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

# Pricing

> What each model costs through the API: chat per million tokens, images per image, and web search, page reading, and transcription per call.

A key pays for every request from your credits, at the prices below, on every plan. One credit is \$0.01. `GET /v1/models` lists the same prices in micros, a millionth of a dollar. Morse writes this page from the prices production bills, so it changes when they do.

**Type**

**Privacy**

**Weights**

Lab

of  models

**Chat**

**Image**

**Web and audio**

## How chat is priced

Chat prices are per million tokens. Input is the prompt, and cached input is the part of it the model's vendor reads from its prompt cache. Output counts every token the model writes, its reasoning included. Context is the most tokens a request can hold, prompt and output together.

The same model at two [privacy tiers](https://docs.trymorse.ai/models.md#what-each-tier-protects) has two ids, and a row for each.

A "Prompt over" row is the price of a long prompt. Once a prompt passes that length, the whole request, its output included, pays those prices.

On most models, the prompt tokens the vendor writes to its cache cost the input price. These models charge more for them, per million tokens.

| Model | Cache write | Long-prompt cache write |
| - | - | - |
| GPT-6 Astra `gpt-6-astra` | \$15.00 | \$30.00 |
| GPT-6 Luna `gpt-6-luna` | \$0.15 | \$0.30 |
| GPT-6.1 Sol `gpt-6.1-sol` | \$3.00 | \$6.00 |
| GPT-6.1 Terra `gpt-6.1-terra` | \$1.50 | \$3.00 |

Before a chat starts, Morse holds the most it could cost: the prompt at the cache-write price, plus the output limit. Set a lower `max_tokens` to hold less. When the reply ends, Morse charges what the tokens cost and returns the rest. See [Billing](https://docs.trymorse.ai/billing.md).

## How images are priced

Each image costs the price per image, plus the price per reference image for each reference image you send. Each image costs at least one credit, and you pay only for the images delivered.

The price per image is what Morse holds for each image. Most image vendors report what each image cost, and Morse then charges by that report, so an image can cost a little more or less than its listed price.

## How web search, page reading, and transcription are priced

Each call costs a flat price, on top of any chat it serves. A failed call costs nothing.

