Context window

RWKV-7 Goose 0.1B (approximately 190M parameters) is the smallest model in the RWKV-7 Goose series. Suitable for ultra-low-resource deployment with constant-memory inference. Uses RWKV-7 architecture with the Generalized Delta Rule. Trained on the World v2.8 corpus. Apache 2.0 licensed.

No tracked provider route

RWKV-6 Finch 1.6B is the smallest model in the RWKV-6 Finch series, ideal for lightweight deployments requiring constant-memory inference. Apache 2.0 licensed.

No tracked provider route

RWKV-7 Goose 0.4B (approximately 450M parameters) is a lightweight model from the RWKV-7 Goose series. Designed for edge deployment and resource-constrained environments where constant-memory O(1) inference is critical. Uses RWKV-7 architecture with the Generalized Delta Rule. Trained on the World v2.9 corpus. Apache 2.0 licensed.

No tracked provider route

RWKV-6 Finch 3B is a mid-range model in the RWKV-6 Finch series, offering a balance between capability and deployment efficiency. Apache 2.0 licensed. Constant-memory inference with no KV cache.

No tracked provider route

RWKV-7 Goose 1.5B is a mid-range model from the RWKV-7 Goose World3 series. Uses the seventh-generation RWKV architecture with Generalized Delta Rule for expressive dynamic state evolution. Trained on 3.1 trillion tokens from the multilingual World v3 corpus. Constant-memory inference with no KV cache. Apache 2.0 licensed.

No tracked provider route

RWKV-6 Finch 7B is a flagship mid-size model from the RWKV-6 architecture series. Introduced alongside the Eagle and Finch paper (arXiv 2404.05892, April 2024). The Finch 14B model was subsequently derived by stacking two Finch 7B weights. Uses multi-headed matrix-valued states for improved language comprehension. Constant-memory inference. Apache 2.0 licensed.

No tracked provider route

RWKV-7 Goose 2.9B is the largest released model in the RWKV-7 Goose World3 series. Built on the seventh-generation RWKV architecture with the Generalized Delta Rule and dynamic state evolution, it achieves competitive benchmark performance against transformer models of equivalent scale. Trained on 3.1 trillion tokens from the World v3 multilingual corpus (100+ languages, BF16). As a pure recurrent architecture, it requires constant O(1) memory during inference (no KV cache) and processes sequences in linear O(n) time. Licensed Apache 2.0.

No tracked provider route

RWKV-6 Finch 14B is the largest model in the RWKV-6 Finch series, created by stacking two 7B Finch models. Released September 3, 2024. Achieves strong performance on MMLU (56.05%), ARC, HellaSwag (57.69%), and Winogrande (74.43%). The RWKV-6 architecture uses matrix-valued states and dynamic data-driven recurrence, improving comprehension and in-context reasoning compared to RWKV-5 (Eagle). Constant-memory O(1) inference with no KV cache. Apache 2.0 licensed.

No tracked provider route

LTM-2-mini is Magic's research prototype supporting a 100 million token context window, announced August 29, 2024. Uses a novel sequence-dimension algorithm approximately 1,000× more memory-efficient than transformer attention at this scale — requiring only a fraction of a single H100's HBM versus 638 H100s for Llama 3.1 405B at the same context length. Not publicly released for API access or self-hosting; Magic stated they were separately training a full LTM-2 model. Specialization: coding/software development. Source: https://magic.dev/blog/100m-token-context-windows

No tracked provider route

Meta's Llama 4 Scout is a 17-billion parameter mixture-of-experts model with 16 expert routing. Optimized for efficient inference on edge and cloud environments with strong multi-turn conversation capabilities. Available on Cloudflare Workers AI.

$0.170 in / $0.220 out / 1M tokens

12 routes

LTM-1 (Long-Term Memory 1) is Magic's first model with a 5 million token context window, announced June 6, 2023. Designed to process entire codebases in context for AI-assisted software development. Architecture and parameter count not publicly disclosed. Not available as a public API; Magic used it in an early-access coding product. Source: https://magic.dev/blog/ltm-1

No tracked provider route

MiniMax-01 combines MiniMax-Text-01 and MiniMax-VL-01, pairing a 456B-total-parameter MoE language model with multimodal understanding for long-context text generation and vision-language tasks.

