> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sideren.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Available models

> Every model on Sideren with the lowest plan that includes it, its context window and its list price.

Request a model by name with the `model` field. Go includes 100 models, Starter and Pro 101, and Max and Scale 127; 16 more run only in [PAYG mode](https://docs.sideren.io/plans/pay-as-you-go.md#models-only-in-payg-mode), on purchased credit. Free has no models of its own for now.

**Lowest plan** is the cheapest plan that includes the model; every plan above it includes it too. In PAYG mode every model is available, whatever your plan. Each plan's page lists its models with cached-input prices too.

Closed-weight models are called by their name (`gpt-6.1-sol`). Open-weight models are called `@sdn/<name>` (`@sdn/glm-5.3`). The older spellings (`sdn-glm-5.3` and the bare `glm-5.3`) keep working. In YAML, quote an id that starts with `@`: `model: "@sdn/glm-5.3"`.

Prices are list prices in US dollars per 1M tokens. Each model's page on [sideren.io/models](https://www.sideren.io/models) has its description and capabilities.

> [!NOTE]
>
> This page is a snapshot. `GET /v1/models` is the live catalog, with `sideren.access` saying whether your plan includes each model ([Models endpoint](https://docs.sideren.io/api/models-endpoint.md)).

## Anthropic

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Claude Fable 5.1 `fable-5.1` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$10 | \$50 |
| Claude Opus 5.5 `opus-5.5` | [Max](https://docs.sideren.io/plans/max.md) | 1M | \$4 | \$20 |
| Claude Opus 5 `opus-5` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$5 | \$25 |
| Claude Sonnet 5.5 `sonnet-5.5` | [Starter](https://docs.sideren.io/plans/starter.md) | 1M | \$2 | \$10 |
| Claude Sonnet 5 `sonnet-5` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$3 | \$15 |
| Claude Opus 4.8 `opus-4.8` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$5 | \$25 |
| Claude Opus 4.6 `opus-4.6` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$5 | \$25 |
| Sonnet 4.6 `sonnet-4.6` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 200K | \$3 | \$15 |
| Claude Opus 4.5 `opus-4.5` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 200K | \$5 | \$25 |
| Claude Haiku 5.5 `haiku-5.5` | [Go](https://docs.sideren.io/plans/go.md) | 100K | \$0.1 | \$0.5 |

`opus-4.5` retires on Nov 24, 2026: move to `opus-4.6`.

## Meta

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Muse Wonder 1.0 `muse-wonder-1.0` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$4 | \$20 |
| Muse Spark 1.3 `muse-spark-1.3` | [Go](https://docs.sideren.io/plans/go.md) | 1.05M | \$1.25 | \$4.25 |
| Muse Spark 1.3 Contributor `muse-spark-1.3-contributor` | [Go](https://docs.sideren.io/plans/go.md) | 1.05M | \$0.1 | \$0.2 |
| Llama 4 Maverick `@sdn/llama-4-maverick` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.24 | \$0.97 |
| Llama 3.3 70B `@sdn/llama-3.3-70b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.72 | \$0.72 |
| Llama 3.1 70B `@sdn/llama-3.1-70b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.72 | \$0.72 |
| Llama 3.2 11B Vision `@sdn/llama-3.2-11b-vision` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.049 | \$0.676 |
| Llama 4 Scout `@sdn/llama-4-scout` | [Go](https://docs.sideren.io/plans/go.md) | 3.5M | \$0.17 | \$0.66 |
| Llama 3.2 3B `@sdn/llama-3.2-3b` | [Go](https://docs.sideren.io/plans/go.md) | 80K | \$0.051 | \$0.335 |
| Llama 3 70B `@sdn/llama-3-70b` | [Go](https://docs.sideren.io/plans/go.md) | 8K | \$2.65 | \$3.5 |
| Llama 3.1 8B `@sdn/llama-3.1-8b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.22 | \$0.22 |
| Llama 3.2 1B `@sdn/llama-3.2-1b` | [Go](https://docs.sideren.io/plans/go.md) | 60K | \$0.027 | \$0.201 |
| Llama 3 8B `@sdn/llama-3-8b` | [Go](https://docs.sideren.io/plans/go.md) | 8K | \$0.3 | \$0.6 |

`muse-spark-1.3-contributor`: Meta may use prompts and replies to train its models. A key with zero data retention can't use it.

