# LLM Models List

Browse active large language models with known text-generation support. Compare provider offers, context windows, capabilities, and token prices.

- Active LLM model IDs: 637
- Executable provider offers: 975
- API providers: 25
- Complete catalog records: 6,427
- Latest recorded update: 2026-08-03

## How this LLM list works

The page builds a conservative directory from active provider offers with explicit typed text-generation support.

### Inclusion criteria

- The provider offer is allowed and is not catalog-only, deprecated, or retired.
- The execution metadata explicitly marks text generation as supported.
- The input and output modality sets both include text.

### Exclusions

- The list excludes catalog-only, deprecated, and retired provider offers.
- The list excludes offers without explicit typed text execution support.
- The list excludes records that do not support both text input and text output.

### Data rules

- **Grouping:** Provider offers are grouped by a conservative normalized model ID and by explicit aliases from the model database. A vendor prefix is removed only when the remaining ID is specific and agrees with the model name.
- **Context limits:** The context value is the largest recorded provider limit for the grouped model identity.
- **Token price:** The displayed price pair comes from the offer with the lowest known input-token price.
- **Ordering:** Models are ordered by the latest valid metadata date, then by name and model ID for stable output.

### Limits of the data

- This page is a directory. It does not rank model quality or benchmark performance.
- A missing price or capability means that the catalog does not have a confirmed value. It does not prove that the model lacks that feature.
- Provider metadata changes often and can become stale between catalog releases.

## What this page can answer

Use this page to find active LLM model IDs, see which providers offer each model, and compare known context windows, capabilities, and token prices. Follow a model link for the complete provider record.

## Sources

- [llm_db](https://github.com/agentjido/llmdb) — Primary source for model records, typed execution data, prices, and capabilities. Checked 2026-07-30.
- [models.dev](https://models.dev) — One upstream source used by the llm_db catalog. Checked 2026-07-30.

See [About LLM Catalog](https://llmcatalog.dev/about) for more information about the data.

