# ModelPickr

> Which model for a job, and what it costs per month. Specs and prices are republished from Models.dev (MIT). Data last refreshed 2026-10-14T17:43:43.286Z.

ModelPickr is a static directory at https://modelpickr.com. It keeps text models from established labs that several providers sell, scores each job separately, and estimates a monthly bill from published token prices. A benchmark row counts only when the source is the model's lab or the benchmark owner. Artificial Analysis, OpenRouter, and LLM Stats are not republished. There is no site search URL. The models table filters in the browser.

## Key pages

- [Home](https://modelpickr.com/): job picker, catalog size, and the latest price and release changes.
- [Models](https://modelpickr.com/models): every text model, with input and output price, context, provider count, release date, and capabilities.
- [Labs](https://modelpickr.com/labs): one page per lab.
- [Jobs](https://modelpickr.com/best): coding agents, long-document Q&A, and summarization.
- [Coding agents](https://modelpickr.com/best/coding-agents): Which model should I use for a coding agent, and what will it cost each month? Status: indexed.
- [Long-document Q&A](https://modelpickr.com/best/long-document-qa): Which model should I use to ask questions of documents over 200,000 tokens, and what will it cost each month? Status: indexed.
- [Cheapest summarization](https://modelpickr.com/best/cheapest-summarization): Which model is the cheapest way to summarize a steady stream of documents, and what will it cost each month? Status: draft, noindex.
- [Compare](https://modelpickr.com/compare): pairwise pages inside a model family.
- [Calculator](https://modelpickr.com/calculator): monthly bill from requests per day, tokens, and cache hit rate.
- [Changes](https://modelpickr.com/changes): snapshot diff of releases, price moves, and removals. RSS at https://modelpickr.com/changes.rss.
- [Methodology](https://modelpickr.com/methodology): quality bar, citation rule, and the per-job score.
- [Sources](https://modelpickr.com/sources): Models.dev attribution and what is not republished.
- [Newsletter](https://modelpickr.com/newsletter): weekly email on new models and price changes, via Buttondown.
- [Full extract](https://modelpickr.com/llms-full.txt): methodology, current picks, and indexable model URLs.

## Optional

- [Sitemap](https://modelpickr.com/sitemap.xml): same document as https://modelpickr.com/sitemap-index.xml.

# Methodology

The catalog is the canonical text-model list from Models.dev (https://github.com/anomalyco/models.dev, MIT), joined to provider listings. Embeddings, rerankers, and models that do not output text are omitted. Rates are USD per 1 million tokens. The reference price is the lab's own positive listing when one exists. Otherwise it is the positive provider rate closest to the median. Listings at $0 are ignored while any positive price exists.

A model clears the bar when the lab is established, at least five providers list it, it is not deprecated or alpha, and the name is not a specialized tool (OCR, embeddings, rerankers, speech, safeguard, moderation). Coding agents also require tool calls, reasoning, and 128,000 tokens of context. Long-document Q&A requires 200,000 tokens. Summarization requires 32,000 tokens. Every current job requires a numeric price and skips $0 listings.

Coding agents start from the hardest cited software-engineering benchmark (SWE-Bench Pro, then SWE-Bench Verified, then Terminal-Bench, DeepSWE, Aider Polyglot, SWE-Atlas Codebase QnA), plus tool-calling signals. Models within 4 points are one flagship band: the lower bill is the top pick and the higher bill is the premium pick. Long-document Q&A weighs the log of the context window, the input rate the long prompt pays, and a cited MRCR score. Summarization is quality minus a log of the monthly cost, with cited GPQA Diamond when the lab published one. Unversioned aliases lose points. The budget pick is a cheaper model at or below the 25th cost percentile. If the top pick is already the cheapest, there is no budget card.

OpenRouter is an internal cross-check. Its prices are not stored and not shown.

# Current picks

Data last refreshed 2026-10-14T17:43:43.286Z. 519 text models, 64 labs, 485 indexable model pages, 767 cited benchmark rows, 348 omitted because the source was not the lab or the benchmark owner.

### Coding agents

Which model should I use for a coding agent, and what will it cost each month?
https://modelpickr.com/best/coding-agents
Indexed.
The ranking keeps models from established labs that call tools, reason, and offer at least 128,000 tokens of context. The score uses cited software-engineering benchmarks from the lab or the benchmark owner, plus tool-calling signals. Models within a few points are one flagship band, and the lower monthly bill is the top pick.
- Outputs text. Embeddings and image-only models are not in the catalog.
- Lab is one of: openai, anthropic, google, meta, mistral, deepseek, xai, alibaba, moonshotai, zhipuai, cohere, amazon, nvidia, microsoft, ai21.
- Listed by at least 5 providers. A model on only the lab and a reseller does not clear this.
- Not deprecated, and not an alpha release. Beta releases stay in.
- Not a specialized model: OCR, embeddings, rerankers, speech, safeguard, or moderation, matched on the name.
- Supports tool calls.
- Supports reasoning.
- Context window of at least 128,000 tokens.
- Has a numeric input and output price.
- Reference price is not $0. A zero in Models.dev is often an unpublished price.
- A benchmark counts only when its source is the model's lab (including that lab's Hugging Face org) or the benchmark owner. Artificial Analysis, OpenRouter, and LLM Stats are dropped. When one benchmark has several cited scores, the median is used.
- Agentic-coding score: the percentile of the hardest cited software-engineering benchmark the model has, in this order: SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench, DeepSWE, Aider Polyglot, then SWE-Atlas Codebase QnA. A fallback bench is capped (0.94, 0.86, 0.80, 0.80, 0.78) so a lone terminal score cannot beat a high SWE-Bench Pro. Other cited coding benches add up to 6 points. Structured output adds 3 tool-calling points, an explicit false removes 3, and a cited Toolathlon or MCP Atlas result adds 2. Preview and snapshot names lose 5. A name with no version digit loses 8.
- The top pick is the highest job score. On coding agents, models within 4 points of that leader are treated as a flagship tie: the lower monthly bill is the top pick and the higher bill is the premium pick. Otherwise the premium pick is the best upgrade that costs more than the top pick. The budget pick is the highest job score that costs less than the top pick and sits at or below the 25th cost percentile. Output rates above $50 per 1M tokens stay out of the premium card. Summarization uses raw quality, not quality per dollar, when it chooses that upgrade. Remaining ties break to more providers, then a lower monthly cost, then a newer release date.
- top: Claude Opus 5 (anthropic/claude-opus-5) at $199 per month. Lower bill among the top cited coding scores: SWE-Bench Pro 79.2 and SWE-Bench Verified 96 (anthropic.com). https://modelpickr.com/models/anthropic/claude-opus-5
- budget: GPT-5.6 Luna (openai/gpt-5.6-luna) at $8.86 per month. Lower bill with a cited coding result: SWE-Bench Pro 62.7 and Terminal-Bench 84.7 (openai.com). https://modelpickr.com/models/openai/gpt-5.6-luna
- premium: Claude Fable 5 (anthropic/claude-fable-5) at $398 per month. Higher bill at the top of the cited coding table: SWE-Bench Pro 80.3 and Terminal-Bench 88 (anthropic.com). https://modelpickr.com/models/anthropic/claude-fable-5
When not to use it: Skip the top pick when the agent is a short script and the budget card is the bill you will actually pay, when you need open weights, or when the work is not software engineering. A cited SWE-Bench score is a coding-agent signal, not a guarantee on your repository.

### Long-document Q&A

Which model should I use to ask questions of documents over 200,000 tokens, and what will it cost each month?
https://modelpickr.com/best/long-document-qa
Indexed.
Models under 200,000 tokens of context are left out. The score weighs the context window, the input rate this long prompt pays, and a cited MRCR result from the lab. A long window is not a promise that the model uses the whole document well.
- Outputs text. Embeddings and image-only models are not in the catalog.
- Lab is one of: openai, anthropic, google, meta, mistral, deepseek, xai, alibaba, moonshotai, zhipuai, cohere, amazon, nvidia, microsoft, ai21.
- Listed by at least 5 providers. A model on only the lab and a reseller does not clear this.
- Not deprecated, and not an alpha release. Beta releases stay in.
- Not a specialized model: OCR, embeddings, rerankers, speech, safeguard, or moderation, matched on the name.
- Context window of at least 200,000 tokens.
- Has a numeric input and output price.
- Reference price is not $0. A zero in Models.dev is often an unpublished price.
- A benchmark counts only when its source is the model's lab (including that lab's Hugging Face org) or the benchmark owner. Artificial Analysis, OpenRouter, and LLM Stats are dropped. When one benchmark has several cited scores, the median is used.
- Long-document score: 100 times the log of the context window relative to 1,048,576 tokens, minus 10 times the log of one plus the input rate this workload actually pays (including a long-context tier). Compact names lose 22. Efficiency-tier descriptions lose 6. Preview and snapshot names lose 8. A name with no version digit loses 8. A cited MRCR score adds up to 24.
- The top pick is the highest job score. On coding agents, models within 4 points of that leader are treated as a flagship tie: the lower monthly bill is the top pick and the higher bill is the premium pick. Otherwise the premium pick is the best upgrade that costs more than the top pick. The budget pick is the highest job score that costs less than the top pick and sits at or below the 25th cost percentile. Output rates above $50 per 1M tokens stay out of the premium card. Summarization uses raw quality, not quality per dollar, when it chooses that upgrade. Remaining ties break to more providers, then a lower monthly cost, then a newer release date.
- top: Muse Spark 1.3 (meta/muse-spark-1.3) at $94.64 per month. Best mix of context window and the long-prompt price: 1,048,576-token window, billed at $1.25 per 1M input on this workload, MRCR 98.3. https://modelpickr.com/models/meta/muse-spark-1.3
- budget: DeepSeek V4 Flash (deepseek/deepseek-v4-flash) at $10.60 per month. Best long-context value among the cheaper models: 1,000,000-token window, billed at $0.14 per 1M input on this workload, MRCR 78.7. https://modelpickr.com/models/deepseek/deepseek-v4-flash
- premium: Qwen3.8 Max (alibaba/qwen3.8-max) at $151 per month. Best long-context mix among the models that cost more: 1,000,000-token window, billed at $2.00 per 1M input on this workload, MRCR 92.9. https://modelpickr.com/models/alibaba/qwen3.8-max
When not to use it: Skip this pick when the documents are short enough that a smaller window is cheaper, when you need retrieval over a corpus instead of one prompt, or when you want a lab-published long-context result and the card does not cite one. MRCR is one needle test, not a full reading of your files.