$0.200 in / $1.10 out / 1M tokens

1 route

Gemini 1.5 Pro, created by Google DeepMind, is a state-of-the-art multimodal large language model that significantly advances over its predecessors in processing and analyzing large datasets across various formats like text, images, audio, and video. It features a highly extended context window of up to 2 million tokens, allowing it to maintain coherence over lengthy interactions. With over 200 billion parameters, the model excels in tasks requiring nuanced language processing, coding assistance, and advanced reasoning. Integrated into Google's platforms such as Vertex AI, Gemini 1.5 Pro also emphasizes ethical considerations, ensuring safety and appropriateness in AI deployment.

$1.25 in / $5.00 out / 1M tokens

2 routes

Stable Gemini 1.5 Pro release (February variant) optimized for complex reasoning and high-quality multimodal analysis. Supports 2M context for extended document and video processing.

No tracked provider route

Updated Pro experimental variant with refinements to reasoning depth and creative task performance.

No tracked provider route

Experimental Pro variant with enhanced reasoning and multimodal understanding for complex problem-solving tasks.

No tracked provider route

Google's most capable Gemini 3.5 model, announced at Google I/O on May 19, 2026. Features a 2M-token context window, Deep Think reasoning mode, and frontier multimodal capabilities. In limited Vertex AI enterprise preview as of June 2026; general availability expected by end of June 2026 per Google CEO Sundar Pichai. Pricing and full API documentation pending GA release.

No tracked provider route

Premium extended-reasoning GPT-5.4 variant producing smarter and more precise responses. Replacement for o3-deep-research and o4-mini-deep-research. No prompt caching discount.

$30.00 in / $180.00 out / 1M tokens

3 routes · 1 batch

OpenAI's fast, low-cost GPT-5.6 model. Luna is the affordable tier in the Sol, Terra, and Luna lineup, optimized for latency-sensitive applications such as summarization, drafting, autocomplete, and routine automation. Generally available July 9, 2026 across ChatGPT, Codex, and the OpenAI API (model ID gpt-5.6-luna). Supports text and image inputs, reasoning, tool use, prompt caching, and Batch API with a 1,050,000-token context window and 128K max output.

$1.00 in / $6.00 out / 1M tokens

2 routes · 1 batch · 1 cache

GPT-5.5 Pro is OpenAI's premium extra-compute deployment of GPT-5.5, released April 23, 2026. It uses the same underlying weights as GPT-5.5 standard with additional parallel test-time compute for harder tasks. Supports text and image inputs, reasoning effort control, tool use, structured outputs, code execution, a 1,050,000-token context window, and 128K max output. Key datapack rows: Terminal-Bench 2.1 78.2%, SWE-bench Pro 58.6%, GPQA Diamond 93.6%, ARC-AGI-2 high effort 83.3%, BrowseComp Pro compute 90.1%, and FrontierMath Tier 4 39.6%. Official pricing is $30/M input, $180/M output, $10/M batch input, and $45/M batch output; native cached input discount is not listed.

$30.00 in / $180.00 out / 1M tokens

3 routes · 1 batch

OpenAI's balanced mid-tier GPT-5.6 model. Terra delivers performance competitive with GPT-5.5 at about 2x lower cost, suited for high-volume production workloads such as customer support, document analysis, and internal tooling. Generally available July 9, 2026 across ChatGPT, Codex, and the OpenAI API (model ID gpt-5.6-terra). Supports text and image inputs, reasoning, tool use, prompt caching, and Batch API with a 1,050,000-token context window and 128K max output.