## Recently updated models

| Model | Model ID | Offers | Context | Input / output per 1M tokens | Updated |
| --- | --- | ---: | ---: | ---: | --- |
| [Kimi K3 Fast](https://llmcatalog.dev/models/venice/kimi-k3-fast-api) | `kimi-k3-fast-api` | 1 | 1,000,000 | $4.50 / $22.50 | 2026-08-03 |
| [Qwen: Qwen3.8 Max](https://llmcatalog.dev/models/alibaba/qwen3.8-max) | `qwen3.8-max` | 3 | 1,000,000 | $2.00 / $6.00 | 2026-08-03 |
| [DeepSeek V4 Flash 0731](https://llmcatalog.dev/models/openrouter/deepseek/deepseek-v4-flash-0731) | `deepseek-v4-flash-0731` | 3 | 1,048,576 | $0.09 / $0.18 | 2026-08-01 |
| [DeepSeek V4 Flash](https://llmcatalog.dev/models/venice/deepseek-v4-flash) | `deepseek-v4-flash` | 6 | 1,048,576 | $0.14 / $0.28 | 2026-07-31 |
| [DeepSeek V4 Flash 0731](https://llmcatalog.dev/models/togetherai/deepseek-ai/DeepSeek-V4-Flash-0731) | `DeepSeek-V4-Flash-0731` | 1 | 1,000,000 | $0.14 / $0.28 | 2026-07-31 |
| [DeepSeek V4 Flash 0731](https://llmcatalog.dev/models/ollama_cloud/deepseek-v4-flash:0731) | `deepseek-v4-flash:0731` | 1 | 1,048,576 | N/A / N/A | 2026-07-31 |
| [deepseek/deepseek-v4-flash-free](https://llmcatalog.dev/models/opencode/deepseek-v4-flash-free) | `deepseek-v4-flash-free` | 2 | 200,000 | $0.00 / $0.00 | 2026-07-31 |
| [Thinking Machines: Inkling Small](https://llmcatalog.dev/models/openrouter/thinkingmachines/inkling-small) | `inkling-small` | 1 | 524,288 | $0.50 / $1.20 | 2026-07-30 |
| [Kimi K3](https://llmcatalog.dev/models/fireworks_ai/accounts/fireworks/models/kimi-k3) | `kimi-k3` | 6 | 1,048,576 | $3.00 / $15.00 | 2026-07-27 |
| [Kimi K3 Fast](https://llmcatalog.dev/models/fireworks_ai/accounts/fireworks/routers/kimi-k3-fast) | `kimi-k3-fast` | 1 | 1,048,576 | $4.50 / $22.50 | 2026-07-27 |
| [Claude Opus 5](https://llmcatalog.dev/models/anthropic/claude-opus-5) | `claude-opus-5` | 4 | 1,000,000 | $5.00 / $25.00 | 2026-07-24 |
| [Claude Opus 5 (Fast)](https://llmcatalog.dev/models/openrouter/anthropic/claude-opus-5-fast) | `claude-opus-5-fast` | 2 | 1,000,000 | $10.00 / $50.00 | 2026-07-24 |
| [Seed 2.1 Turbo](https://llmcatalog.dev/models/venice/seed-2-1-turbo) | `seed-2-1-turbo` | 1 | 256,000 | $0.63 / $3.13 | 2026-07-24 |
| [Ling-3.0-flash (free)](https://llmcatalog.dev/models/openrouter/inclusionai/ling-3.0-flash:free) | `ling-3.0-flash:free` | 1 | 262,144 | $0.00 / $0.00 | 2026-07-23 |
| [Qwen 3.6 35B A3B](https://llmcatalog.dev/models/venice/qwen3-6-35b-a3b) | `qwen3-6-35b-a3b` | 1 | 256,000 | $0.10 / $1.00 | 2026-07-22 |
| [Gemini 3.5 Flash-Lite](https://llmcatalog.dev/models/venice/gemini-3-5-flash-lite) | `gemini-3-5-flash-lite` | 1 | 1,000,000 | $0.38 / $3.13 | 2026-07-21 |
| [Gemini 3.6 Flash](https://llmcatalog.dev/models/venice/gemini-3-6-flash) | `gemini-3-6-flash` | 1 | 1,000,000 | $1.88 / $9.38 | 2026-07-21 |
| [Google: Gemini 3.5 Flash Lite](https://llmcatalog.dev/models/google/gemini-3.5-flash-lite) | `gemini-3.5-flash-lite` | 3 | 1,048,576 | $0.30 / $2.50 | 2026-07-21 |
| [Google: Gemini 3.6 Flash](https://llmcatalog.dev/models/google/gemini-3.6-flash) | `gemini-3.6-flash` | 3 | 1,048,576 | $1.50 / $7.50 | 2026-07-21 |
| [Poolside: Laguna S 2.1](https://llmcatalog.dev/models/openrouter/poolside/laguna-s-2.1) | `laguna-s-2.1` | 1 | 1,048,576 | $0.09 / $0.18 | 2026-07-21 |
| [Poolside: Laguna S 2.1 (free)](https://llmcatalog.dev/models/openrouter/poolside/laguna-s-2.1:free) | `laguna-s-2.1:free` | 1 | 262,144 | $0.00 / $0.00 | 2026-07-21 |
| [Meituan: LongCat 2.0](https://llmcatalog.dev/models/openrouter/meituan/longcat-2.0) | `longcat-2.0` | 2 | 1,048,756 | $0.30 / $1.20 | 2026-07-20 |
| [Qwen 3.8 Max](https://llmcatalog.dev/models/venice/qwen-3-8-max) | `qwen-3-8-max` | 1 | 1,000,000 | $2.50 / $7.50 | 2026-07-19 |
| [Inkling](https://llmcatalog.dev/models/venice/inkling) | `inkling` | 1 | 524,288 | $1.25 / $5.06 | 2026-07-17 |
| [Kimi K3](https://llmcatalog.dev/models/togetherai/moonshotai/Kimi-K3) | `Kimi-K3` | 1 | 1,048,576 | $3.00 / $15.00 | 2026-07-16 |
| [Kimi K3 (Free)](https://llmcatalog.dev/models/zenmux/moonshotai/kimi-k3-free) | `kimi-k3-free` | 1 | 1,048,576 | $0.00 / $0.00 | 2026-07-16 |
| [Inkling](https://llmcatalog.dev/models/togetherai/thinkingmachines/Inkling) | `thinkingmachines/Inkling` | 1 | 524,288 | $1.00 / $4.05 | 2026-07-15 |
| [Qwen: Qwen3.7 Flash](https://llmcatalog.dev/models/openrouter/qwen/qwen3.7-flash) | `qwen3.7-flash` | 2 | 1,000,000 | $0.03 / $0.13 | 2026-07-15 |