### Cheapest summarization

Which model is the cheapest way to summarize a steady stream of documents, and what will it cost each month?
https://modelpickr.com/best/cheapest-summarization
Draft and noindex. The top pick has no cited benchmark from its lab or from a benchmark owner, including no GPQA Diamond score. The rank is capability flags minus a log of the monthly cost, so the cheapest model that clears the bar wins without a published quality citation. This page stays noindex until that citation exists.
The score is quality minus a log of the monthly cost, with a cited GPQA Diamond result when the lab published one. The premium card uses raw quality. If the top pick is already the cheapest model, there is no separate budget card.
- Outputs text. Embeddings and image-only models are not in the catalog.
- Lab is one of: openai, anthropic, google, meta, mistral, deepseek, xai, alibaba, moonshotai, zhipuai, cohere, amazon, nvidia, microsoft, ai21.
- Listed by at least 5 providers. A model on only the lab and a reseller does not clear this.
- Not deprecated, and not an alpha release. Beta releases stay in.
- Not a specialized model: OCR, embeddings, rerankers, speech, safeguard, or moderation, matched on the name.
- Context window of at least 32,000 tokens.
- Has a numeric input and output price.
- Reference price is not $0. A zero in Models.dev is often an unpublished price.
- A benchmark counts only when its source is the model's lab (including that lab's Hugging Face org) or the benchmark owner. Artificial Analysis, OpenRouter, and LLM Stats are dropped. When one benchmark has several cited scores, the median is used.
- Summarization score: quality minus 10 times the log of the monthly cost. Doubling the bill costs 10 quality points. Quality starts at 22 and adds reasoning, structured output, tool calls, the log of the context window, and up to 18 from a cited GPQA Diamond score. General-purpose names add 14, efficiency names such as flash or mini add 6, and nano, micro, tiny, or edge names lose 16. A name with no version digit loses 8.
- The top pick is the highest job score. On coding agents, models within 4 points of that leader are treated as a flagship tie: the lower monthly bill is the top pick and the higher bill is the premium pick. Otherwise the premium pick is the best upgrade that costs more than the top pick. The budget pick is the highest job score that costs less than the top pick and sits at or below the 25th cost percentile. Output rates above $50 per 1M tokens stay out of the premium card. Summarization uses raw quality, not quality per dollar, when it chooses that upgrade. Remaining ties break to more providers, then a lower monthly cost, then a newer release date.
- top: Qwen3.7 Flash (alibaba/qwen3.7-flash) at $1.70 per month. Best quality per dollar for a steady stream of summaries: quality 54.0 at $1.70 a month, no cited GPQA Diamond score. https://modelpickr.com/models/alibaba/qwen3.7-flash
- budget: none
- premium: GPT-6 Astra (openai/gpt-6-astra) at $600 per month. Highest summary quality if you spend more: quality 79.3 before the bill, GPQA Diamond 96 (openai.com). https://modelpickr.com/models/openai/gpt-6-astra
When not to use it: A fraction of a cent per summary is the wrong trade for customer-facing copy, for a language the cheap model handles badly, or when you need a cited quality score rather than the lowest bill. The premium card is the cited upgrade.