$2.50 in / $15.00 out / 1M tokens

2 routes · 1 batch · 1 cache

GPT-5.5 is OpenAI's fully retrained agentic model, released April 23, 2026. Optimised for agentic coding, computer use, knowledge work, and early scientific research. Achieves 82.7% on Terminal-Bench 2.0 (Codex CLI scaffold), 84.9% on GDPval, 58.6% on SWE-Bench Pro, 93.6% on GPQA Diamond, and 82.6% on SWE-Bench Verified (Vals.ai independent harness). Knowledge cutoff December 2025. Supports reasoning effort levels (none/low/medium/high/xhigh). Context window 1,050,000 tokens with a long-context surcharge above 272K tokens. Model ID: gpt-5.5.

$5.00 in / $30.00 out / 1M tokens

4 routes · 1 batch · 2 cache

GPT-5.4 is OpenAI's flagship frontier reasoning model, released March 5, 2026. It incorporates advances from GPT-5.3-Codex for coding and agentic workflows, and adds 'Thinking' mode with editable reasoning plans. Key capabilities include computer use (navigating interfaces via Playwright), image understanding and generation integration, full-stack web app generation, tool calling, and deep research. Knowledge cutoff is August 31, 2025. Model ID: gpt-5.4.

$2.50 in / $15.00 out / 1M tokens

4 routes · 1 batch · 3 cache

OpenAI's flagship GPT-5.6 model and highest-capability tier in the Sol, Terra, and Luna naming system. GPT-5.6 Sol is built for demanding reasoning, long-horizon coding, agentic workflows, and cybersecurity tasks, introducing max reasoning effort and ultra multi-agent mode. Generally available July 9, 2026 across ChatGPT, Codex, and the OpenAI API (model IDs gpt-5.6-sol and alias gpt-5.6). Supports text and image inputs, reasoning, tool use, code execution, prompt caching, and Batch API with a 1,050,000-token context window and 128K max output.

$5.00 in / $30.00 out / 1M tokens

2 routes · 1 batch · 1 cache

GPT-6 Astra is OpenAI's flagship GPT-6 model, announced September 3, 2026 as a new generation of intelligence for computer use, browsing, software engineering, cybersecurity, science, and professional work. Official OpenAI API id gpt-6-astra. Docs list a 1,050,000-token context window, 922,000 max input tokens, 128,000 max output tokens, Apr 30, 2026 knowledge cutoff, image+text input to text output, reasoning.effort low/medium/high/xhigh/max (none is not supported), function calling, structured outputs, prompt caching, Batch API, computer use, and code interpreter. OpenAI API Standard list is $10 per 1M input tokens and $50 per 1M output tokens. Rolling out today to a limited set of organizations / Trusted Access Program; ChatGPT Plus, Pro, Business, and Enterprise, plus broader OpenAI API and AWS availability, in the coming days. Compare it for Coding, Agents, and research. Sibling of live gpt-5.6-sol under a new family gpt-6 — do not overwrite GPT-5.6.

$10.00 in / $50.00 out / 1M tokens

1 route · 1 batch · 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 · 1 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 · 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

1 route · 1 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.

$0.090 in / $0.450 out / 1M tokens

6 routes · 1 cache

30B MoE model with 3B active parameters - superior reasoning with IMO/IOI 2025 gold-medal performance

No tracked provider route

Gemini 3.5 Flash is Google DeepMind's generally available Flash model for sustained frontier-level performance on agentic and coding tasks. It supports multimodal inputs, native thinking, tool and function calling, structured outputs, code execution, search grounding, batch processing, and long contexts up to 1M tokens.

$1.50 in / $9.00 out / 1M tokens

4 routes · 2 batch · 3 cache

Gemini 3.1 Flash-Lite is Google's generally available low-latency Gemini 3.1 model, launched May 7, 2026. It is optimized for high-volume, cost-sensitive workloads with text, image, and video inputs, a 1M token context window, and a 66K token maximum output. The GA model uses the stable API ID gemini-3.1-flash-lite and replaces gemini-3.1-flash-lite-preview, which is scheduled to shut down on May 25, 2026. Pricing is $0.25 per 1M input tokens and $1.50 per 1M output tokens.

