2-24B-A2B, it is reasoning-only (explicit chain of thought before the final answer) and is post-trained for tool calling and multi-step agent harnesses. Open weights under LFM Open License v1.0 on Hugging Face; also on Liquid Console, OpenRouter, and Vercel AI Gateway.

$0.050 in / $0.700 out / 1M tokens

3 routes · 3 cache

Seed 1.6 is a general-purpose multimodal model from ByteDance Seed supporting text, image, and video inputs. It incorporates multimodal capabilities and deep thinking for complex tasks at 256K context.

$0.250 in / $2.00 out / 1M tokens

2 routes · 1 cache

Amazon Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that processes text, images, and videos at 1M token context with improved reasoning over Nova Lite v1.

$0.300 in / $2.50 out / 1M tokens

2 routes · 1 cache

Qwen3-VL-8B-Instruct is a compact 8B multimodal vision-language model from Alibaba, delivering high-fidelity image understanding and grounding at 128K context.

$0.080 in / $0.500 out / 1M tokens

2 routes · 1 cache

MAI-Thinking-1 is Microsoft AI's flagship reasoning model, built from scratch on enterprise-grade commercially licensed data without third-party distillation. The sparse mixture-of-experts model activates about 35B parameters from roughly 1T total parameters, supports a 256K-token context window, and targets frontier reasoning and software engineering work at a mid-weight price point. Microsoft reports 97% on AIME 2025, 94.5% on AIME 2026, 84.2% on GPQA Diamond, 87.7% on LiveCodeBench v6, 73.5% on SWE-bench Verified, and 52.8% on SWE-bench Pro. In a 1,276-task Surge blind side-by-side evaluation, it narrowly beat Claude Sonnet 4.6 but trailed Claude Opus 4.6. It supports function calling and developer instructions through the Chat Completions API.

$2.00 in / $8.00 out / 1M tokens

1 route · 1 cache

MiniMax M2-her is a dialogue-first model from MiniMax built for immersive roleplay, character-driven chat, and expressive storytelling at 64K context.

$0.300 in / $1.20 out / 1M tokens

1 route · 1 cache

The Llama 3.1 8B Instruct model, released on July 23, 2024, is a multilingual large language model with 8 billion parameters, optimized for instruction-following tasks. It features an enhanced transformer architecture, supporting languages like English, German, French, and others. The model excels in dialogue applications, having been fine-tuned using supervised fine-tuning and reinforcement learning with human feedback. Trained on approximately 15 trillion tokens with a December 2023 data cutoff, it outperforms many existing open-source and closed chat models in various benchmarks. Ideal for commercial and research applications such as conversational agents and content generation, the model can be accessed on Hugging Face .

$0.020 in / $0.050 out / 1M tokens

12 routes · 1 cache

OpenAI's GPT-4.1 model released April 2025, excelling at coding tasks, precise instruction following, and web development. Outperforms GPT-4o in these areas with a 1 million token context window. Available via API and in ChatGPT for Plus, Pro, Team, Enterprise, and Edu users.

$2.00 in / $8.00 out / 1M tokens

4 routes · 1 batch · 3 cache

GLM-4.6V is Z.ai's large multimodal model for high-fidelity visual understanding and long-context reasoning across images, charts, and documents at 128K context.

$0.300 in / $0.900 out / 1M tokens

3 routes · 2 cache

Fast and efficient small model from OpenAI replacing GPT-4o mini. Released April 2025 alongside GPT-4.1. Shows improvements in instruction-following, coding, and intelligence with a 1 million token context window. Available in ChatGPT for paid users.

$0.400 in / $1.60 out / 1M tokens

4 routes · 3 cache

Qwen3.8-27B is the Qwen3.8 generation's native vision-language dense model, building on Qwen3.6-27B with key improvements in coding and office productivity across text and visual modalities. It enables more reliable end-to-end completion of complex tasks with consistently trustworthy results. Apache 2.0 weights are on Hugging Face; the hosted qwen3.8-27b API supports 1M context, reasoning, function calling, tool use, structured outputs, and prompt caching.

$0.425 in / $2.55 out / 1M tokens

2 routes · 2 cache

Hybrid thinking/non-thinking text model from DeepSeek with tool use, agent support and a 128K context window.

$0.270 in / $1.00 out / 1M tokens

9 routes · 1 cache

Claude Sonnet 4.5 is Anthropic's Claude 4.5 model with multimodal text and image input and an optional reasoning mode. It offers a 200K-token context window and scores 86 on MMLU PRO.