# Indexable model URLs

- GLM-5.2 (zhipuai/glm-5.2): https://modelpickr.com/models/zhipuai/glm-5.2
- Kimi K3 (moonshotai/kimi-k3): https://modelpickr.com/models/moonshotai/kimi-k3
- GLM-5.3 (zhipuai/glm-5.3): https://modelpickr.com/models/zhipuai/glm-5.3
- GLM-5.3-Flash (zhipuai/glm-5.3-flash): https://modelpickr.com/models/zhipuai/glm-5.3-flash
- DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash): https://modelpickr.com/models/deepseek/deepseek-v4.1-flash
- DeepSeek V4 Pro (deepseek/deepseek-v4-pro): https://modelpickr.com/models/deepseek/deepseek-v4-pro
- Kimi K2.7 Code (moonshotai/kimi-k2.7-code): https://modelpickr.com/models/moonshotai/kimi-k2.7-code
- DeepSeek V4 Flash 0731 (deepseek/deepseek-v4-flash-0731): https://modelpickr.com/models/deepseek/deepseek-v4-flash-0731
- DeepSeek V4 Flash (deepseek/deepseek-v4-flash): https://modelpickr.com/models/deepseek/deepseek-v4-flash
- Kimi K2.6 (moonshotai/kimi-k2.6): https://modelpickr.com/models/moonshotai/kimi-k2.6
- Claude Opus 4.8 (anthropic/claude-opus-4-8): https://modelpickr.com/models/anthropic/claude-opus-4-8
- MiniMax-M3 (minimax/MiniMax-M3): https://modelpickr.com/models/minimax/MiniMax-M3
- Qwen3.8 27B (alibaba/qwen3.8-27b): https://modelpickr.com/models/alibaba/qwen3.8-27b
- GPT-5.5 (openai/gpt-5.5): https://modelpickr.com/models/openai/gpt-5.5
- GPT-5.6 Sol (openai/gpt-5.6-sol): https://modelpickr.com/models/openai/gpt-5.6-sol
- GLM-5.1 (zhipuai/glm-5.1): https://modelpickr.com/models/zhipuai/glm-5.1
- Claude Sonnet 4.6 (anthropic/claude-sonnet-4-6): https://modelpickr.com/models/anthropic/claude-sonnet-4-6
- GPT-5.6 Luna (openai/gpt-5.6-luna): https://modelpickr.com/models/openai/gpt-5.6-luna
- GPT OSS 120B (openai/gpt-oss-120b): https://modelpickr.com/models/openai/gpt-oss-120b
- Claude Fable 5 (anthropic/claude-fable-5): https://modelpickr.com/models/anthropic/claude-fable-5
- Claude Sonnet 5 (anthropic/claude-sonnet-5): https://modelpickr.com/models/anthropic/claude-sonnet-5
- DeepSeek V4 Pro 0813 (deepseek/deepseek-v4-pro-0813): https://modelpickr.com/models/deepseek/deepseek-v4-pro-0813
- GPT-5.6 Terra (openai/gpt-5.6-terra): https://modelpickr.com/models/openai/gpt-5.6-terra
- Claude Opus 4.7 (anthropic/claude-opus-4-7): https://modelpickr.com/models/anthropic/claude-opus-4-7
- Gemma 4 31B IT (google/gemma-4-31b-it): https://modelpickr.com/models/google/gemma-4-31b-it
- Claude Opus 5 (anthropic/claude-opus-5): https://modelpickr.com/models/anthropic/claude-opus-5
- GPT-5.4 (openai/gpt-5.4): https://modelpickr.com/models/openai/gpt-5.4
- Qwen3.6 35B-A3B (alibaba/qwen3.6-35b-a3b): https://modelpickr.com/models/alibaba/qwen3.6-35b-a3b
- Claude Opus 4.6 (anthropic/claude-opus-4-6): https://modelpickr.com/models/anthropic/claude-opus-4-6
- Gemini 3.5 Flash (google/gemini-3.5-flash): https://modelpickr.com/models/google/gemini-3.5-flash
- Claude Fable 5.1 (anthropic/claude-fable-5-1): https://modelpickr.com/models/anthropic/claude-fable-5-1
- Grok 4.6 (xai/grok-4.6): https://modelpickr.com/models/xai/grok-4.6
- Qwen3.8 Max (alibaba/qwen3.8-max): https://modelpickr.com/models/alibaba/qwen3.8-max
- Claude Opus 5.5 (anthropic/claude-opus-5-5): https://modelpickr.com/models/anthropic/claude-opus-5-5
- MiniMax-M2.7 (minimax/MiniMax-M2.7): https://modelpickr.com/models/minimax/MiniMax-M2.7
- GPT-5.4 mini (openai/gpt-5.4-mini): https://modelpickr.com/models/openai/gpt-5.4-mini
- GPT-6 Astra (openai/gpt-6-astra): https://modelpickr.com/models/openai/gpt-6-astra
- GPT-6 Luna (openai/gpt-6-luna): https://modelpickr.com/models/openai/gpt-6-luna
- Qwen3.7 Max (alibaba/qwen3.7-max): https://modelpickr.com/models/alibaba/qwen3.7-max
- GPT-6 Sol (openai/gpt-6-sol): https://modelpickr.com/models/openai/gpt-6-sol
- GPT-6.1 Sol (openai/gpt-6.1-sol): https://modelpickr.com/models/openai/gpt-6.1-sol
- GLM-5 (zhipuai/glm-5): https://modelpickr.com/models/zhipuai/glm-5
- Qwen3.7 Plus (alibaba/qwen3.7-plus): https://modelpickr.com/models/alibaba/qwen3.7-plus
- Claude Haiku 5.5 (anthropic/claude-haiku-5-5): https://modelpickr.com/models/anthropic/claude-haiku-5-5
- Claude Sonnet 5.5 (anthropic/claude-sonnet-5-5): https://modelpickr.com/models/anthropic/claude-sonnet-5-5
- Qwen3.8 Flash (alibaba/qwen3.8-flash): https://modelpickr.com/models/alibaba/qwen3.8-flash
- Gemini 3.6 Flash (google/gemini-3.6-flash): https://modelpickr.com/models/google/gemini-3.6-flash
- Gemma 4 26B A4B IT (google/gemma-4-26b-a4b-it): https://modelpickr.com/models/google/gemma-4-26b-a4b-it
- GPT-5.4 nano (openai/gpt-5.4-nano): https://modelpickr.com/models/openai/gpt-5.4-nano
- Claude Haiku 4.5 (latest) (anthropic/claude-haiku-4-5): https://modelpickr.com/models/anthropic/claude-haiku-4-5
- Gemini 3.1 Pro Preview (google/gemini-3.1-pro-preview): https://modelpickr.com/models/google/gemini-3.1-pro-preview
- Gemini 3.7 Flash (google/gemini-3.7-flash): https://modelpickr.com/models/google/gemini-3.7-flash
- Llama-3.3-70B-Instruct (meta/llama-3.3-70b-instruct): https://modelpickr.com/models/meta/llama-3.3-70b-instruct
- GPT-4.1 (openai/gpt-4.1): https://modelpickr.com/models/openai/gpt-4.1
- Grok 4.3 (xai/grok-4.3): https://modelpickr.com/models/xai/grok-4.3
- MiMo-V2.5 (xiaomi/mimo-v2.5): https://modelpickr.com/models/xiaomi/mimo-v2.5
- Qwen3.5 397B-A17B (alibaba/qwen3.5-397b-a17b): https://modelpickr.com/models/alibaba/qwen3.5-397b-a17b
- Qwen3.6 27B (alibaba/qwen3.6-27b): https://modelpickr.com/models/alibaba/qwen3.6-27b
- Gemini 3.5 Flash Lite (google/gemini-3.5-flash-lite): https://modelpickr.com/models/google/gemini-3.5-flash-lite
- Gemini 3.8 Flash (google/gemini-3.8-flash): https://modelpickr.com/models/google/gemini-3.8-flash
- GPT-5 (openai/gpt-5): https://modelpickr.com/models/openai/gpt-5
- GPT-5 Mini (openai/gpt-5-mini): https://modelpickr.com/models/openai/gpt-5-mini
- Grok 4.5 (xai/grok-4.5): https://modelpickr.com/models/xai/grok-4.5
- MiniMax-M2.5 (minimax/MiniMax-M2.5): https://modelpickr.com/models/minimax/MiniMax-M2.5
- Kimi K2.5 (moonshotai/kimi-k2.5): https://modelpickr.com/models/moonshotai/kimi-k2.5
- GPT-4.1 mini (openai/gpt-4.1-mini): https://modelpickr.com/models/openai/gpt-4.1-mini
- MiMo-V2.5-Pro (xiaomi/mimo-v2.5-pro): https://modelpickr.com/models/xiaomi/mimo-v2.5-pro
- Claude Sonnet 4.5 (latest) (anthropic/claude-sonnet-4-5): https://modelpickr.com/models/anthropic/claude-sonnet-4-5
- Inkling (thinkingmachines/inkling): https://modelpickr.com/models/thinkingmachines/inkling
- Grok 4.7 (xai/grok-4.7): https://modelpickr.com/models/xai/grok-4.7
- MiMo-V2.6-Flash (xiaomi/mimo-v2.6-flash): https://modelpickr.com/models/xiaomi/mimo-v2.6-flash
- Qwen3.8 2.4T A95B (alibaba/qwen3.8-2.4t-a95b): https://modelpickr.com/models/alibaba/qwen3.8-2.4t-a95b
- Gemini 2.5 Flash (google/gemini-2.5-flash): https://modelpickr.com/models/google/gemini-2.5-flash
- Gemini 3.1 Flash Lite (google/gemini-3.1-flash-lite): https://modelpickr.com/models/google/gemini-3.1-flash-lite
- GPT-4o mini (openai/gpt-4o-mini): https://modelpickr.com/models/openai/gpt-4o-mini
- GPT-5 Nano (openai/gpt-5-nano): https://modelpickr.com/models/openai/gpt-5-nano
- GPT-5.1 (openai/gpt-5.1): https://modelpickr.com/models/openai/gpt-5.1
- GPT-5.2 (openai/gpt-5.2): https://modelpickr.com/models/openai/gpt-5.2
- MiMo-V2.6-Pro (xiaomi/mimo-v2.6-pro): https://modelpickr.com/models/xiaomi/mimo-v2.6-pro
- GLM-4.7-Flash (zhipuai/glm-4.7-flash): https://modelpickr.com/models/zhipuai/glm-4.7-flash
- Claude Opus 4.5 (latest) (anthropic/claude-opus-4-5): https://modelpickr.com/models/anthropic/claude-opus-4-5
- Gemini 2.5 Pro (google/gemini-2.5-pro): https://modelpickr.com/models/google/gemini-2.5-pro
- Nemotron 3 Ultra 550B A55B (nvidia/nemotron-3-ultra-550b-a55b): https://modelpickr.com/models/nvidia/nemotron-3-ultra-550b-a55b
- GPT-4.1 nano (openai/gpt-4.1-nano): https://modelpickr.com/models/openai/gpt-4.1-nano
- GPT-5.3 Codex (openai/gpt-5.3-codex): https://modelpickr.com/models/openai/gpt-5.3-codex
- GPT OSS 20B (openai/gpt-oss-20b): https://modelpickr.com/models/openai/gpt-oss-20b
- Hy3 (tencent/hy3): https://modelpickr.com/models/tencent/hy3
- GLM-4.7 (zhipuai/glm-4.7): https://modelpickr.com/models/zhipuai/glm-4.7
- Qwen3.6 Plus (alibaba/qwen3.6-plus): https://modelpickr.com/models/alibaba/qwen3.6-plus