$0.250 in / $1.50 out / 1M tokens

3 routes · 1 cache

Antigravity Agent is Google DeepMind's preview managed agent for autonomous coding and browsing workflows. Powered by Gemini 3.5 Flash, it plans, reasons, runs code, manages files, and browses the web inside a secure Google-hosted Linux sandbox through the Interactions API. It accepts text and image input, has a 1,048,576-token input context window that compacts at about 135K tokens, and supports a 65,536-token output limit. Environment compute is not billed during preview; Google describes pricing as pay-as-you-go based on underlying Gemini model tokens and tool use.

Pricing not tracked / 1M tokens

1 route

Gemini 3.8 Flash is Google DeepMind's generally available most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows, released September 2, 2026. It accepts text, image, video, audio, and PDF inputs and returns text, with a 1,048,576-token context window, up to 65,536 output tokens, and Gemini API support for thinking (low/medium/high; minimal is not supported), function calling, tool use, structured outputs, code execution, prompt caching, search grounding, URL context, computer use (preview), and batch, flex, and priority consumption. Official model ID: gemini-3.8-flash. Sibling of live gemini-3.7-flash under a new family gemini-3.8. Compare it for Coding, Agents, Long context, Vision, and JSON / Tool use.

$0.750 in / $3.75 out / 1M tokens

2 routes · 2 batch · 2 cache

Tencent Hunyuan Hy4 preview is a Mixture-of-Experts flagship language model released and open-sourced August 28, 2026. First-party Tencent release: 770B total parameters with 49B activated per token, context window exceeding 1M tokens, aimed at coding, office productivity, game development, and scientific research. Hugging Face model card (tencent/Hy4-preview) documents a 78-layer MoE backbone (256 routed experts, top-8 plus 1 shared expert), Gated DeepSeek Sparse Attention with IndexCache, iHC residual streams, native MTP speculative decoding, Apache License 2.0 weights (also Hy4-preview-FP8), and OpenAI-compatible serving via vLLM/SGLang with tool-call and reasoning parsers. Public access: Hugging Face/ModelScope/GitCode/CNB weights; API via Tencent Cloud TokenHub and OpenRouter (model id tencent/hy4-preview); also WorkBuddy, CodeBuddy, Yuanbao, and ima. Official API list pricing USD 0.834 / 2.501 per 1M input/output tokens and USD 0.042 per 1M cache hits. Sibling of seeded hy3-preview under family hunyuan. Compare it for Agents and Coding.

$0.834 in / $2.50 out / 1M tokens

2 routes · 2 cache

Xiaomi MiMo-V2-Pro language model. The larger, higher-capability model in the MiMo V2 series with an extended 1M token context window.

$1.00 in / $3.00 out / 1M tokens

2 routes · 1 cache

Specialized for browser control agents. $1.25/$10.00 (<=200K), $2.50/$15.00 (>200K). Available on AI Studio and Vertex AI; no free tier.

$1.25 in / $10.00 out / 1M tokens

2 routes

Muse Spark 1.3 is Meta Superintelligence Labs' latest Muse Spark checkpoint, released September 2, 2026. Official Meta Model API model ID: muse-spark-1.3. First-party models docs: the latest version, recommended for new work, tuned for agentic workflows (multi-step tool, browser, and long-horizon tasks) with improved coding over 1.2; default model in docs examples. Product line (dev.meta.ai): Built for long-horizon coding and agentic work. Cleaner code, fewer tokens. First-party research post: rolling out today in Muse Code and Meta Model API; previously available reasoning modes available today with max reasoning coming shortly after additional safety testing. Official table: text, image, video, audio*, PDF input and text output; 1,048,576-token context. Official quickstart limits: context 1048576, output 131072; input modalities text/image/pdf/video, output text. Audio understanding in 1.3 is currently not fully supported (use 1.2 or Muse Voice Transcribe for audio). Tool/function calling, structured outputs, prompt caching, search grounding, and reasoning_effort (minimal/low/medium/high/xhigh; none is not supported). Compare it for Coding, Agents, Long context, and Vision.