$3.00 in / $15.00 out / 1M tokens

7 routes · 4 cache

Claude Opus 4.5 is Anthropic's Claude 4.5 model with multimodal text and image input and an optional reasoning mode. It offers a 200K-token context window and scores 80.7 on MMMU.

$5.00 in / $25.00 out / 1M tokens

6 routes · 1 batch · 4 cache

OpenAI GPT-4o: Flagship multimodal model with vision, function calling, and broad capability. $2.50/M input, $10/M output.

$2.50 in / $10.00 out / 1M tokens

5 routes · 1 batch · 3 cache

Qwen3.6-35B-A3B is an open-weight multimodal MoE model with 35B total parameters and 3B activated per token, released April 2026. It features a hybrid architecture combining Gated DeltaNet linear attention and standard Gated Attention with 256 total experts (8 routed + 1 shared), and includes a vision encoder for image and video understanding. Optimized for agentic coding, long-context reasoning, and visual tasks; supports 256K native context (extensible to ~1M via YaRN) with integrated thinking mode for multi-turn agent interactions.

$0.150 in / $1.00 out / 1M tokens

3 routes · 1 cache

Qwen3-VL-235B-A22B-Instruct is Alibaba's open-weight flagship multimodal MoE model combining strong text generation with visual understanding, supporting 256K context.

$0.300 in / $1.50 out / 1M tokens

3 routes · 1 cache

Mistral Medium 3 is Mistral AI's enterprise-grade model delivering frontier-level capabilities including vision, function calling, and code generation at competitive cost for business applications.

$0.400 in / $2.00 out / 1M tokens

3 routes · 1 cache

Alibaba's multimodal agentic model with text, image, and video input. Combines vision-language understanding with full agentic capabilities: deep reasoning, self-programming, tool invocation, and autonomous iteration. GUI grounding: 79.0 on ScreenSpot Pro. Max output 66K tokens. Pricing: $0.40/$1.60 per 1M tokens in/out.

Pricing not tracked / 1M tokens

2 routes

UI-TARS-1.5 is ByteDance's multimodal vision-language agent model optimized for GUI-based environments including desktop interfaces, web browsers, and mobile apps. It supports grounding, planning, and action execution for computer-use tasks.

$0.100 in / $0.200 out / 1M tokens

1 route · 1 cache

Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence. Proprietary decoder-only model with 1M-token context, 64K max output, multimodal vision, extended thinking, and function calling. Available via Anthropic API, AWS Bedrock, GCP Vertex AI, and OpenRouter at $3/1M input and $15/1M output tokens.

$3.00 in / $15.00 out / 1M tokens

6 routes · 1 batch · 5 cache

Claude Opus 4.7 is Anthropic's generally available flagship model with 1M context, 128K max output, adaptive thinking, and a new tokenizer with roughly 555K words per 1M tokens.

$5.00 in / $25.00 out / 1M tokens

6 routes · 1 batch · 5 cache

Claude Opus 4.6 is Anthropic's Claude 4.6 model with multimodal text and image input and an optional reasoning mode. It offers a 1M-token context window and scores 80.8 on SWE-bench Verified.

$5.00 in / $25.00 out / 1M tokens

6 routes · 1 batch · 5 cache

GLM-4.7 is Z.ai's flagship text model featuring enhanced programming capabilities and deeper reasoning at 200K context, succeeding GLM-4.6.

$0.550 in / $2.20 out / 1M tokens

8 routes · 2 cache

Claude Opus 4.8 is Anthropic's flagship Claude 4.8 model, released May 28, 2026 for agentic coding, long-horizon reasoning, computer use, and professional knowledge work. It supports text and image inputs, adaptive reasoning, tool use, structured outputs, computer-use tools, prompt caching, Batch API, Dynamic Workflows parallel subagents, a 1M-token context window on Anthropic API/Bedrock/Vertex, and 128K max output. Reported benchmark scores: SWE-bench Pro 69.2%, SWE-bench Verified 88.6%, Terminal-Bench 2.1 74.6%, HLE with tools 57.9%, OSWorld-Verified 83.4%, and MCP-Atlas 82.2%. Standard Anthropic API pricing is $5/M input and $25/M output.

$5.00 in / $25.00 out / 1M tokens

6 routes · 1 batch · 4 cache

Claude Sonnet 5 is Anthropic's next-generation Sonnet model for agentic coding, tool use, computer use, and professional work. It is a proprietary decoder-only model with a 1M-token context window, 128K max output, multimodal vision, adaptive thinking, function calling, structured outputs, prompt caching, and Batch API support. It is available through the Claude API, AWS Bedrock, Google Cloud Vertex AI, Microsoft Foundry preview, and OpenRouter. Anthropic lists durable standard pricing at $3/1M input and $15/1M output tokens, with introductory $2/$10 pricing through 2026-08-31.