- Gemini 3 Flash Preview (google/gemini-3-flash-preview): https://modelpickr.com/models/google/gemini-3-flash-preview
- Step 3.7 Flash (stepfun/step-3.7-flash): https://modelpickr.com/models/stepfun/step-3.7-flash
- Gemini 2.5 Flash-Lite (google/gemini-2.5-flash-lite): https://modelpickr.com/models/google/gemini-2.5-flash-lite
- Nemotron 3 Super 120B A12B (nvidia/nemotron-3-super-120b-a12b): https://modelpickr.com/models/nvidia/nemotron-3-super-120b-a12b
- GPT-4o (openai/gpt-4o): https://modelpickr.com/models/openai/gpt-4o
- GPT-5.5 Pro (openai/gpt-5.5-pro): https://modelpickr.com/models/openai/gpt-5.5-pro
- GLM-4.6 (zhipuai/glm-4.6): https://modelpickr.com/models/zhipuai/glm-4.6
- Qwen3.5 122B-A10B (alibaba/qwen3.5-122b-a10b): https://modelpickr.com/models/alibaba/qwen3.5-122b-a10b
- Qwen3.6 Flash (alibaba/qwen3.6-flash): https://modelpickr.com/models/alibaba/qwen3.6-flash
- o4-mini (openai/o4-mini): https://modelpickr.com/models/openai/o4-mini
- Grok Build 0.1 (xai/grok-build-0.1): https://modelpickr.com/models/xai/grok-build-0.1
- Qwen3.5 35B-A3B (alibaba/qwen3.5-35b-a3b): https://modelpickr.com/models/alibaba/qwen3.5-35b-a3b
- Muse Spark 1.2 (meta/muse-spark-1.2): https://modelpickr.com/models/meta/muse-spark-1.2
- Mistral Small 4 (mistral/mistral-small-2603): https://modelpickr.com/models/mistral/mistral-small-2603
- GPT-5.4 Pro (openai/gpt-5.4-pro): https://modelpickr.com/models/openai/gpt-5.4-pro
- o3 (openai/o3): https://modelpickr.com/models/openai/o3
- Qwen3.5 27B (alibaba/qwen3.5-27b): https://modelpickr.com/models/alibaba/qwen3.5-27b
- DeepSeek V4 Flash Vision Exp (deepseek/deepseek-v4-flash-vision-exp): https://modelpickr.com/models/deepseek/deepseek-v4-flash-vision-exp
- Nemotron 3 Nano 30B A3B (nvidia/nemotron-3-nano-30b-a3b): https://modelpickr.com/models/nvidia/nemotron-3-nano-30b-a3b
- Hy4 preview (tencent/hy4-preview): https://modelpickr.com/models/tencent/hy4-preview
- GLM-5-Turbo (zhipuai/glm-5-turbo): https://modelpickr.com/models/zhipuai/glm-5-turbo
- DeepSeek V3.2 (deepseek/deepseek-v3.2): https://modelpickr.com/models/deepseek/deepseek-v3.2
- Muse Spark 1.3 (meta/muse-spark-1.3): https://modelpickr.com/models/meta/muse-spark-1.3
- o3-mini (openai/o3-mini): https://modelpickr.com/models/openai/o3-mini
- Qwen3 32B (alibaba/qwen3-32b): https://modelpickr.com/models/alibaba/qwen3-32b
- Qwen3-Next 80B-A3B Instruct (alibaba/qwen3-next-80b-a3b-instruct): https://modelpickr.com/models/alibaba/qwen3-next-80b-a3b-instruct
- Qwen3.5 9B (alibaba/qwen3.5-9b): https://modelpickr.com/models/alibaba/qwen3.5-9b
- Gemini 4 Argon (google/gemini-4-argon): https://modelpickr.com/models/google/gemini-4-argon
- Muse Spark 1.1 (meta/muse-spark-1.1): https://modelpickr.com/models/meta/muse-spark-1.1
- Devstral 2 (mistral/devstral-2512): https://modelpickr.com/models/mistral/devstral-2512
- Mistral Large 3 (mistral/mistral-large-2512): https://modelpickr.com/models/mistral/mistral-large-2512
- GLM-4.5 (zhipuai/glm-4.5): https://modelpickr.com/models/zhipuai/glm-4.5
- GLM-4.5-Air (zhipuai/glm-4.5-air): https://modelpickr.com/models/zhipuai/glm-4.5-air
- GLM-5V-Turbo (zhipuai/glm-5v-turbo): https://modelpickr.com/models/zhipuai/glm-5v-turbo
- Qwen3-Coder 30B-A3B Instruct (alibaba/qwen3-coder-30b-a3b-instruct): https://modelpickr.com/models/alibaba/qwen3-coder-30b-a3b-instruct
- Qwen3 Max (alibaba/qwen3-max): https://modelpickr.com/models/alibaba/qwen3-max
- MiniMax-M2.7-highspeed (minimax/MiniMax-M2.7-highspeed): https://modelpickr.com/models/minimax/MiniMax-M2.7-highspeed
- Step 5 Preview (stepfun/step-5-preview): https://modelpickr.com/models/stepfun/step-5-preview
- GLM-4.5V (zhipuai/glm-4.5v): https://modelpickr.com/models/zhipuai/glm-4.5v
- DeepSeek-R1 (deepseek/deepseek-r1): https://modelpickr.com/models/deepseek/deepseek-r1
- Gemma 3 27B IT (google/gemma-3-27b-it): https://modelpickr.com/models/google/gemma-3-27b-it
- Muse Glimmer 30B (meta/muse-glimmer-30b): https://modelpickr.com/models/meta/muse-glimmer-30b
- MiniMax-M2 (minimax/MiniMax-M2): https://modelpickr.com/models/minimax/MiniMax-M2
- MiniMax-M2.1 (minimax/MiniMax-M2.1): https://modelpickr.com/models/minimax/MiniMax-M2.1
- Kimi K2.7 Code Highspeed (moonshotai/kimi-k2.7-code-highspeed): https://modelpickr.com/models/moonshotai/kimi-k2.7-code-highspeed
- Nemotron 3.5 Lightning 30B A3B (nvidia/nemotron-3.5-lightning): https://modelpickr.com/models/nvidia/nemotron-3.5-lightning
- GPT-4 Turbo (openai/gpt-4-turbo): https://modelpickr.com/models/openai/gpt-4-turbo
- GPT-5 Pro (openai/gpt-5-pro): https://modelpickr.com/models/openai/gpt-5-pro
- GLM-4.6V (zhipuai/glm-4.6v): https://modelpickr.com/models/zhipuai/glm-4.6v
- Qwen3 Coder Next (alibaba/qwen3-coder-next): https://modelpickr.com/models/alibaba/qwen3-coder-next
- Qwen3 VL 235B A22B Instruct (alibaba/qwen3-vl-235b-a22b-instruct): https://modelpickr.com/models/alibaba/qwen3-vl-235b-a22b-instruct
- Qwen3.7 Flash (alibaba/qwen3.7-flash): https://modelpickr.com/models/alibaba/qwen3.7-flash
- Claude Haiku 4.5 (anthropic/claude-haiku-4-5-20251001): https://modelpickr.com/models/anthropic/claude-haiku-4-5-20251001
- Gemini 3.1 Pro Preview Custom Tools (google/gemini-3.1-pro-preview-customtools): https://modelpickr.com/models/google/gemini-3.1-pro-preview-customtools
- GPT-3.5-turbo (openai/gpt-3.5-turbo): https://modelpickr.com/models/openai/gpt-3.5-turbo
- Fugu Ultra (sakana/fugu-ultra): https://modelpickr.com/models/sakana/fugu-ultra
- Inkling Small (thinkingmachines/inkling-small): https://modelpickr.com/models/thinkingmachines/inkling-small
- Qwen Plus (alibaba/qwen-plus): https://modelpickr.com/models/alibaba/qwen-plus
- Qwen3 235B-A22B Instruct 2507 (alibaba/qwen3-235b-a22b-instruct-2507): https://modelpickr.com/models/alibaba/qwen3-235b-a22b-instruct-2507
- Qwen3 Coder Flash (alibaba/qwen3-coder-flash): https://modelpickr.com/models/alibaba/qwen3-coder-flash
- Qwen3.5 Plus (alibaba/qwen3.5-plus): https://modelpickr.com/models/alibaba/qwen3.5-plus
- Seed 2.0 Code (bytedance-seed/seed-2.0-code): https://modelpickr.com/models/bytedance-seed/seed-2.0-code
- Nano Banana Pro (google/gemini-3-pro-image): https://modelpickr.com/models/google/gemini-3-pro-image
- Nano Banana 2 (google/gemini-3.1-flash-image): https://modelpickr.com/models/google/gemini-3.1-flash-image
- Mistral Medium 3.5 (mistral/mistral-medium-2604): https://modelpickr.com/models/mistral/mistral-medium-2604
- Kimi K2 Thinking (moonshotai/kimi-k2-thinking): https://modelpickr.com/models/moonshotai/kimi-k2-thinking
- GPT-5.2 Codex (openai/gpt-5.2-codex): https://modelpickr.com/models/openai/gpt-5.2-codex
- Grok 4.20 (Non-Reasoning) (xai/grok-4.20-0309-non-reasoning): https://modelpickr.com/models/xai/grok-4.20-0309-non-reasoning
- Grok 4.20 (Reasoning) (xai/grok-4.20-0309-reasoning): https://modelpickr.com/models/xai/grok-4.20-0309-reasoning
- Qwen3-Next 80B-A3B (Thinking) (alibaba/qwen3-next-80b-a3b-thinking): https://modelpickr.com/models/alibaba/qwen3-next-80b-a3b-thinking
- Qwen3.8 Omni Flash (alibaba/qwen3.8-omni-flash): https://modelpickr.com/models/alibaba/qwen3.8-omni-flash
- Claude Opus 4.5 (anthropic/claude-opus-4-5-20251101): https://modelpickr.com/models/anthropic/claude-opus-4-5-20251101
- Claude Sonnet 4.5 (anthropic/claude-sonnet-4-5-20250929): https://modelpickr.com/models/anthropic/claude-sonnet-4-5-20250929
- Gemini 3.1 Flash Lite Preview (google/gemini-3.1-flash-lite-preview): https://modelpickr.com/models/google/gemini-3.1-flash-lite-preview
- Llama-3.1-8B-Instruct (meta/llama-3.1-8b-instruct): https://modelpickr.com/models/meta/llama-3.1-8b-instruct
- GPT-5.1 Codex (openai/gpt-5.1-codex): https://modelpickr.com/models/openai/gpt-5.1-codex
- GPT-5.1 Codex mini (openai/gpt-5.1-codex-mini): https://modelpickr.com/models/openai/gpt-5.1-codex-mini
- GPT-5.2 Pro (openai/gpt-5.2-pro): https://modelpickr.com/models/openai/gpt-5.2-pro
- o1 (openai/o1): https://modelpickr.com/models/openai/o1
- Qwen3-Coder 480B-A35B Instruct (alibaba/qwen3-coder-480b-a35b-instruct): https://modelpickr.com/models/alibaba/qwen3-coder-480b-a35b-instruct
- Qwen3.5 Flash (alibaba/qwen3.5-flash): https://modelpickr.com/models/alibaba/qwen3.5-flash
- Seed 2.0 Mini (bytedance-seed/seed-2.0-mini): https://modelpickr.com/models/bytedance-seed/seed-2.0-mini