$1.25 in / $4.25 out / 1M tokens

1 route · 1 cache

Muse Spark 1.3 Contributor is the Contributor-tier catalog ID (muse-spark-1.3-contributor) of Muse Spark 1.3 on Meta Model API. Official models page lists it as a distinct Model ID on the Contributor tier with the same 1,048,576-token context and the same input modalities as muse-spark-1.3 (text, image, video, audio*, PDF) and text output. First-party pricing page lists it with its own Contributor rates. Heavily discounted token pricing in exchange for permission to use prompts and completions to train future Meta models. Audio understanding in 1.3 is currently not fully supported. Not a separately published checkpoint or weights drop. Compare it for Coding and Agents.

$0.100 in / $0.200 out / 1M tokens

1 route · 1 cache

Gemini Omni 1.1 Flash is Google DeepMind's generally available video generation and editing model, released August 27, 2026. It provides fast conversational video generation and editing through the Gemini API and Interactions API, with scene extension, interpolation, resolution upscaling, and support for video references. It accepts text, image, and video input and outputs video with native audio at 360p, 720p, 1080p, or 4K (3s–10s at 24 FPS). Official model ID: gemini-omni-1.1-flash. Compare it for Video generation.

$1.50 in / $17.50 out / 1M tokens

1 route

Gemini 3.7 Flash is Google DeepMind's generally available multimodal workhorse model for coding and agents, released August 13, 2026. It accepts text, image, video, audio, and PDF inputs and returns text, with a 1,048,576-token context window, up to 65,536 output tokens, and Gemini API support for thinking (low/medium/high; minimal is not supported), function calling, tool use, structured outputs, code execution, prompt caching, and batch processing. Official model ID: gemini-3.7-flash. Compare it for Coding, Agents, Long context, Vision, and JSON / Tool use.

$0.750 in / $3.75 out / 1M tokens

1 route · 1 batch · 1 cache

Muse Spark 1.2 is Meta Superintelligence Labs' proprietary multimodal reasoning model for agentic coding and long-context work, released August 5, 2026. It supports a 1,048,576-token context window and up to 131,072 output tokens through the Meta Model API. No public weights release at launch.

$1.25 in / $4.25 out / 1M tokens

1 route · 1 cache

Gemini 3.5 Flash-Lite is Google DeepMind's generally available multimodal model in the Gemini 3.5 family. It accepts text, image, video, audio, and PDF inputs and returns text, with a 1,048,576-token context window, up to 65,536 output tokens, and Gemini API support for code execution, prompt caching, and batch processing. Compare it for Coding, Agents, Long context, Vision, and JSON / Tool use. In Google AI Studio, select Gemini 3.5 Flash-Lite when lower token cost and high throughput are the priority; select Gemini 3.6 Flash when higher capability matters more.

$0.300 in / $2.50 out / 1M tokens

1 route

Gemini 3.6 Flash is Google DeepMind's generally available multimodal model. It accepts text, image, video, audio, and PDF inputs and returns text, with a 1,048,576-token context window, up to 65,536 output tokens, and Gemini API support for code execution, prompt caching, and batch processing. Compare it for Coding, Agents, Long context, Vision, and JSON / Tool use. In Google AI Studio, select Gemini 3.6 Flash when higher capability is the priority; select Gemini 3.5 Flash-Lite when lower token cost and high throughput matter more.