## Google

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Gemini 4 Argon `gemini-4-argon` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$2 | \$10 |
| Gemini 3.1 Pro Preview `gemini-3.1-pro-preview` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 200K | \$2 | \$12 |
| Gemini 3.8 Flash `gemini-3.8-flash` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1M | \$0.75 | \$3.75 |
| Gemini 3.7 Flash `gemini-3.7-flash` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$0.75 | \$3.75 |
| Gemini 3.6 Flash `gemini-3.6-flash` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$0.75 | \$3.75 |
| Gemini 3.5 Flash `gemini-3.5-flash` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$1.5 | \$9 |
| Gemini 3.5 Flash Lite `gemini-3.5-flash-lite` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$0.3 | \$2.5 |
| Gemini 3.1 Flash Lite `gemini-3.1-flash-lite` | [PAYG only](https://docs.sideren.io/plans/pay-as-you-go.md) | 1.05M | \$0.25 | \$1.5 |
| Gemma 4 26B `@sdn/gemma-4-26b` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$0.1 | \$0.3 |
| Gemma 3 27B `@sdn/gemma-3-27b` | [Go](https://docs.sideren.io/plans/go.md) | 203K | \$0.12 | \$0.2 |
| Gemma 3 12B `@sdn/gemma-3-12b` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.05 | \$0.1 |
| Gemma 3 4B `@sdn/gemma-3-4b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.04 | \$0.08 |

## OpenAI

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| GPT-6 Astra `gpt-6-astra` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$10 | \$50 |
| GPT-6.1 Sol `gpt-6.1-sol` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$2 | \$10 |
| GPT-6 Sol `gpt-6-sol` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$2 | \$10 |
| GPT-5.6 Sol `gpt-5.6-sol` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$5 | \$30 |
| GPT-5.5 `gpt-5.5` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$5 | \$30 |
| GPT-6.1 Terra `gpt-6.1-terra` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$1 | \$5 |
| GPT-5 Codex `gpt-5-codex` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.25 | \$10 |
| GPT-5.6 Terra `gpt-5.6-terra` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$2 | \$12 |
| GPT-5.4 `gpt-5.4` | [Max](https://docs.sideren.io/plans/max.md) | 272K | \$2.5 | \$15 |
| GPT-5.3 Codex `gpt-5.3-codex` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.75 | \$14 |
| GPT-5.2 `gpt-5.2` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.75 | \$14 |
| GPT-5.2 Codex `gpt-5.2-codex` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.75 | \$14 |
| GPT-5.1 `gpt-5.1` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.25 | \$10 |
| GPT-5.1 Codex Max `gpt-5.1-codex-max` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.25 | \$10 |
| GPT-5.1 Codex `gpt-5.1-codex` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.25 | \$10 |
| GPT-5 `gpt-5` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$1.25 | \$10 |
| GPT-5.4 mini `gpt-5.4-mini` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$0.75 | \$4.5 |
| GPT-6 Luna `gpt-6-luna` | [Go](https://docs.sideren.io/plans/go.md) | 272K | \$0.1 | \$0.5 |
| GPT-5.6 Luna `gpt-5.6-luna` | [Go](https://docs.sideren.io/plans/go.md) | 272K | \$0.2 | \$1.2 |
| GPT-5.1 Codex mini `gpt-5.1-codex-mini` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$0.25 | \$2 |
| GPT Chat (latest) `gpt-chat-latest` | [Max](https://docs.sideren.io/plans/max.md) | 200K | \$5 | \$30 |
| GPT-5 mini `gpt-5-mini` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$0.25 | \$2 |
| GPT-5.4 nano `gpt-5.4-nano` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$0.2 | \$1.25 |
| GPT-4.1 `gpt-4.1` | [Max](https://docs.sideren.io/plans/max.md) | 1.05M | \$2 | \$8 |
| GPT-5 nano `gpt-5-nano` | [Max](https://docs.sideren.io/plans/max.md) | 400K | \$0.05 | \$0.4 |
| GPT-OSS 120B `@sdn/gpt-oss-120b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.35 | \$0.75 |
| GPT-4.1 mini `gpt-4.1-mini` | [Max](https://docs.sideren.io/plans/max.md) | 1.05M | \$0.4 | \$1.6 |
| GPT-OSS Safeguard 120B `@sdn/gpt-oss-safeguard-120b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.15 | \$0.6 |
| GPT-4.1 nano `gpt-4.1-nano` | [Max](https://docs.sideren.io/plans/max.md) | 1.05M | \$0.1 | \$0.4 |
| GPT-OSS Safeguard 20B `@sdn/gpt-oss-safeguard-20b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.07 | \$0.2 |
| GPT-OSS 20B `@sdn/gpt-oss-20b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.2 | \$0.3 |

`gpt-chat-latest` retires on Dec 2, 2026.