- DeepSeek-V3.1 (deepseek/deepseek-v3.1): https://modelpickr.com/models/deepseek/deepseek-v3.1
- Nano Banana (google/gemini-2.5-flash-image): https://modelpickr.com/models/google/gemini-2.5-flash-image
- Gemma 3 12B IT (google/gemma-3-12b-it): https://modelpickr.com/models/google/gemma-3-12b-it
- Codestral 25.08 (mistral/codestral-2508): https://modelpickr.com/models/mistral/codestral-2508
- Mistral Large 4 (mistral/mistral-large-4): https://modelpickr.com/models/mistral/mistral-large-4
- Nemotron 3 Nano Omni 30B A3B Reasoning (nvidia/nemotron-3-nano-omni-30b-a3b-reasoning): https://modelpickr.com/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
- GPT-4 (openai/gpt-4): https://modelpickr.com/models/openai/gpt-4
- GPT-4o (2024-11-20) (openai/gpt-4o-2024-11-20): https://modelpickr.com/models/openai/gpt-4o-2024-11-20
- GPT-5.1 Codex Max (openai/gpt-5.1-codex-max): https://modelpickr.com/models/openai/gpt-5.1-codex-max
- GPT OSS Safeguard 20B (openai/gpt-oss-safeguard-20b): https://modelpickr.com/models/openai/gpt-oss-safeguard-20b
- Step 3.5 Flash (stepfun/step-3.5-flash): https://modelpickr.com/models/stepfun/step-3.5-flash
- MiMo-V2.6-Pro-UltraSpeed (xiaomi/mimo-v2.6-pro-ultraspeed): https://modelpickr.com/models/xiaomi/mimo-v2.6-pro-ultraspeed
- GLM-4.7-FlashX (zhipuai/glm-4.7-flashx): https://modelpickr.com/models/zhipuai/glm-4.7-flashx
- Qwen Max (alibaba/qwen-max): https://modelpickr.com/models/alibaba/qwen-max
- Qwen3 VL 30B A3B Instruct (alibaba/qwen3-vl-30b-a3b-instruct): https://modelpickr.com/models/alibaba/qwen3-vl-30b-a3b-instruct
- Qwen3.8 Max Preview (alibaba/qwen3.8-max-preview): https://modelpickr.com/models/alibaba/qwen3.8-max-preview
- Seed 2.0 Lite (bytedance-seed/seed-2.0-lite): https://modelpickr.com/models/bytedance-seed/seed-2.0-lite
- Command R+ (cohere/command-r-plus-08-2024): https://modelpickr.com/models/cohere/command-r-plus-08-2024
- Nano Banana 2 Lite (google/gemini-3.1-flash-lite-image): https://modelpickr.com/models/google/gemini-3.1-flash-lite-image
- Gemma 3 4B IT (google/gemma-3-4b-it): https://modelpickr.com/models/google/gemma-3-4b-it
- Mistral Large (latest) (mistral/mistral-large-latest): https://modelpickr.com/models/mistral/mistral-large-latest
- GPT-4o (2024-08-06) (openai/gpt-4o-2024-08-06): https://modelpickr.com/models/openai/gpt-4o-2024-08-06
- Qwen Flash (alibaba/qwen-flash): https://modelpickr.com/models/alibaba/qwen-flash
- Qwen3 30B A3B (alibaba/qwen3-30b-a3b): https://modelpickr.com/models/alibaba/qwen3-30b-a3b
- Qwen3-VL Plus (alibaba/qwen3-vl-plus): https://modelpickr.com/models/alibaba/qwen3-vl-plus
- Qwen3.6 Max Preview (alibaba/qwen3.6-max-preview): https://modelpickr.com/models/alibaba/qwen3.6-max-preview
- Claude Opus 4.1 (latest) (anthropic/claude-opus-4-1): https://modelpickr.com/models/anthropic/claude-opus-4-1
- Claude Opus 4.1 (anthropic/claude-opus-4-1-20250805): https://modelpickr.com/models/anthropic/claude-opus-4-1-20250805
- Claude Sonnet 4 (anthropic/claude-sonnet-4-20250514): https://modelpickr.com/models/anthropic/claude-sonnet-4-20250514
- Nano Banana Pro Preview (google/gemini-3-pro-image-preview): https://modelpickr.com/models/google/gemini-3-pro-image-preview
- Nano Banana 2 Preview (google/gemini-3.1-flash-image-preview): https://modelpickr.com/models/google/gemini-3.1-flash-image-preview
- Llama 4 Maverick 17B Instruct (meta/llama-4-maverick-17b-instruct): https://modelpickr.com/models/meta/llama-4-maverick-17b-instruct
- MiniMax-M2.5-highspeed (minimax/MiniMax-M2.5-highspeed): https://modelpickr.com/models/minimax/MiniMax-M2.5-highspeed
- Mistral Nemo (mistral/mistral-nemo): https://modelpickr.com/models/mistral/mistral-nemo
- Nemotron 3.5 Content Safety (nvidia/nemotron-3.5-content-safety): https://modelpickr.com/models/nvidia/nemotron-3.5-content-safety
- o3-pro (openai/o3-pro): https://modelpickr.com/models/openai/o3-pro
- Sonar (perplexity/sonar): https://modelpickr.com/models/perplexity/sonar
- Fugu Max (sakana/fugu-max): https://modelpickr.com/models/sakana/fugu-max
- Qwen3 235B-A22B (alibaba/qwen3-235b-a22b): https://modelpickr.com/models/alibaba/qwen3-235b-a22b
- Qwen3 VL 235B A22B Thinking (alibaba/qwen3-vl-235b-a22b-thinking): https://modelpickr.com/models/alibaba/qwen3-vl-235b-a22b-thinking
- Qwen3.8 Max 0902 (alibaba/qwen3.8-max-0902): https://modelpickr.com/models/alibaba/qwen3.8-max-0902
- Trinity Large Thinking (arcee-ai/trinity-large-thinking): https://modelpickr.com/models/arcee-ai/trinity-large-thinking
- Command R (cohere/command-r-08-2024): https://modelpickr.com/models/cohere/command-r-08-2024
- Command R7B (cohere/command-r7b-12-2024): https://modelpickr.com/models/cohere/command-r7b-12-2024
- DeepSeek Chat (deepseek/deepseek-chat): https://modelpickr.com/models/deepseek/deepseek-chat
- DeepSeek-V3 (deepseek/deepseek-v3): https://modelpickr.com/models/deepseek/deepseek-v3
- Gemini Embedding 001 (google/gemini-embedding-001): https://modelpickr.com/models/google/gemini-embedding-001
- Gemini Flash Latest (google/gemini-flash-latest): https://modelpickr.com/models/google/gemini-flash-latest
- Ling 3.1 Flash (inclusionai/ling-3.1-flash): https://modelpickr.com/models/inclusionai/ling-3.1-flash
- LongCat-2.0 (meituan/longcat-2.0): https://modelpickr.com/models/meituan/longcat-2.0
- Llama 4 Scout 17B Instruct (meta/llama-4-scout-17b-instruct): https://modelpickr.com/models/meta/llama-4-scout-17b-instruct
- Muse Wonder (meta/muse-wonder-1.0): https://modelpickr.com/models/meta/muse-wonder-1.0
- Ministral 3 14B 2512 (mistral/ministral-14b-2512): https://modelpickr.com/models/mistral/ministral-14b-2512
- Ministral 3 3B 2512 (mistral/ministral-3b-2512): https://modelpickr.com/models/mistral/ministral-3b-2512
- Ministral 3 8B 2512 (mistral/ministral-8b-2512): https://modelpickr.com/models/mistral/ministral-8b-2512
- Mistral Medium 3 (mistral/mistral-medium-2505): https://modelpickr.com/models/mistral/mistral-medium-2505
- Mistral Small 3 (mistral/mistral-small-24b-instruct-2501): https://modelpickr.com/models/mistral/mistral-small-24b-instruct-2501
- Mistral Small 3.2 (mistral/mistral-small-2506): https://modelpickr.com/models/mistral/mistral-small-2506
- GPT-4o (2024-05-13) (openai/gpt-4o-2024-05-13): https://modelpickr.com/models/openai/gpt-4o-2024-05-13
- GPT OSS Safeguard 120B (openai/gpt-oss-safeguard-120b): https://modelpickr.com/models/openai/gpt-oss-safeguard-120b
- o1-pro (openai/o1-pro): https://modelpickr.com/models/openai/o1-pro
- Sonar Pro (perplexity/sonar-pro): https://modelpickr.com/models/perplexity/sonar-pro
- Laguna S 2.1 (poolside/laguna-s-2.1): https://modelpickr.com/models/poolside/laguna-s-2.1
- MiMo-V2-Pro (xiaomi/mimo-v2-pro): https://modelpickr.com/models/xiaomi/mimo-v2-pro
- GLM-4.6V-Flash (zhipuai/glm-4.6v-flash): https://modelpickr.com/models/zhipuai/glm-4.6v-flash
- Qwen3 Coder Plus (alibaba/qwen3-coder-plus): https://modelpickr.com/models/alibaba/qwen3-coder-plus
- Qwen3.8 Flash Next (alibaba/qwen3.8-flash-next): https://modelpickr.com/models/alibaba/qwen3.8-flash-next
- Qwen 3.8 Max Prime (alibaba/qwen3.8-max-prime): https://modelpickr.com/models/alibaba/qwen3.8-max-prime
- Seed 2.0 Pro (bytedance-seed/seed-2.0-pro): https://modelpickr.com/models/bytedance-seed/seed-2.0-pro
- Seed 2.1 Turbo (bytedance-seed/seed-2.1-turbo): https://modelpickr.com/models/bytedance-seed/seed-2.1-turbo
- DeepSeek R1 0528 (deepseek/deepseek-r1-0528): https://modelpickr.com/models/deepseek/deepseek-r1-0528
- DeepSeek V3 0324 (deepseek/deepseek-v3-0324): https://modelpickr.com/models/deepseek/deepseek-v3-0324
- Gemini Embedding 2 (google/gemini-embedding-2): https://modelpickr.com/models/google/gemini-embedding-2
- Gemini Flash-Lite Latest (google/gemini-flash-lite-latest): https://modelpickr.com/models/google/gemini-flash-lite-latest
- Nano Banana 2.1 (google/gemini-nano-banana-2.1): https://modelpickr.com/models/google/gemini-nano-banana-2.1
- Mistral Medium 3 (mistral/mistral-medium-3): https://modelpickr.com/models/mistral/mistral-medium-3
- Mistral Medium 3.5 (mistral/mistral-medium-3-5): https://modelpickr.com/models/mistral/mistral-medium-3-5
- Mistral Medium (latest) (mistral/mistral-medium-latest): https://modelpickr.com/models/mistral/mistral-medium-latest
- Mistral Small 3.1 24B (mistral/mistral-small-3.1-24b-instruct): https://modelpickr.com/models/mistral/mistral-small-3.1-24b-instruct