$1.50 in / $7.50 out / 1M tokens

1 route

Spark-X2.5-1.7B is the smaller SparkLLM / XHToken (iFlytek) post-trained on-device general language model in the Spark-X2.5 series. Hugging Face card XHToken/Spark-X2.5-1.7B (Apache License 2.0 LICENSE blob, Copyright 2026 XHToken) documents Spark2_5ForCausalLM with the same hybrid 3:1 sliding-window / full-attention pattern, native 1,048,576-token context, safetensors 1,707,657,216 parameters (card title 1.7B; HF size widget rounds to 2B), thinking mode, tool-call parser spark25, and Llama-Factory fine-tuning. Same first-party GitHub README as the 4B: ~20T pretrain, SFT plus RL / MOPD from base XHToken/Spark-X2.5-1.7B-Base; 200+ languages; agent/coding/reasoning on-device. Serving: SGLang, vLLM, MLX, llama.cpp, Ollama, LM Studio. Xingchen MaaS listed on SparkLLM DEV as limited-time free; first-party Token Plan docs on 2026-09-01 list Spark-X2 / X2-Agent / X2-Flash only, not X2.5 IDs or USD rates. Sibling Spark-X2.5-4B. Do not packet unreleased Spark X2.5 293B. Compare it for Agents, Coding, and Long context.

No tracked provider route

Spark-X2.5-4B is SparkLLM / XHToken (iFlytek) post-trained on-device general language model in the Spark-X2.5 series. Hugging Face card XHToken/Spark-X2.5-4B (Apache License 2.0 LICENSE blob, Copyright 2026 XHToken) documents a compact dense decoder (Spark2_5ForCausalLM) with hybrid attention: repeating 3 sliding-window layers plus 1 full-attention layer, native context up to 1,048,576 tokens (config max_position_embeddings), safetensors 4,112,079,360 parameters, thinking-mode chat template, tool-call parser spark25, and Llama-Factory fine-tuning. First-party GitHub README and HF card: pretrained ~20T tokens then SFT plus large-scale RL / MOPD from base XHToken/Spark-X2.5-4B-Base; 200+ languages; conversation, writing, translation, reasoning, coding, tool use, and agent harnesses (Codex, Claude Code, OpenClaw, Hermes). Serving recipes for SGLang, vLLM, MLX, llama.cpp, Ollama, LM Studio. Weights also listed on ModelScope, Modelers, SCNet. Xingchen MaaS API mentioned on SparkLLM DEV as limited-time free without published USD list prices or X2.5 providerModelId on first-party Token Plan as of 2026-09-01. Sibling Spark-X2.5-1.7B. Do not packet unreleased Spark X2.5 293B. Compare it for Agents, Coding, and Long context.

No tracked provider route

Llama 3 70B Gradient 1048K is Gradient's Gradient Llama 3 model. It offers a 1048K-token context window.

No tracked provider route

Llama 3 8B Gradient 1048K is Gradient's Gradient Llama 3 model. It offers a 1048K-token context window.

No tracked provider route

Llama 3.1 8B Gradient 1048K is Gradient's Gradient Llama 3 model. It offers a 1048K-token context window.

No tracked provider route

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 · 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 · 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.

$0.075 in / $0.250 out / 1M tokens

1 route · 1 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

1 route · 1 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

1 route

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 · 1 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%, Terminal-Bench 2.0 59.1% on BenchLM's independent June 2026 harness, and Chatbot Arena 1456 (2026-06-16). Current API pricing: $0.435/$0.87 per 1M input/output tokens; DeepSeek made the former 75% promotional rate permanent in May 2026.

$0.435 in / $0.870 out / 1M tokens

5 routes · 3 cache

Alibaba's closed-weight flagship language model, announced at the 2026 Alibaba Cloud Summit (May 20). Scored 56.6 on Artificial Analysis Intelligence Index at launch—highest-ranked Chinese model. 1M-token context with prompt caching (up to 90% discount). Pricing: $2.50/$7.50 per 1M tokens in/out.

$1.25 in / $3.75 out / 1M tokens

4 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

Gemini 1.5 Flash is a large language AI model by Google, crafted for speed and efficiency in high-volume scenarios 145. As a lightweight model, it's optimized for fast processing and cost-effectiveness, making it ideal for real-time applications and high-frequency tasks 567. With its multimodal capabilities, Gemini 1.5 Flash effectively processes and reasons across multiple data types, including text, images, audio, video, and PDFs 145. Despite its smaller size compared to Gemini 1.5 Pro, it excels in tasks like summarization, chat applications, and data extraction from lengthy documents, employing "knowledge distillation" to transfer essential knowledge from larger models 5. Additionally, it features an extensive context window of up to 1 million tokens, allowing it to manage large information volumes effectively 456.

