# Free Models (OpenRouter `:free` + OpenCode free)

Last updated: 2026-10-14T15:04:29Z
Sources: https://openrouter.ai/api/v1/models (see also https://openrouter.ai/models), https://opencode.ai/inference/v1/models + https://models.dev/api.json (see also https://opencode.ai/v2/docs/console/models)
Models currently available: **23** (14 OpenRouter, 9 OpenCode)

Status legend: `ACTIVE` = listed, `NEW` = first seen in the last run, `⚠️ DEPRECATED` = expiring soon (OpenRouter) or flagged deprecated in models.dev (OpenCode), `REMOVED` = no longer listed.

## Overview

| Status | Provider | Name | ID | Context Length | Max Completion | #Params | 🧠 | 💻 |
|---|---|---|---|---|---|---|---|---|
| ACTIVE | opencode | OpenCode: Big Pickle | `opencode/big-pickle` | 200,000 | 32,000 | 7 | 80 | 79 |
| ACTIVE | opencode | OpenCode: Cat Jam Free | `opencode/cat-jam-free` | 262,144 | 131,072 | 7 | 89 | 84 |
| ACTIVE | opencode | OpenCode: LongCat 2.5 Preview Free | `opencode/longcat-2.5-preview-free` | 1,000,000 | 131,072 | 5 | 92 | 89 |
| ACTIVE | opencode | OpenCode: MiMo-V2.6-Flash Free | `opencode/mimo-v2.6-flash-free` | 200,000 | 32,000 | 5 | 75 | 74 |
| ACTIVE ⚠️ | opencode | OpenCode: Muse Spark 1.2 Free | `opencode/muse-spark-1.2-contributor-free` | 1,048,576 | 131,072 | 7 | 96 | 99 |
| ACTIVE | opencode | OpenCode: Muse Spark 1.3 Free | `opencode/muse-spark-1.3-contributor-free` | 1,048,576 | 131,072 | 7 | 96 | 99 |
| ACTIVE | opencode | OpenCode: Nemotron 3.5 Lightning Free | `opencode/nemotron-3.5-lightning-free` | 262,144 | 262,144 | 7 | 93 | 85 |
| ACTIVE | opencode | OpenCode: Space Bunny Free | `opencode/space-bunny-free` | 1,048,576 | 524,288 | 4 | 90 | 90 |
| ACTIVE | opencode | OpenCode: Step 5 Preview Free | `opencode/step-5-preview-free` | 1,000,000 | 65,536 | 6 | 88 | 98 |
| ACTIVE | openrouter | Cohere: North Mini Code (free) | `cohere/north-mini-code:free` | 256,000 | 64,000 | 12 | 80 | 72 |
| ACTIVE | openrouter | Dots Studio: Dots3-Note Preview (free) | `dots-studio/dots-3-note-preview:free` | 512,000 | 460,800 | 9 | 96 | 95 |
| ACTIVE | openrouter | Google: Gemma 4 26B A4B  (free) | `google/gemma-4-26b-a4b-it:free` | 262,144 | 32,768 | 9 | 82 | 86 |
| ACTIVE | openrouter | Google: Gemma 4 31B (free) | `google/gemma-4-31b-it:free` | 262,144 | 32,768 | 9 | 82 | 86 |
| ACTIVE | openrouter | LiquidAI: LFM2.5-2.6B (free) | `liquid/lfm-2.5-2.6b:free` | 65,536 | 8,192 | 18 | 67 | 68 |
| ACTIVE | openrouter | NVIDIA: Nemotron 3 Nano Omni (free) | `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256,000 | 65,536 | 8 | 80 | 77 |
| ACTIVE | openrouter | NVIDIA: Nemotron 3 Super (free) | `nvidia/nemotron-3-super-120b-a12b:free` | 262,144 | 235,929 | 11 | 92 | 85 |
| ACTIVE | openrouter | NVIDIA: Nemotron 3 Ultra (free) | `nvidia/nemotron-3-ultra-550b-a55b:free` | 1,000,000 | 65,536 | 9 | 88 | 83 |
| ACTIVE | openrouter | NVIDIA: Nemotron 3.5 Content Safety (free) | `nvidia/nemotron-3.5-content-safety:free` | 128,000 | 8,192 | 6 | 60 | 38 |
| ACTIVE | openrouter | NVIDIA: Nemotron 3.5 Lightning (free) | `nvidia/nemotron-3.5-lightning:free` | 1,000,000 | 65,536 | 8 | 88 | 83 |
| ACTIVE ⚠️ (expires 2026-10-31) | openrouter | Poolside: Laguna S 2.1 (free) | `poolside/laguna-s-2.1:free` | 262,144 | 32,768 | 6 | 77 | 71 |
| ACTIVE ⚠️ (expires 2026-10-31) | openrouter | Poolside: Laguna XS 2.1 (free) | `poolside/laguna-xs-2.1:free` | 262,144 | 32,768 | 6 | 77 | 71 |
| ACTIVE | openrouter | Thinking Machines: Inkling Small (free) | `thinkingmachines/inkling-small:free` | 1,048,576 | 262,144 | 11 | 95 | 90 |
| ACTIVE | openrouter | Thinking Machines: Inkling (free) | `thinkingmachines/inkling:free` | 1,048,576 | 262,144 | 11 | 95 | 90 |