## Moonshot AI

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Kimi K3.1 Pro `@sdn/kimi-k3.1-pro` | [Go](https://docs.sideren.io/plans/go.md) | 1.05M | \$2 | \$10 |
| Kimi K3 `@sdn/kimi-k3` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$3 | \$15 |
| Kimi K2.7 Code `@sdn/kimi-k2.7-code` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.95 | \$4 |
| Kimi K2.6 `@sdn/kimi-k2.6` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.95 | \$4 |
| Kimi K2.5 `@sdn/kimi-k2.5` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.6 | \$3 |
| Kimi K2 Thinking `@sdn/kimi-k2-thinking` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.6 | \$2.5 |

## Z.ai

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| GLM 5.3 `@sdn/glm-5.3` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$1.4 | \$4.4 |
| GLM 5.2 `@sdn/glm-5.2` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$1.4 | \$4.4 |
| GLM 5.3 Flash `@sdn/glm-5.3-flash` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.15 | \$0.5 |
| GLM 5.3 Flash Ultra Fast `@sdn/glm-5.3-flash-ultra-fast` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.3 | \$1 |
| GLM 5 `@sdn/glm-5` | [Go](https://docs.sideren.io/plans/go.md) | 200K | \$1 | \$3.2 |
| GLM 4.7 `@sdn/glm-4.7` | [Go](https://docs.sideren.io/plans/go.md) | 200K | \$0.6 | \$2.2 |
| GLM 4.6 `@sdn/glm-4.6` | [Go](https://docs.sideren.io/plans/go.md) | 200K | \$0.6 | \$2.2 |
| GLM 4.7 Flash `@sdn/glm-4.7-flash` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.0605 | \$0.4 |

`@sdn/glm-5.3-flash-ultra-fast` is 50% off at launch, from Nov 8, 2026, 17:00 UTC until Nov 15, 2026, 17:00 UTC. The table shows its list price, which applies after.

## DeepSeek

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| DeepSeek V4 Pro `@sdn/deepseek-v4-pro` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$1.32 | \$3.96 |
| DeepSeek V4 Flash `@sdn/deepseek-v4-flash` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.44 | \$1.32 |
| DeepSeek V4.1 Flash 1017 `@sdn/deepseek-v4.1-flash-1017` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.3 | \$1.2 |
| DeepSeek V4.1 Flash Ultra Fast `@sdn/deepseek-v4.1-flash-ultra-fast` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.6 | \$2.4 |
| DeepSeek V3.2 `@sdn/deepseek-v3.2` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.57 | \$1.71 |
| DeepSeek V3.1 `@sdn/deepseek-v3.1` | [Go](https://docs.sideren.io/plans/go.md) | 164K | \$0.58 | \$1.68 |
| DeepSeek R1 `@sdn/deepseek-r1` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$1.35 | \$5.4 |

`@sdn/deepseek-v4.1-flash-ultra-fast` is 50% off at launch, from Nov 8, 2026, 17:00 UTC until Nov 15, 2026, 17:00 UTC. The table shows its list price, which applies after.

## xAI

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Grok 4.7 `grok-4.7` | [Go](https://docs.sideren.io/plans/go.md) | 200K | \$2 | \$6 |
| Grok 4.6 `grok-4.6` | [Go](https://docs.sideren.io/plans/go.md) | 500K | \$2 | \$6 |
| Grok 4.3 `grok-4.3` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$1.25 | \$2.5 |
| Grok 4 `grok-4` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$3 | \$15 |
| Grok 4.20 `grok-4.20` | [Go](https://docs.sideren.io/plans/go.md) | 2M | \$1.25 | \$2.5 |
| Grok 4.20 (non-reasoning) `grok-4.20-non-reasoning` | [Go](https://docs.sideren.io/plans/go.md) | 2M | \$1.25 | \$2.5 |
| Grok 4.1 Fast `grok-4.1-fast` | [Go](https://docs.sideren.io/plans/go.md) | 2M | \$0.2 | \$0.5 |