| [Thinking Machines: Inkling](https://llmcatalog.dev/models/openrouter/thinkingmachines/inkling) | `thinkingmachines/inkling` | 1 | 1,048,576 | $1.00 / $4.05 | 2026-07-15 |
| [Kwaipilot: KAT-Coder-Air V2.5](https://llmcatalog.dev/models/openrouter/kwaipilot/kat-coder-air-v2.5) | `kat-coder-air-v2.5` | 2 | 256,000 | $0.15 / $0.60 | 2026-07-10 |
| [Kwaipilot: KAT-Coder-Pro V2.5](https://llmcatalog.dev/models/openrouter/kwaipilot/kat-coder-pro-v2.5) | `kat-coder-pro-v2.5` | 2 | 256,000 | $0.74 / $2.96 | 2026-07-10 |
| [GPT-5.6](https://llmcatalog.dev/models/openai/gpt-5.6) | `gpt-5.6` | 1 | 1,050,000 | $5.00 / $30.00 | 2026-07-09 |
| [GPT-5.6 Luna](https://llmcatalog.dev/models/venice/openai-gpt-56-luna) | `openai-gpt-56-luna` | 1 | 1,000,000 | $1.25 / $7.50 | 2026-07-09 |
| [GPT-5.6 Luna Pro](https://llmcatalog.dev/models/venice/openai-gpt-56-luna-pro) | `openai-gpt-56-luna-pro` | 1 | 1,000,000 | $1.25 / $7.50 | 2026-07-09 |
| [GPT-5.6 Sol](https://llmcatalog.dev/models/venice/openai-gpt-56-sol) | `openai-gpt-56-sol` | 1 | 1,000,000 | $6.25 / $37.50 | 2026-07-09 |
| [GPT-5.6 Sol Pro](https://llmcatalog.dev/models/venice/openai-gpt-56-sol-pro) | `openai-gpt-56-sol-pro` | 1 | 1,000,000 | $6.25 / $37.50 | 2026-07-09 |
| [GPT-5.6 Terra](https://llmcatalog.dev/models/venice/openai-gpt-56-terra) | `openai-gpt-56-terra` | 1 | 1,000,000 | $3.13 / $18.75 | 2026-07-09 |
| [GPT-5.6 Terra Pro](https://llmcatalog.dev/models/venice/openai-gpt-56-terra-pro) | `openai-gpt-56-terra-pro` | 1 | 1,000,000 | $3.13 / $18.75 | 2026-07-09 |
| [Meta: Muse Spark 1.1](https://llmcatalog.dev/models/openrouter/meta/muse-spark-1.1) | `muse-spark-1.1` | 2 | 1,048,576 | $1.25 / $4.25 | 2026-07-09 |
| [OpenAI: GPT-5.6 Luna](https://llmcatalog.dev/models/openrouter/openai/gpt-5.6-luna) | `gpt-5.6-luna` | 3 | 1,050,000 | $0.10 / $0.60 | 2026-07-09 |
| [OpenAI: GPT-5.6 Luna Pro](https://llmcatalog.dev/models/openrouter/openai/gpt-5.6-luna-pro) | `gpt-5.6-luna-pro` | 1 | 1,050,000 | $0.10 / $0.60 | 2026-07-09 |
| [OpenAI: GPT-5.6 Sol](https://llmcatalog.dev/models/openai/gpt-5.6-sol) | `gpt-5.6-sol` | 3 | 1,050,000 | $5.00 / $30.00 | 2026-07-09 |
| [OpenAI: GPT-5.6 Sol Pro](https://llmcatalog.dev/models/openrouter/openai/gpt-5.6-sol-pro) | `gpt-5.6-sol-pro` | 1 | 1,050,000 | $5.00 / $30.00 | 2026-07-09 |
| [OpenAI: GPT-5.6 Terra](https://llmcatalog.dev/models/openrouter/openai/gpt-5.6-terra) | `gpt-5.6-terra` | 3 | 1,050,000 | $1.00 / $6.00 | 2026-07-09 |
| [OpenAI: GPT-5.6 Terra Pro](https://llmcatalog.dev/models/openrouter/openai/gpt-5.6-terra-pro) | `gpt-5.6-terra-pro` | 1 | 1,050,000 | $1.00 / $6.00 | 2026-07-09 |
| [Aion 3.0](https://llmcatalog.dev/models/venice/aion-labs-aion-3-0) | `aion-labs-aion-3-0` | 1 | 128,000 | $3.75 / $7.50 | 2026-07-08 |
| [Aion 3.0 Mini](https://llmcatalog.dev/models/venice/aion-labs-aion-3-0-mini) | `aion-labs-aion-3-0-mini` | 1 | 128,000 | $0.88 / $1.75 | 2026-07-08 |
| [Grok 4.5](https://llmcatalog.dev/models/venice/grok-4-5) | `grok-4-5` | 1 | 500,000 | $2.27 / $6.80 | 2026-07-08 |
| [SpaceXAI: Grok 4.5](https://llmcatalog.dev/models/openrouter/x-ai/grok-4.3) | `grok-4.3` | 3 | 1,000,000 | $1.25 / $2.50 | 2026-07-08 |
| [AionLabs: Aion-3.0](https://llmcatalog.dev/models/openrouter/aion-labs/aion-3.0) | `aion-3.0` | 1 | 131,072 | $3.00 / $6.00 | 2026-07-07 |

## Related LLM model lists

- [Compare objective AI model rankings](https://llmcatalog.dev/rankings/ai-models) — Review separate rankings for paid token price, context size, and catalog freshness.
- [Compare the cheapest LLM APIs](https://llmcatalog.dev/rankings/cheapest-llm-api) — Order paid text-generation offers by known input-token price and check output cost.
- [Browse vision LLM models](https://llmcatalog.dev/models/vision) — Find active text models that accept image input and return text.
- [Find tool-calling LLM models](https://llmcatalog.dev/models/tool-calling) — Compare active text models with explicit tools capability metadata.
- [Compare the largest LLM context windows](https://llmcatalog.dev/models/long-context) — Review active model identities with recorded context limits of 128,000 tokens or more.
- [Browse open-weight LLM models](https://llmcatalog.dev/models/open-weights) — Find active text models whose catalog metadata marks open weights as true.
- [Explore video AI models](https://llmcatalog.dev/models/video) — Use separate lists for models that accept video and models that generate video.

Canonical URL: https://llmcatalog.dev/llm-models

Full catalog: https://llmcatalog.dev/

MCP endpoint: `https://llmcatalog.dev/api/mcp`