## Details

### OpenCode: Big Pickle

- **Provider:** opencode
- **ID:** `opencode/big-pickle`
- **Status:** ACTIVE
- **Description:** Reasoning model for deliberate analysis, multi-step problem solving, and tool use
- **Context Length:** 200,000
- **Max Completion:** 32,000
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Cat Jam Free

- **Provider:** opencode
- **ID:** `opencode/cat-jam-free`
- **Status:** ACTIVE
- **Description:** A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.
- **Context Length:** 262,144
- **Max Completion:** 131,072
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: LongCat 2.5 Preview Free

- **Provider:** opencode
- **ID:** `opencode/longcat-2.5-preview-free`
- **Status:** ACTIVE
- **Description:** Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window
- **Context Length:** 1,000,000
- **Max Completion:** 131,072
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: MiMo-V2.6-Flash Free

- **Provider:** opencode
- **ID:** `opencode/mimo-v2.6-flash-free`
- **Status:** ACTIVE
- **Description:** MiMo Flash model for multimodal coding agents and long-context automation
- **Context Length:** 200,000
- **Max Completion:** 32,000
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Muse Spark 1.2 Free

- **Provider:** opencode
- **ID:** `opencode/muse-spark-1.2-contributor-free`
- **Status:** ACTIVE ⚠️ DEPRECATED
- **Description:** Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.
- **Context Length:** 1,048,576
- **Max Completion:** 131,072
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Muse Spark 1.3 Free

- **Provider:** opencode
- **ID:** `opencode/muse-spark-1.3-contributor-free`
- **Status:** ACTIVE
- **Description:** Muse Spark 1.3 is a multimodal reasoning model from Meta for coding and agentic workflows.
- **Context Length:** 1,048,576
- **Max Completion:** 131,072
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Nemotron 3.5 Lightning Free

- **Provider:** opencode
- **ID:** `opencode/nemotron-3.5-lightning-free`
- **Status:** ACTIVE
- **Description:** Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
- **Context Length:** 262,144
- **Max Completion:** 262,144
- **Supported Parameters:** `tools`, `tool_choice`, `temperature`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Space Bunny Free

- **Provider:** opencode
- **ID:** `opencode/space-bunny-free`
- **Status:** ACTIVE
- **Description:** Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input
- **Context Length:** 1,048,576
- **Max Completion:** 524,288
- **Supported Parameters:** `tools`, `tool_choice`, `reasoning`, `include_reasoning`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### OpenCode: Step 5 Preview Free

- **Provider:** opencode
- **ID:** `opencode/step-5-preview-free`
- **Status:** ACTIVE
- **Description:** StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
- **Context Length:** 1,000,000
- **Max Completion:** 65,536
- **Supported Parameters:** `tools`, `tool_choice`, `reasoning`, `include_reasoning`, `structured_outputs`, `response_format`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Cohere: North Mini Code (free)

- **Provider:** openrouter
- **ID:** `cohere/north-mini-code:free`
- **Status:** ACTIVE
- **Description:** North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
- **Context Length:** 256,000
- **Max Completion:** 64,000
- **Supported Parameters:** `frequency_penalty`, `include_reasoning`, `max_tokens`, `presence_penalty`, `reasoning`, `seed`, `stop`, `temperature`, `tool_choice`, `tools`, `top_k`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Dots Studio: Dots3-Note Preview (free)

- **Provider:** openrouter
- **ID:** `dots-studio/dots-3-note-preview:free`
- **Status:** ACTIVE
- **Description:** Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...
- **Context Length:** 512,000
- **Max Completion:** 460,800
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `response_format`, `structured_outputs`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Google: Gemma 4 26B A4B  (free)