## Alibaba Qwen

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Qwen3 Coder 480B `@sdn/qwen3-coder-480b` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.45 | \$1.8 |
| Qwen3 235B `@sdn/qwen3-235b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.22 | \$0.88 |
| Qwen 3.8 27B `@sdn/qwen3.8-27b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.45 | \$3.2 |
| Qwen3 Coder Next `@sdn/qwen3-coder-next` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.5 | \$1.2 |
| Qwen3 VL 235B `@sdn/qwen3-vl-235b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.3 | \$1.5 |
| Qwen3 Next 80B `@sdn/qwen3-next-80b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.14 | \$1.2 |
| Qwen3 Coder 30B `@sdn/qwen3-coder-30b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.15 | \$0.6 |
| Qwen3 30B A3B `@sdn/qwen3-30b-a3b` | [Go](https://docs.sideren.io/plans/go.md) | 33K | \$0.051 | \$0.335 |
| Qwen3 32B `@sdn/qwen3-32b` | [Go](https://docs.sideren.io/plans/go.md) | 16K | \$0.15 | \$0.6 |
| Qwen2.5 Coder 32B `@sdn/qwen2.5-coder-32b` | [Go](https://docs.sideren.io/plans/go.md) | 33K | \$0.66 | \$1 |

## Cohere

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Command A `@sdn/command-a` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$2.5 | \$10 |

## MiniMax

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| MiniMax M3.1 Flash `@sdn/minimax-m3.1-flash` | [Go](https://docs.sideren.io/plans/go.md) | 300K | \$0.15 | \$0.6 |
| MiniMax M2.5 `@sdn/minimax-m2.5` | [Go](https://docs.sideren.io/plans/go.md) | 197K | \$0.3 | \$1.2 |
| MiniMax M2.1 `@sdn/minimax-m2.1` | [Go](https://docs.sideren.io/plans/go.md) | 205K | \$0.3 | \$1.2 |
| MiniMax M2 `@sdn/minimax-m2` | [Go](https://docs.sideren.io/plans/go.md) | 205K | \$0.3 | \$1.2 |

## Sarvam

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Sarvam 105B `@sdn/sarvam-105b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.18 | \$0.7 |
| Sarvam 105B Conversations `sarvam-105b-conversations` | [Go](https://docs.sideren.io/plans/go.md) | 32K | \$0.18 | \$0.7 |

## Mistral AI

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Mistral Medium 3.5 `mistral-medium-3.5` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$1.5 | \$7.5 |
| Devstral 2 123B `@sdn/devstral-2-123b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.4 | \$2 |
| Mistral Large 3 675B `@sdn/mistral-large-3-675b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.5 | \$1.5 |
| Magistral Small `@sdn/magistral-small` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.5 | \$1.5 |
| Mistral Small 3.1 `@sdn/mistral-small-3.1` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.351 | \$0.555 |
| Pixtral Large `@sdn/pixtral-large` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$2 | \$6 |
| Mistral Large 24.02 `@sdn/mistral-large-2402` | [Go](https://docs.sideren.io/plans/go.md) | 33K | \$4 | \$12 |
| Ministral 14B `@sdn/ministral-14b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.2 | \$0.2 |
| Mistral Small `@sdn/mistral-small` | [Go](https://docs.sideren.io/plans/go.md) | 33K | \$1 | \$3 |
| Ministral 8B `@sdn/ministral-8b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.15 | \$0.15 |
| Ministral 3B `@sdn/ministral-3b` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$0.1 | \$0.1 |

## NVIDIA

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Nemotron 3 120B `@sdn/nemotron-3-120b` | [Go](https://docs.sideren.io/plans/go.md) | 256K | \$0.5 | \$1.5 |
| Nemotron Super 3 120B `@sdn/nemotron-super-3-120b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.15 | \$0.65 |
| Nemotron Nano 3 30B `@sdn/nemotron-nano-3-30b` | [Go](https://docs.sideren.io/plans/go.md) | 262K | \$0.06 | \$0.24 |
| Nemotron Nano 12B `@sdn/nemotron-nano-12b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.2 | \$0.6 |

## Microsoft

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Phi-4 `@sdn/phi-4` | [Go](https://docs.sideren.io/plans/go.md) | 16K | \$0.125 | \$0.5 |
| Phi-4 mini `@sdn/phi-4-mini` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.075 | \$0.3 |