- Mistral Small 3.2 24B (mistral/mistral-small-3.2-24b-instruct): https://modelpickr.com/models/mistral/mistral-small-3.2-24b-instruct
- Voxtral Small 24B 2507 (mistral/voxtral-small-24b-2507): https://modelpickr.com/models/mistral/voxtral-small-24b-2507
- Kimi K2 Instruct 0905 (moonshotai/kimi-k2-0905): https://modelpickr.com/models/moonshotai/kimi-k2-0905
- Step 3.5 Flash 2603 (stepfun/step-3.5-flash-2603): https://modelpickr.com/models/stepfun/step-3.5-flash-2603
- Hy3 preview (tencent/hy3-preview): https://modelpickr.com/models/tencent/hy3-preview
- GLM-4.5-Flash (zhipuai/glm-4.5-flash): https://modelpickr.com/models/zhipuai/glm-4.5-flash
- Qwen MT Plus (alibaba/qwen-mt-plus): https://modelpickr.com/models/alibaba/qwen-mt-plus
- Qwen Turbo (alibaba/qwen-turbo): https://modelpickr.com/models/alibaba/qwen-turbo
- Qwen2.5-Coder-32B-Instruct (alibaba/qwen2.5-coder-32b-instruct): https://modelpickr.com/models/alibaba/qwen2.5-coder-32b-instruct
- Claude Opus 4 (anthropic/claude-opus-4-20250514): https://modelpickr.com/models/anthropic/claude-opus-4-20250514
- Command A (cohere/command-a): https://modelpickr.com/models/cohere/command-a
- MythoMax L2 13B (gryphe/mythomax-l2-13b): https://modelpickr.com/models/gryphe/mythomax-l2-13b
- Mercury 2 (inception/mercury-2): https://modelpickr.com/models/inception/mercury-2
- Llama-3.1-70B-Instruct (meta/llama-3.1-70b-instruct): https://modelpickr.com/models/meta/llama-3.1-70b-instruct
- Llama 3.2 1B Instruct (meta/llama-3.2-1b-instruct): https://modelpickr.com/models/meta/llama-3.2-1b-instruct
- MiniMax-M2 Her (minimax/MiniMax-M2-Her): https://modelpickr.com/models/minimax/MiniMax-M2-Her
- Magistral Medium (latest) (mistral/magistral-medium-latest): https://modelpickr.com/models/mistral/magistral-medium-latest
- Ministral 3 14B (mistral/ministral-3-14b-instruct-2512): https://modelpickr.com/models/mistral/ministral-3-14b-instruct-2512
- Mistral Large (mistral/mistral-large): https://modelpickr.com/models/mistral/mistral-large
- Mistral Large 2407 (mistral/mistral-large-2407): https://modelpickr.com/models/mistral/mistral-large-2407
- Mistral Medium 3.1 (mistral/mistral-medium-3.1): https://modelpickr.com/models/mistral/mistral-medium-3.1
- Saba (mistral/mistral-saba): https://modelpickr.com/models/mistral/mistral-saba
- Mistral Small (latest) (mistral/mistral-small-latest): https://modelpickr.com/models/mistral/mistral-small-latest
- Mixtral 8x22B Instruct (mistral/mixtral-8x22b-instruct): https://modelpickr.com/models/mistral/mixtral-8x22b-instruct
- Pixtral 12B (mistral/pixtral-12b): https://modelpickr.com/models/mistral/pixtral-12b
- Voxtral Small (latest) (mistral/voxtral-small-latest): https://modelpickr.com/models/mistral/voxtral-small-latest
- Kimi K2 0711 (moonshotai/kimi-k2): https://modelpickr.com/models/moonshotai/kimi-k2
- Nemotron Nano 12B v2 VL (nvidia/nemotron-nano-12b-v2-vl): https://modelpickr.com/models/nvidia/nemotron-nano-12b-v2-vl
- Nemotron Nano 9B v2 (nvidia/nemotron-nano-9b-v2): https://modelpickr.com/models/nvidia/nemotron-nano-9b-v2
- GPT-5.3 Chat (latest) (openai/gpt-5.3-chat-latest): https://modelpickr.com/models/openai/gpt-5.3-chat-latest
- Sonar Reasoning Pro (perplexity/sonar-reasoning-pro): https://modelpickr.com/models/perplexity/sonar-reasoning-pro
- Laguna XS 2.1 (poolside/laguna-xs-2.1): https://modelpickr.com/models/poolside/laguna-xs-2.1
- Fugu Ultra v2 (sakana/fugu-ultra-v2): https://modelpickr.com/models/sakana/fugu-ultra-v2
- Sakana Namazu (sakana/sakana-namazu): https://modelpickr.com/models/sakana/sakana-namazu
- Solar Pro 4 (upstage/solar-pro4): https://modelpickr.com/models/upstage/solar-pro4
- Qwen-VL Max (alibaba/qwen-vl-max): https://modelpickr.com/models/alibaba/qwen-vl-max
- Nova Lite (amazon/nova-lite): https://modelpickr.com/models/amazon/nova-lite
- Nova Lite 1.0 (amazon/nova-lite-v1): https://modelpickr.com/models/amazon/nova-lite-v1
- Nova Micro (amazon/nova-micro): https://modelpickr.com/models/amazon/nova-micro
- Nova Pro (amazon/nova-pro): https://modelpickr.com/models/amazon/nova-pro
- Nova Pro 1.0 (amazon/nova-pro-v1): https://modelpickr.com/models/amazon/nova-pro-v1
- Claude Sonnet 3.7 (anthropic/claude-3-7-sonnet-20250219): https://modelpickr.com/models/anthropic/claude-3-7-sonnet-20250219
- Seed 1.6 Flash (bytedance-seed/seed-1-6-flash): https://modelpickr.com/models/bytedance-seed/seed-1-6-flash
- Seed Evolving (bytedance-seed/seed-evolving): https://modelpickr.com/models/bytedance-seed/seed-evolving
- Command A (cohere/command-a-03-2025): https://modelpickr.com/models/cohere/command-a-03-2025
- Command A Reasoning (cohere/command-a-reasoning-08-2025): https://modelpickr.com/models/cohere/command-a-reasoning-08-2025
- DeepSeek V3 0324 (deepseek/deepseek-chat-v3-0324): https://modelpickr.com/models/deepseek/deepseek-chat-v3-0324
- DeepSeek OCR 2 (deepseek/deepseek-ocr-2): https://modelpickr.com/models/deepseek/deepseek-ocr-2
- DeepSeek Reasoner (deepseek/deepseek-reasoner): https://modelpickr.com/models/deepseek/deepseek-reasoner
- DeepSeek V4 Flash 0423 (deepseek/deepseek-v4-flash-0423): https://modelpickr.com/models/deepseek/deepseek-v4-flash-0423
- Gemini 3 Pro Preview (google/gemini-3-pro-preview): https://modelpickr.com/models/google/gemini-3-pro-preview
- Gemma 2 27B (google/gemma-2-27b-it): https://modelpickr.com/models/google/gemma-2-27b-it
- Lyria 3 Clip Preview (google/lyria-3-clip-preview): https://modelpickr.com/models/google/lyria-3-clip-preview
- Lyria 3 Pro Preview (google/lyria-3-pro-preview): https://modelpickr.com/models/google/lyria-3-pro-preview
- Mercury 2.5 (inception/mercury-2.5): https://modelpickr.com/models/inception/mercury-2.5
- Ling 3.0 Flash (inclusionai/ling-3.0-flash): https://modelpickr.com/models/inclusionai/ling-3.0-flash
- Ling 3.0 Flash Fin (inclusionai/ling-3.0-flash-fin): https://modelpickr.com/models/inclusionai/ling-3.0-flash-fin
- LongCat-2.5-Preview (meituan/longcat-2.5-preview): https://modelpickr.com/models/meituan/longcat-2.5-preview
- Llama-3.2-3B (meta/llama-3.2-3b): https://modelpickr.com/models/meta/llama-3.2-3b
- WizardLM 2 8x22B (microsoft/wizardlm-2-8x22b): https://modelpickr.com/models/microsoft/wizardlm-2-8x22b
- Codestral (latest) (mistral/codestral-latest): https://modelpickr.com/models/mistral/codestral-latest
- Devstral 2 (latest) (mistral/devstral-medium-latest): https://modelpickr.com/models/mistral/devstral-medium-latest
- Ministral 3 3B (mistral/ministral-3-3b-instruct-2512): https://modelpickr.com/models/mistral/ministral-3-3b-instruct-2512
- Ministral 3 8B (mistral/ministral-3-8b-instruct-2512): https://modelpickr.com/models/mistral/ministral-3-8b-instruct-2512
- Mistral Small 3.1 24B (mistral/mistral-small-3-1-24b-instruct-2503): https://modelpickr.com/models/mistral/mistral-small-3-1-24b-instruct-2503
- Pixtral Large (25.02) (mistral/pixtral-large-2502): https://modelpickr.com/models/mistral/pixtral-large-2502
- Kimi K2 Instruct (moonshotai/kimi-k2-instruct): https://modelpickr.com/models/moonshotai/kimi-k2-instruct
- Hermes 3 405B Instruct (nousresearch/hermes-3-llama-3.1-405b): https://modelpickr.com/models/nousresearch/hermes-3-llama-3.1-405b
- Hermes 3 70B Instruct (nousresearch/hermes-3-llama-3.1-70b): https://modelpickr.com/models/nousresearch/hermes-3-llama-3.1-70b
- Llama 3.1 Nemotron 70B Instruct (nvidia/llama-3.1-nemotron-70b-instruct): https://modelpickr.com/models/nvidia/llama-3.1-nemotron-70b-instruct
- GPT-5-Codex (openai/gpt-5-codex): https://modelpickr.com/models/openai/gpt-5-codex
- GPT-5.2 Chat (openai/gpt-5.2-chat-latest): https://modelpickr.com/models/openai/gpt-5.2-chat-latest
- GPT-5.4 Image 2 (openai/gpt-5.4-image-2): https://modelpickr.com/models/openai/gpt-5.4-image-2
- GPT-5.5 Instant (openai/gpt-5.5-instant): https://modelpickr.com/models/openai/gpt-5.5-instant
- Whisper 3 Large (openai/whisper-large-v3): https://modelpickr.com/models/openai/whisper-large-v3
- Sonar Deep Research (perplexity/sonar-deep-research): https://modelpickr.com/models/perplexity/sonar-deep-research
- Sarvam 105B (sarvam/sarvam-105b): https://modelpickr.com/models/sarvam/sarvam-105b
- Apertus 70B (swiss-ai/apertus-70b): https://modelpickr.com/models/swiss-ai/apertus-70b
- Hy-MT2-1.8B (tencent/hy-mt2-1.8b): https://modelpickr.com/models/tencent/hy-mt2-1.8b