- **Provider:** openrouter
- **ID:** `google/gemma-4-26b-a4b-it:free`
- **Status:** ACTIVE
- **Description:** Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
- **Context Length:** 262,144
- **Max Completion:** 32,768
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `response_format`, `seed`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Google: Gemma 4 31B (free)

- **Provider:** openrouter
- **ID:** `google/gemma-4-31b-it:free`
- **Status:** ACTIVE
- **Description:** Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
- **Context Length:** 262,144
- **Max Completion:** 32,768
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `response_format`, `seed`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### LiquidAI: LFM2.5-2.6B (free)

- **Provider:** openrouter
- **ID:** `liquid/lfm-2.5-2.6b:free`
- **Status:** ACTIVE
- **Description:** LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
- **Context Length:** 65,536
- **Max Completion:** 8,192
- **Supported Parameters:** `frequency_penalty`, `include_reasoning`, `logprobs`, `max_completion_tokens`, `max_tokens`, `min_p`, `presence_penalty`, `reasoning`, `repetition_penalty`, `response_format`, `seed`, `stop`, `structured_outputs`, `temperature`, `tool_choice`, `tools`, `top_k`, `top_logprobs`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### NVIDIA: Nemotron 3 Nano Omni (free)

- **Provider:** openrouter
- **ID:** `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`
- **Status:** ACTIVE
- **Description:** NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
- **Context Length:** 256,000
- **Max Completion:** 65,536
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `seed`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### NVIDIA: Nemotron 3 Super (free)

- **Provider:** openrouter
- **ID:** `nvidia/nemotron-3-super-120b-a12b:free`
- **Status:** ACTIVE
- **Description:** NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
- **Context Length:** 262,144
- **Max Completion:** 235,929
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `reasoning_effort`, `response_format`, `seed`, `structured_outputs`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### NVIDIA: Nemotron 3 Ultra (free)

- **Provider:** openrouter
- **ID:** `nvidia/nemotron-3-ultra-550b-a55b:free`
- **Status:** ACTIVE
- **Description:** NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
- **Context Length:** 1,000,000
- **Max Completion:** 65,536
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `reasoning_effort`, `seed`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### NVIDIA: Nemotron 3.5 Content Safety (free)

- **Provider:** openrouter
- **ID:** `nvidia/nemotron-3.5-content-safety:free`
- **Status:** ACTIVE
- **Description:** NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
- **Context Length:** 128,000
- **Max Completion:** 8,192
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `seed`, `temperature`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### NVIDIA: Nemotron 3.5 Lightning (free)

- **Provider:** openrouter
- **ID:** `nvidia/nemotron-3.5-lightning:free`
- **Status:** ACTIVE
- **Description:** NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
- **Context Length:** 1,000,000
- **Max Completion:** 65,536
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `seed`, `temperature`, `tool_choice`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Poolside: Laguna S 2.1 (free)

- **Provider:** openrouter
- **ID:** `poolside/laguna-s-2.1:free`
- **Status:** ACTIVE ⚠️ DEPRECATED (expires 2026-10-31)
- **Description:** Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
- **Context Length:** 262,144
- **Max Completion:** 32,768
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `temperature`, `tool_choice`, `tools`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Poolside: Laguna XS 2.1 (free)

- **Provider:** openrouter
- **ID:** `poolside/laguna-xs-2.1:free`
- **Status:** ACTIVE ⚠️ DEPRECATED (expires 2026-10-31)
- **Description:** Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
- **Context Length:** 262,144
- **Max Completion:** 32,768
- **Supported Parameters:** `include_reasoning`, `max_tokens`, `reasoning`, `temperature`, `tool_choice`, `tools`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Thinking Machines: Inkling Small (free)

- **Provider:** openrouter
- **ID:** `thinkingmachines/inkling-small:free`
- **Status:** ACTIVE
- **Description:** Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
- **Context Length:** 1,048,576
- **Max Completion:** 262,144
- **Supported Parameters:** `frequency_penalty`, `include_reasoning`, `max_tokens`, `presence_penalty`, `reasoning`, `reasoning_effort`, `seed`, `stop`, `temperature`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

### Thinking Machines: Inkling (free)

- **Provider:** openrouter
- **ID:** `thinkingmachines/inkling:free`
- **Status:** ACTIVE
- **Description:** Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
- **Context Length:** 1,048,576
- **Max Completion:** 262,144
- **Supported Parameters:** `frequency_penalty`, `include_reasoning`, `max_tokens`, `presence_penalty`, `reasoning`, `reasoning_effort`, `seed`, `stop`, `temperature`, `tools`, `top_p`
- **First seen:** 2026-10-14 · **Last seen:** 2026-10-14

## Last run (changes)

No changes.