$0.075 in / $0.300 out / 1M tokens

2 routes

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

1 route · 1 cache

NVIDIA's open frontier-reasoning model (550B total / 55B active MoE, hybrid Transformer-Mamba). Highest Artificial Analysis Intelligence Index for any US open model (score: 48). 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.

$0.500 in / $2.20 out / 1M tokens

1 route

Lightweight 8B variant of Gemini 1.5 Flash optimized for speed and cost-efficiency. Supports 1M token context with fast inference for real-time applications.

$0.0375 in / $0.150 out / 1M tokens

1 route

Gemini 1.5 Flash on Google Vertex AI is Google DeepMind's Gemini 1.5 model with multimodal text and image input. It offers a 1M-token context window.

$0.035 in / $0.105 out / 1M tokens

1 route

Gemini 1.5 Flash on Google Vertex AI (Extended Context) is Google DeepMind's Gemini 1.5 model with multimodal text and image input. It offers a 1M-token context window.

$0.070 in / $0.210 out / 1M tokens

1 route

Gemini 1.5 Pro on Google Vertex AI is Google DeepMind's Gemini 1.5 model with multimodal text and image input. It offers a 1M-token context window.

$0.125 in / $0.375 out / 1M tokens

1 route

Gemini 1.5 Pro on Google Vertex AI (Extended Context) is Google DeepMind's Gemini 1.5 model with multimodal text and image input. It offers a 1M-token context window.

$0.250 in / $0.750 out / 1M tokens

1 route

Google's Gemini 1.0 Ultra is a leading large language model designed for tackling highly complex tasks with advanced analytical capabilities. As the largest model in the Gemini 1.0 family, it excels in coding, mathematical reasoning, and multimodal reasoning. Its strength lies in its ability to seamlessly understand and process diverse data types, including text, code, audio, images, and video. Gemini Ultra surpasses human experts on the MMLU benchmark with a 90% score, although it has limitations in image generation and some multimodal tasks. The model features a 32,000-token context window, less than some competitors, and access is primarily through a paid subscription or via Google Cloud for developers.

$1.00 in / $3.00 out / 1M tokens

1 route

Gemini 2.0 Flash Lite Preview (02-05). Retiring June 1, 2026. Migrate to Gemini 2.5 or Gemini 3 series.

No tracked provider route

Gemini 2.0 Pro (Experimental 02-05) is Google DeepMind's Gemini 2.0 model. Its knowledge cutoff is 2024-08.

No tracked provider route

Google Gemini 2.0 Flash experimental model with 1M context for long-form understanding.

No tracked provider route

Google LearnLM experimental model optimized for educational and tutoring applications.

No tracked provider route

Stable Gemini 1.5 Flash release (February variant) optimized for high-speed processing and cost efficiency. Supports 1M context with fast token generation for real-time use.

No tracked provider route

Updated experimental 8B Flash with improvements to latency and multimodal understanding capabilities.

No tracked provider route

Experimental 8B Flash variant with optimizations for edge deployment and ultra-fast multimodal inference.

No tracked provider route

Experimental Flash variant with enhancements to multimodal capabilities and inference speed.

No tracked provider route

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

Google DeepMind's most advanced reasoning Gemini model. Part of the Gemini 3 series with frontier-class intelligence, multimodal understanding, and 1M token context window.

$1.25 in / $5.00 out / 1M tokens

2 routes

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

Amazon Nova 2 Pro is a preview text-generation model in the Amazon Nova 2 family, announced for Amazon Bedrock and made available to Amazon Nova Forge customers. It targets higher-capability general reasoning and generation workloads than Nova 2 Lite, supports a 1M-token context window, and currently has restricted preview access rather than standard public token pricing.

Pricing not tracked / 1M tokens

1 route

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

1 route · 1 cache