- Hy-MT2-30B-A3B (tencent/hy-mt2-30b-a3b): https://modelpickr.com/models/tencent/hy-mt2-30b-a3b
- Hy-MT2-7B (tencent/hy-mt2-7b): https://modelpickr.com/models/tencent/hy-mt2-7b
- Solar Pro 3 (upstage/solar-pro3): https://modelpickr.com/models/upstage/solar-pro3
- MiMo-V2-Flash (xiaomi/mimo-v2-flash): https://modelpickr.com/models/xiaomi/mimo-v2-flash
- Aion-3.0 (aion-labs/aion-3.0): https://modelpickr.com/models/aion-labs/aion-3.0
- Aion-3.0-Mini (aion-labs/aion-3.0-mini): https://modelpickr.com/models/aion-labs/aion-3.0-mini
- Aion-RP 1.0 (8B) (aion-labs/aion-rp-llama-3.1-8b): https://modelpickr.com/models/aion-labs/aion-rp-llama-3.1-8b
- Gemma-SEA-LION-v4-27B-IT (aisingapore/gemma-sea-lion-v4-27b-it): https://modelpickr.com/models/aisingapore/gemma-sea-lion-v4-27b-it
- Qwen-Omni Turbo (alibaba/qwen-omni-turbo): https://modelpickr.com/models/alibaba/qwen-omni-turbo
- Qwen-VL Plus (alibaba/qwen-vl-plus): https://modelpickr.com/models/alibaba/qwen-vl-plus
- Qwen2.5-VL 72B Instruct (alibaba/qwen2-5-vl-72b-instruct): https://modelpickr.com/models/alibaba/qwen2-5-vl-72b-instruct
- Qwen3 Max Preview (alibaba/qwen3-max-preview): https://modelpickr.com/models/alibaba/qwen3-max-preview
- Qwen3 VL Flash (Alibaba Cloud) (alibaba/qwen3-vl-flash): https://modelpickr.com/models/alibaba/qwen3-vl-flash
- QwQ 32B (alibaba/qwq-32b): https://modelpickr.com/models/alibaba/qwq-32b
- QwQ Plus (alibaba/qwq-plus): https://modelpickr.com/models/alibaba/qwq-plus
- Nova 2 Lite (amazon/nova-2-lite): https://modelpickr.com/models/amazon/nova-2-lite
- Nova Micro 1.0 (amazon/nova-micro-v1): https://modelpickr.com/models/amazon/nova-micro-v1
- Magnum v4 72B (anthracite-org/magnum-v4-72b): https://modelpickr.com/models/anthracite-org/magnum-v4-72b
- Claude Mythos 5 (anthropic/claude-mythos-5): https://modelpickr.com/models/anthropic/claude-mythos-5
- Claude Sonnet 4 (latest) (anthropic/claude-sonnet-4-0): https://modelpickr.com/models/anthropic/claude-sonnet-4-0
- Seed 1.6 (bytedance-seed/seed-1-6): https://modelpickr.com/models/bytedance-seed/seed-1-6
- Seed 1.6 Vision (bytedance-seed/seed-1-6-vision): https://modelpickr.com/models/bytedance-seed/seed-1-6-vision
- Seed 1.8 (bytedance-seed/seed-1-8): https://modelpickr.com/models/bytedance-seed/seed-1-8
- Seed 2.1 Pro (bytedance-seed/seed-2.1-pro): https://modelpickr.com/models/bytedance-seed/seed-2.1-pro
- Seed Character (bytedance-seed/seed-character): https://modelpickr.com/models/bytedance-seed/seed-character
- Aya Expanse 32B (cohere/c4ai-aya-expanse-32b): https://modelpickr.com/models/cohere/c4ai-aya-expanse-32b
- North Mini Code (cohere/north-mini-code-1-0): https://modelpickr.com/models/cohere/north-mini-code-1-0
- Ornith 1.5 35B A3B (deepreinforce/ornith-1.5-35b-a3b): https://modelpickr.com/models/deepreinforce/ornith-1.5-35b-a3b
- DeepSeek V3.1 (deepseek/deepseek-chat-v3.1): https://modelpickr.com/models/deepseek/deepseek-chat-v3.1
- DeepSeek V4 Pro 0423 (deepseek/deepseek-v4-pro-0423): https://modelpickr.com/models/deepseek/deepseek-v4-pro-0423
- Deep Research Max Preview (google/deep-research-max-preview-04-2026): https://modelpickr.com/models/google/deep-research-max-preview-04-2026
- Gemini Deep Research Preview (google/deep-research-preview-04-2026): https://modelpickr.com/models/google/deep-research-preview-04-2026
- Gemini 2.5 Computer Use Preview (google/gemini-2.5-computer-use-preview-10-2025): https://modelpickr.com/models/google/gemini-2.5-computer-use-preview-10-2025
- Gemini 2.5 Pro Preview 06-05 (google/gemini-2.5-pro-preview): https://modelpickr.com/models/google/gemini-2.5-pro-preview
- Gemma 4 12B IT (google/gemma-4-12b-it): https://modelpickr.com/models/google/gemma-4-12b-it
- Gemma 4 E2B IT (google/gemma-4-E2B-it): https://modelpickr.com/models/google/gemma-4-E2B-it
- Gemma 4 E4B IT (google/gemma-4-E4B-it): https://modelpickr.com/models/google/gemma-4-E4B-it
- Granite-4.0-H-Micro (ibm/granite-4-h-micro): https://modelpickr.com/models/ibm/granite-4-h-micro
- Ling 3.0 Flash VL (inclusionai/ling-3.0-flash-vl): https://modelpickr.com/models/inclusionai/ling-3.0-flash-vl
- Schematron V2 Small (inference-net/schematron-v2-small): https://modelpickr.com/models/inference-net/schematron-v2-small
- Schematron V2 Turbo (inference-net/schematron-v2-turbo): https://modelpickr.com/models/inference-net/schematron-v2-turbo
- Llama-3.2-11B-Vision-Instruct (meta/llama-3.2-11b-vision-instruct): https://modelpickr.com/models/meta/llama-3.2-11b-vision-instruct
- Llama-3.2-1B (meta/llama-3.2-1b): https://modelpickr.com/models/meta/llama-3.2-1b
- Llama-Guard-3-8B (meta/llama-guard-3-8b): https://modelpickr.com/models/meta/llama-guard-3-8b
- MiniMax M1 80K (minimax/minimax-m1-80k): https://modelpickr.com/models/minimax/minimax-m1-80k
- MiniMax-M3.1-Flash-Preview (minimax/MiniMax-M3.1-Flash-Preview): https://modelpickr.com/models/minimax/MiniMax-M3.1-Flash-Preview
- Devstral Medium (mistral/devstral-medium-2507): https://modelpickr.com/models/mistral/devstral-medium-2507
- Devstral Small (mistral/devstral-small-2507): https://modelpickr.com/models/mistral/devstral-small-2507
- Mistral Embed (mistral/mistral-embed): https://modelpickr.com/models/mistral/mistral-embed
- Mistral Large 2.1 (mistral/mistral-large-2411): https://modelpickr.com/models/mistral/mistral-large-2411
- Pixtral Large (latest) (mistral/pixtral-large-latest): https://modelpickr.com/models/mistral/pixtral-large-latest
- Voxtral Mini 3B 2507 (mistral/voxtral-mini-3b-2507): https://modelpickr.com/models/mistral/voxtral-mini-3b-2507
- Kimi K2.8 Preview (moonshotai/kimi-k2.8-preview): https://modelpickr.com/models/moonshotai/kimi-k2.8-preview
- Morph V3 Fast (morph/morph-v3-fast): https://modelpickr.com/models/morph/morph-v3-fast
- Morph V3 Large (morph/morph-v3-large): https://modelpickr.com/models/morph/morph-v3-large
- Hermes 4 405B (nousresearch/hermes-4-405b): https://modelpickr.com/models/nousresearch/hermes-4-405b
- Llama 3.3 Nemotron Super 49B v1 (nvidia/llama-3.3-nemotron-super-49b-v1): https://modelpickr.com/models/nvidia/llama-3.3-nemotron-super-49b-v1
- Llama 3.3 Nemotron Super 49B v1.5 (nvidia/llama-3.3-nemotron-super-49b-v1.5): https://modelpickr.com/models/nvidia/llama-3.3-nemotron-super-49b-v1.5
- GPT-5 Chat (latest) (openai/gpt-5-chat-latest): https://modelpickr.com/models/openai/gpt-5-chat-latest
- GPT-5 Image (openai/gpt-5-image): https://modelpickr.com/models/openai/gpt-5-image
- GPT-5 Image Mini (openai/gpt-5-image-mini): https://modelpickr.com/models/openai/gpt-5-image-mini
- GPT-5.1 Chat (openai/gpt-5.1-chat-latest): https://modelpickr.com/models/openai/gpt-5.1-chat-latest
- GPT-Realtime-2.1 (openai/gpt-realtime-2.1): https://modelpickr.com/models/openai/gpt-realtime-2.1
- Whisper Large v3 Turbo (openai/whisper-large-v3-turbo): https://modelpickr.com/models/openai/whisper-large-v3-turbo
- Laguna M.1 (poolside/laguna-m.1): https://modelpickr.com/models/poolside/laguna-m.1
- Sarvam 30B (sarvam/sarvam-30b): https://modelpickr.com/models/sarvam/sarvam-30b
- ALLaM-2-7b (sdaia/allam-2-7b): https://modelpickr.com/models/sdaia/allam-2-7b
- Cydonia 24B V4.1 (thedrummer/cydonia-24b-v4.1): https://modelpickr.com/models/thedrummer/cydonia-24b-v4.1
- Skyfall 36B V2 (thedrummer/skyfall-36b-v2): https://modelpickr.com/models/thedrummer/skyfall-36b-v2
- Pareto (unbiased/pareto): https://modelpickr.com/models/unbiased/pareto
- ReMM SLERP 13B (undi95/remm-slerp-l2-13b): https://modelpickr.com/models/undi95/remm-slerp-l2-13b
- Solar Pro 2 (upstage/solar-pro2): https://modelpickr.com/models/upstage/solar-pro2
- X-Ai/Grok-4-Fast-Non-Reasoning (xai/grok-4-fast-non-reasoning): https://modelpickr.com/models/xai/grok-4-fast-non-reasoning
- Grok 4.1 Fast (xai/grok-4.1-fast): https://modelpickr.com/models/xai/grok-4.1-fast
- Grok 4.1 Fast (Reasoning) (xai/grok-4.1-fast-reasoning): https://modelpickr.com/models/xai/grok-4.1-fast-reasoning
- MiMo-V2-Omni (xiaomi/mimo-v2-omni): https://modelpickr.com/models/xiaomi/mimo-v2-omni
- AutoGLM Phone 9B Multilingual (zhipuai/autoglm-phone-9b-multilingual): https://modelpickr.com/models/zhipuai/autoglm-phone-9b-multilingual
- Jamba Large (ai21/jamba-large): https://modelpickr.com/models/ai21/jamba-large
- Jamba Mini (ai21/jamba-mini): https://modelpickr.com/models/ai21/jamba-mini