## Amazon

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Nova Pro `nova-pro` | [Go](https://docs.sideren.io/plans/go.md) | 300K | \$0.8 | \$3.2 |
| Nova 2 Lite `nova-2-lite` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.33 | \$2.75 |
| Nova Lite `nova-lite` | [Go](https://docs.sideren.io/plans/go.md) | 300K | \$0.06 | \$0.24 |
| Nova Micro `nova-micro` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.035 | \$0.14 |

## Writer

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Palmyra X5 `palmyra-x5` | [Go](https://docs.sideren.io/plans/go.md) | 1M | \$0.6 | \$6 |
| Palmyra X4 `palmyra-x4` | [Go](https://docs.sideren.io/plans/go.md) | 123K | \$2.5 | \$10 |

## AI Singapore

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Gemma Sea Lion v4 27B `@sdn/gemma-sea-lion-v4-27b` | [Go](https://docs.sideren.io/plans/go.md) | 128K | \$0.351 | \$0.555 |

## IBM

| Model | Lowest plan | Context | Input | Output |
| - | - | - | -: | -: |
| Granite 4.0 H Micro `@sdn/granite-4.0-h-micro` | [Go](https://docs.sideren.io/plans/go.md) | 131K | \$0.017 | \$0.112 |

## Embedding models

Text in, vectors out ([Embeddings](https://docs.sideren.io/api/embeddings.md)). They have no output price.

| Model | Lowest plan | Max input | Input |
| - | - | - | -: |
| Qwen3 Embedding 0.6B `@sdn/qwen3-embed-0.6b` | [Go](https://docs.sideren.io/plans/go.md) | 8K | \$0.02 |
| BGE-M3 `@sdn/bge-m3` | [Go](https://docs.sideren.io/plans/go.md) | 8K | \$0.02 |
| BGE Large EN v1.5 `@sdn/bge-large-en` | [Go](https://docs.sideren.io/plans/go.md) | 1K | \$0.21 |
| EmbeddingGemma 300M `@sdn/embed-gemma-300m` | [Go](https://docs.sideren.io/plans/go.md) | 2K | \$0.02 |
| BGE Base EN v1.5 `@sdn/bge-base-en` | [Go](https://docs.sideren.io/plans/go.md) | 1K | \$0.07 |
| PLaMo Embedding 1B `@sdn/plamo-embed-1b` | [Go](https://docs.sideren.io/plans/go.md) | 4K | \$0.02 |
| BGE Small EN v1.5 `@sdn/bge-small-en` | [Go](https://docs.sideren.io/plans/go.md) | 1K | \$0.03 |

## Longer prompts

These models accept prompts beyond the context window agents plan compaction around. The context window is `context_window` in `GET /v1/models`; the longest prompt is `sideren.max_context_window`.

| Model | Context window | Longest prompt |
| - | - | - |
| GPT-6 Astra `gpt-6-astra` | 272K | 1.05M |
| GPT-6.1 Sol `gpt-6.1-sol` | 272K | 1.05M |
| GPT-6 Sol `gpt-6-sol` | 272K | 1.05M |
| GPT-5.6 Sol `gpt-5.6-sol` | 272K | 1.05M |
| GPT-5.5 `gpt-5.5` | 272K | 1.05M |
| GPT-6.1 Terra `gpt-6.1-terra` | 272K | 1.05M |
| GPT-5.6 Terra `gpt-5.6-terra` | 272K | 1.05M |
| Gemini 3.1 Pro Preview `gemini-3.1-pro-preview` | 200K | 1.05M |
| GPT-5.4 `gpt-5.4` | 272K | 1.05M |
| Grok 4.7 `grok-4.7` | 200K | 500K |
| GPT-6 Luna `gpt-6-luna` | 272K | 1.05M |
| GPT-5.6 Luna `gpt-5.6-luna` | 272K | 1.05M |

## Which model answers

The response's `model` field and the `sideren-model` header echo the id you sent. If the model you name is unavailable, the API may serve the request with a comparable model and keep your conversation moving; catalog rows marked `delivery: "optimized"` are compatibility ids whose physical model is chosen for you. Pin a `delivery: "exact"` id for anything whose exact behavior you depend on ([Model routing](https://docs.sideren.io/guides/model-routing.md)).

* A model on a higher plan returns `400 plan_upgrade_required`, and the message names the cheapest plan that includes it.
* A PAYG-only model requested without PAYG mode returns `400 payg_required`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.