$2.00 in / $10.00 out / 1M tokens

6 routes · 2 batch · 4 cache

Claude Opus 5 is Anthropic's July 2026 flagship Opus model for complex agentic coding, enterprise work, long-horizon reasoning, computer use, and professional analysis. It accepts text and image input and returns text, with adaptive thinking enabled by default and five request-level effort settings from low through max that control thinking depth and token use rather than visible response length. It also supports tool use, structured outputs, prompt caching, Batch API, a 1M-token context window, and up to 128K synchronous output tokens. Anthropic lists standard Claude API pricing at $5 per million input tokens and $25 per million output tokens, with Fast mode at $10/$50. It is available through the Claude API and hosted provider routes.

$5.00 in / $25.00 out / 1M tokens

7 routes · 2 batch · 5 cache

Mistral's 128B flagship merged model, released April 29, 2026. Open weights available on HuggingFace since ~May 22, 2026 under a Modified MIT License (free for companies with <$20M/month revenue). Dense 128B architecture with 256k context window, configurable reasoning effort, vision encoder for variable image sizes, and native function calling. Achieves 91.4% on τ³-Telecom and 77.6% on SWE-Bench Verified. Strong multilingual support across 24+ languages. Replaces Mistral Medium 3.1, Magistral, and Devstral 2 as Mistral's primary merged model. Available via Mistral API at $1.50/$7.50 per million tokens (input/output) and via NVIDIA NIM/endpoints.

$1.50 in / $7.50 out / 1M tokens

3 routes · 1 cache

Mistral Small 4 is a hybrid 119B MoE model unifying instruct, reasoning, and coding capabilities. Features configurable reasoning effort per request and native function calling with JSON output support.

$0.100 in / $0.300 out / 1M tokens

3 routes · 1 cache

Mistral Small 3.2 24B is an updated instruction-tuned model from Mistral optimized for function calling, structured outputs, and vision tasks at 128K context with open weights.

$0.100 in / $0.300 out / 1M tokens

2 routes · 1 cache

MAI-Code-1.1-Flash is Microsoft AI's successor to MAI-Code-1-Flash: a sparse Mixture-of-Experts coding model (138B total / 5B active per the model card) with a 256K context window, text and image input, and text output. It launched in GitHub Copilot on 2026-08-11 with native vision, stronger coding and tool use, and a lower list price than 1-Flash. Microsoft reports SWE-Bench Verified 72.6% and Terminal-Bench 2.1 62.9% in the Copilot harness, ~25% better token efficiency, and about one quarter the cost of the June 1.0 Flash launch. GitHub Copilot models-and-pricing (per 1M tokens): $0.20 input, $0.02 cached input, $1.20 output. On 2026-10-07 Microsoft added an on-device quantized build (Windows ML / Copilot local; recommend >120GB RAM) with zero per-inference charges for local calls. Proprietary product terms; not on Hugging Face.

No tracked provider route

Anthropic's Claude Opus 5.5, first model in the Claude 5.5 family, released September 22, 2026. First-party positioning: long-running agentic coding and knowledge work; performs at the level of Claude Fable 5.1 on most work; typical workloads about 40% less cost than Opus 5 at default settings (list input/output 20% below Opus 5; cache reads 60% below). Claude API id claude-opus-5-5. List price $4 per 1M input and $20 per 1M output; cache reads $0.20 per 1M tokens (0.05x base input); 5-minute cache writes $5; 1-hour cache writes $8; Batch API 50% off ($2/$10). Fast mode (Claude API research preview) is $8/$40. 1M-token context, 128K max output (Batch API beta up to 300K with output-300k-2026-03-24), adaptive thinking always on (default effort medium), text and image input to text output, vision, and tool use. Available on Claude for Pro, Max, Team, and Enterprise and on the Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, and Claude Platform on AWS. Reliable knowledge cutoff June 2026.

$4.00 in / $20.00 out / 1M tokens

5 routes · 1 batch · 5 cache

DeepSeek V4.1 Flash 1017 is the October 17, 2026 update to DeepSeek V4.1 Flash, released under the MIT license with weights on Hugging Face and ModelScope. DeepSeek describes it as a minor update trained with reinforcement learning from self-feedback for end-to-end project development, with shorter task runtime and output length. It supports 1M-token context, up to 384K output tokens, vision input, thinking and non-thinking modes, tool calls and JSON output. The DeepSeek API serves it as deepseek-flash, and the legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp also route to it.

$0.200 in / $0.600 out / 1M tokens

6 routes · 6 cache