- Aion-2.0 (aion-labs/aion-2.0): https://modelpickr.com/models/aion-labs/aion-2.0
- Qwen2.5-Coder-0.5B (alibaba/qwen2.5-coder-0.5b): https://modelpickr.com/models/alibaba/qwen2.5-coder-0.5b
- Qwen3 Omni 30B A3B Thinking (alibaba/qwen3-omni-30b-a3b-thinking): https://modelpickr.com/models/alibaba/qwen3-omni-30b-a3b-thinking
- Nova 2 Lite (amazon/nova-2-lite-v1): https://modelpickr.com/models/amazon/nova-2-lite-v1
- Nova Premier (amazon/nova-premier): https://modelpickr.com/models/amazon/nova-premier
- Claude Sonnet 3.5 v2 (anthropic/claude-3-5-sonnet-20241022): https://modelpickr.com/models/anthropic/claude-3-5-sonnet-20241022
- Claude Haiku 3 (anthropic/claude-3-haiku-20240307): https://modelpickr.com/models/anthropic/claude-3-haiku-20240307
- Apodex 1.1 Mini (apodex/apodex-1.1-mini): https://modelpickr.com/models/apodex/apodex-1.1-mini
- Trinity Large Preview (arcee-ai/trinity-large-preview): https://modelpickr.com/models/arcee-ai/trinity-large-preview
- Trinity Mini (arcee-ai/trinity-mini): https://modelpickr.com/models/arcee-ai/trinity-mini
- Baichuan M2 32B (baichuan/baichuan-m2-32b): https://modelpickr.com/models/baichuan/baichuan-m2-32b
- CoBuddy (baidu/cobuddy): https://modelpickr.com/models/baidu/cobuddy
- ERNIE 4.5 21B A3B (baidu/ernie-4.5-21b-a3b): https://modelpickr.com/models/baidu/ernie-4.5-21b-a3b
- Uncensored (cognitivecomputations/dolphin-mistral-24b-venice-edition): https://modelpickr.com/models/cognitivecomputations/dolphin-mistral-24b-venice-edition
- Command A Plus (cohere/command-a-plus-05-2026): https://modelpickr.com/models/cohere/command-a-plus-05-2026
- Command A Translate (cohere/command-a-translate-08-2025): https://modelpickr.com/models/cohere/command-a-translate-08-2025
- Command A Vision (cohere/command-a-vision-07-2025): https://modelpickr.com/models/cohere/command-a-vision-07-2025
- Command R7B Arabic (cohere/command-r7b-arabic-02-2025): https://modelpickr.com/models/cohere/command-r7b-arabic-02-2025
- North Small Translate (cohere/north-small-translate-1-0): https://modelpickr.com/models/cohere/north-small-translate-1-0
- Ornith 1.0 35B (deepreinforce/ornith-1.0-35b): https://modelpickr.com/models/deepreinforce/ornith-1.0-35b
- DeepSeek R1 0528 Qwen3 8B (deepseek/deepseek-r1-0528-qwen3-8b): https://modelpickr.com/models/deepseek/deepseek-r1-0528-qwen3-8b
- DiffusionGemma 26B A4B IT (google/diffusiongemma-26b-a4b-it): https://modelpickr.com/models/google/diffusiongemma-26b-a4b-it
- Gemini 3.1 Flash Live Preview (google/gemini-3.1-flash-live-preview): https://modelpickr.com/models/google/gemini-3.1-flash-live-preview
- Gemini 3.5 Live Translate Preview (google/gemini-3.5-live-translate-preview): https://modelpickr.com/models/google/gemini-3.5-live-translate-preview
- Gemini Robotics-ER 1.6 Preview (google/gemini-robotics-er-1.6-preview): https://modelpickr.com/models/google/gemini-robotics-er-1.6-preview
- Granite-4.0-H-Small (ibm/granite-4-h-small): https://modelpickr.com/models/ibm/granite-4-h-small
- Ling 3.0 Flash Sante (inclusionai/ling-3.0-flash-sante): https://modelpickr.com/models/inclusionai/ling-3.0-flash-sante
- Weaver (alpha) (mancer/weaver): https://modelpickr.com/models/mancer/weaver
- MAI-Code-1-Flash (microsoft/mai-code-1-flash): https://modelpickr.com/models/microsoft/mai-code-1-flash
- MAI-Code-1.1-Flash (microsoft/mai-code-1.1-flash): https://modelpickr.com/models/microsoft/mai-code-1.1-flash
- Macaron V1 Tall (mindlab/macaron-v1-tall): https://modelpickr.com/models/mindlab/macaron-v1-tall
- Macaron V1 Venti (mindlab/macaron-v1-venti): https://modelpickr.com/models/mindlab/macaron-v1-venti
- Codestral-22B-v0.1 (mistral/codestral-22b-v0.1): https://modelpickr.com/models/mistral/codestral-22b-v0.1
- Devstral Small 2 (mistral/devstral-small-2): https://modelpickr.com/models/mistral/devstral-small-2
- Magistral Small (mistral/magistral-small-2506): https://modelpickr.com/models/mistral/magistral-small-2506
- Magistral Small 1.2 (mistral/magistral-small-2509): https://modelpickr.com/models/mistral/magistral-small-2509
- Ministral 14B (mistral/ministral-14b): https://modelpickr.com/models/mistral/ministral-14b
- Ministral 3B (mistral/ministral-3b): https://modelpickr.com/models/mistral/ministral-3b
- Ministral 8B Instruct (mistral/ministral-8b-instruct-2410): https://modelpickr.com/models/mistral/ministral-8b-instruct-2410
- Toast 1 (mixedbread/toast-1): https://modelpickr.com/models/mixedbread/toast-1
- Motif 3 (motif-technologies/motif-3): https://modelpickr.com/models/motif-technologies/motif-3
- Nex-N2-Pro (nex-agi/nex-n2-pro): https://modelpickr.com/models/nex-agi/nex-n2-pro
- Hermes 2 Pro Llama 3 8B (nousresearch/hermes-2-pro-llama-3-8b): https://modelpickr.com/models/nousresearch/hermes-2-pro-llama-3-8b
- Llama 3.1 Nemotron Safety Guard 8B v3 (nvidia/llama-3.1-nemotron-safety-guard-8b-v3): https://modelpickr.com/models/nvidia/llama-3.1-nemotron-safety-guard-8b-v3
- Llama 3.1 Nemotron Ultra 253B (nvidia/llama-3.1-nemotron-ultra-253b): https://modelpickr.com/models/nvidia/llama-3.1-nemotron-ultra-253b
- Llama Nemotron Embed VL 1B v2 (nvidia/llama-nemotron-embed-vl-1b-v2): https://modelpickr.com/models/nvidia/llama-nemotron-embed-vl-1b-v2
- Llama Nemotron Rerank VL 1B v2 (nvidia/llama-nemotron-rerank-vl-1b-v2): https://modelpickr.com/models/nvidia/llama-nemotron-rerank-vl-1b-v2
- Mistral Nemotron (nvidia/mistral-nemotron): https://modelpickr.com/models/nvidia/mistral-nemotron
- Nemotron 3 Content Safety (nvidia/nemotron-3-content-safety): https://modelpickr.com/models/nvidia/nemotron-3-content-safety
- Nemotron Content Safety Reasoning 4B (nvidia/nemotron-content-safety-reasoning-4b): https://modelpickr.com/models/nvidia/nemotron-content-safety-reasoning-4b
- Nemotron Mini 4B Instruct (nvidia/nemotron-mini-4b-instruct): https://modelpickr.com/models/nvidia/nemotron-mini-4b-instruct
- Nemotron VoiceChat (nvidia/nemotron-voicechat): https://modelpickr.com/models/nvidia/nemotron-voicechat
- GPT-5.3 Codex Spark (openai/gpt-5.3-codex-spark): https://modelpickr.com/models/openai/gpt-5.3-codex-spark
- GPT-5.6 Cyber (openai/gpt-5.6-cyber): https://modelpickr.com/models/openai/gpt-5.6-cyber
- GPT-6 Astra (Fast) (openai/gpt-6-astra-fast): https://modelpickr.com/models/openai/gpt-6-astra-fast
- MiniCPM5-2B (openbmb/minicpm5-2b): https://modelpickr.com/models/openbmb/minicpm5-2b
- PaddleOCR VL (paddlepaddle/paddleocr-vl): https://modelpickr.com/models/paddlepaddle/paddleocr-vl
- Perceptron Mk1 (perceptron/perceptron-mk1): https://modelpickr.com/models/perceptron/perceptron-mk1
- Laguna XS.2 (poolside/laguna-xs.2): https://modelpickr.com/models/poolside/laguna-xs.2
- Arrow 2 (quiverai/arrow-2): https://modelpickr.com/models/quiverai/arrow-2
- Arrow 2 Telos (quiverai/arrow-2-telos): https://modelpickr.com/models/quiverai/arrow-2-telos
- Reka Edge (rekaai/reka-edge): https://modelpickr.com/models/rekaai/reka-edge
- Relace Apply 3 (relace/relace-apply-3): https://modelpickr.com/models/relace/relace-apply-3
- Relace Search (relace/relace-search): https://modelpickr.com/models/relace/relace-search
- Llama 3 8B Lunaris (sao10k/l3-lunaris-8b): https://modelpickr.com/models/sao10k/l3-lunaris-8b
- Llama 3.1 Euryale 70B v2.2 (sao10k/l3.1-euryale-70b): https://modelpickr.com/models/sao10k/l3.1-euryale-70b
- Llama 3.3 Euryale 70B (sao10k/l3.3-euryale-70b): https://modelpickr.com/models/sao10k/l3.3-euryale-70b
- Apertus 8B (swiss-ai/apertus-8b): https://modelpickr.com/models/swiss-ai/apertus-8b
- UnslopNemo 12B (thedrummer/unslopnemo-12b): https://modelpickr.com/models/thedrummer/unslopnemo-12b
- Trendyol Asure 12B (trendyol/asure-12b): https://modelpickr.com/models/trendyol/asure-12b
- Vision Large (vispark/vision-large): https://modelpickr.com/models/vispark/vision-large
- Vision Medium (vispark/vision-medium): https://modelpickr.com/models/vispark/vision-medium
- Vision Small (vispark/vision-small): https://modelpickr.com/models/vispark/vision-small
- Viv Fast (vivgrid/viv-fast): https://modelpickr.com/models/vivgrid/viv-fast
- Palmyra X4 (writer/palmyra-x4): https://modelpickr.com/models/writer/palmyra-x4
- Palmyra X5 (writer/palmyra-x5): https://modelpickr.com/models/writer/palmyra-x5
- MiMo-V2.5-Pro-UltraSpeed (xiaomi/mimo-v2.5-pro-ultraspeed): https://modelpickr.com/models/xiaomi/mimo-v2.5-pro-ultraspeed