## Every price as a table

> [accordion] Chat models
>
> | Model | Tier | Context | Input | Cached input | Output |
> | - | - | - | - | - | - |
> | Claude Fable 5.1 `claude-fable-5-1` | `anon` | 1M | \$12.00 | \$0.30 | \$60.00 |
> | Claude Haiku 5.5 `claude-haiku-5-5` | `anon` | 1M | \$0.12 | \$0.012 | \$0.60 |
> | Prompt over 100,000 tokens | | | \$0.60 | \$0.06 | \$3.00 |
> | Claude Opus 5.5 `claude-opus-5-5` | `anon` | 1M | \$4.80 | \$0.24 | \$24.00 |
> | Claude Sonnet 5.5 `claude-sonnet-5-5` | `anon` | 1M | \$2.40 | \$0.12 | \$12.00 |
> | DeepSeek V4 Flash 0731 `deepseek/deepseek-v4-flash-0731` | `e2ee` | 1M | \$0.528 | \$0.0336 | \$1.584 |
> | DeepSeek V4 Pro `deepseek-v4-pro` | `private` | 1M | \$1.584 | \$0.156 | \$4.752 |
> | DeepSeek V4.1 Flash `deepseek-v4.1-flash` | `private` | 1M | \$0.36 | \$0.0072 | \$1.44 |
> | DeepSeek V4.1 Flash 1017 `deepseek-v4.1-flash-1017` | `private` | 1M | \$0.36 | \$0.0096 | \$1.44 |
> | DeepSeek V4.1 Flash 1017 `deepseek/deepseek-v4.1-flash-1017` | `e2ee` | 1M | \$0.90 | \$0.18 | \$1.92 |
> | DeepSeek V4.1 Flash Uncensored `deepseek-v4.1-flash-uncensored` | `private` | 1M | \$0.396 | \$0.0099 | \$1.584 |
> | Gemini 3.8 Flash `gemini-3.8-flash` | `anon` | 1M | \$0.90 | \$0.09 | \$4.50 |
> | Gemini 4 Argon `gemini-4-argon` | `anon` | 1M | \$2.40 | \$0.12 | \$12.00 |
> | Gemma 4 26B A4B Uncensored `gemma-4-26b-a4b-uncensored-tee` | `tee` | 262K | \$0.18 | \$0.06 | \$0.84 |
> | Gemma 4 26B A4B Uncensored `phala/gemma-4-26b-a4b-uncensored` | `e2ee` | 262K | \$0.18 | \$0.06 | \$0.84 |
> | GLM 5.2 `glm-5.2` | `private` | 1M | \$1.68 | \$0.312 | \$5.28 |
> | GLM 5.2 `z-ai/glm-5.2` | `e2ee` | 1M | \$1.512 | \$0.264 | \$3.60 |
> | GLM 5.3 `glm-5.3` | `private` | 1M | \$1.68 | \$0.312 | \$5.28 |
> | GLM 5.3 `glm-5.3-tee` | `tee` | 1M | \$1.68 | \$0.312 | \$5.28 |
> | GLM 5.3 `z-ai/glm-5.3` | `e2ee` | 1M | \$1.68 | \$0.312 | \$5.28 |
> | GLM 5.3 Flash `glm-5.3-flash` | `private` | 1M | \$0.18 | \$0.036 | \$0.60 |
> | GLM 5.3 Flash `glm-5.3-flash-tee` | `tee` | 1M | \$0.18 | \$0.036 | \$0.60 |
> | GLM 5.3 Flash `z-ai/glm-5.3-flash` | `e2ee` | 1M | \$0.18 | \$0.036 | \$0.60 |
> | GPT-6 Astra `gpt-6-astra` | `anon` | 1.1M | \$12.00 | \$1.20 | \$60.00 |
> | Prompt over 272,000 tokens | | | \$24.00 | \$2.40 | \$90.00 |
> | GPT-6 Luna `gpt-6-luna` | `anon` | 1.1M | \$0.12 | \$0.012 | \$0.60 |
> | Prompt over 272,000 tokens | | | \$0.24 | \$0.024 | \$0.90 |
> | GPT-6.1 Sol `gpt-6.1-sol` | `anon` | 1.1M | \$2.40 | \$0.12 | \$12.00 |
> | Prompt over 272,000 tokens | | | \$4.80 | \$0.24 | \$18.00 |
> | GPT-6.1 Terra `gpt-6.1-terra` | `anon` | 1.1M | \$1.20 | \$0.06 | \$6.00 |
> | Prompt over 272,000 tokens | | | \$2.40 | \$0.12 | \$9.00 |
> | Grok 4.3 `grok-4.3` | `private` | 1M | \$1.50 | \$0.24 | \$3.00 |
> | Prompt over 200,000 tokens | | | \$3.00 | \$0.48 | \$6.00 |
> | Grok 4.7 `grok-4.7` | `private` | 500K | \$2.40 | \$0.60 | \$7.20 |
> | Prompt over 200,000 tokens | | | \$4.80 | \$1.20 | \$14.40 |
> | Kimi K2.6 `moonshotai/kimi-k2.6` | `e2ee` | 262K | \$1.308 | \$0.444 | \$5.52 |
> | Kimi K3 `kimi-k3` | `private` | 1M | \$3.60 | \$0.36 | \$18.00 |
> | Kimi K3 `moonshotai/kimi-k3` | `e2ee` | 1M | \$3.60 | \$0.36 | \$18.00 |
> | Kimi K3.1 Pro `kimi-k3.1-pro` | `private` | 1M | \$2.40 | \$0.24 | \$12.00 |
> | MiniMax M3.1 Flash `minimax-m3.1-flash` | `private` | 1M | \$0.18 | \$0.018 | \$0.72 |
> | Muse Spark 1.3 `muse-spark-1.3` | `anon` | 1M | \$1.50 | \$0.18 | \$5.10 |
> | Muse Wonder `muse-wonder-1.0` | `anon` | 1M | \$4.80 | \$0.24 | \$24.00 |
> | Qwen3.6 35B A3B `Qwen/Qwen3.6-35B-A3B-FP8` | `e2ee` | 262K | \$0.204 | \$0.0672 | \$1.32 |
> | Qwen3.8 27B `Qwen/Qwen3.8-27B` | `e2ee` | 262K | \$0.048 | \$0.0216 | \$1.62 |
> | Qwen3.8 27B Uncensored `qwen3.8-27b-uncensored-tee` | `tee` | 262K | \$0.36 | \$0.06 | \$1.80 |
> | Qwen3.8 27B Uncensored `phala/qwen3.8-27b-uncensored` | `e2ee` | 262K | \$0.36 | \$0.06 | \$1.80 |

> [accordion] Image models
>
> | Model | Tier | Per image | Per reference image |
> | - | - | - | - |
> | CyberRealistic (Uncensored) `cyberillustrious` | `anon` | \$0.01 | \$0.00 |
> | CyberRealistic XL (Uncensored) `cyberrealistic-xl` | `anon` | \$0.01 | \$0.00 |
> | FLUX.2 \[max] `flux-2-max` | `anon` | \$0.192 | \$0.144 |
> | FLUX.2 \[pro] `flux-2-pro` | `anon` | \$0.09 | \$0.072 |
> | Grok Imagine Image 2.0 `grok-imagine-image-2.0` | `private` | \$0.096 | \$0.012 |
> | Hassaku XL Anime (Uncensored) `hassaku-xl` | `anon` | \$0.01 | \$0.00 |
> | Ideogram 4.5 `ideogram-4.5` | `anon` | \$0.264 | \$0.00 |
> | Krea 2 Turbo (Uncensored) `krea-2-turbo-uncensored` | `anon` | \$0.06 | \$0.00 |
> | Nano Banana 2 `gemini-3.1-flash-image` | `anon` | \$0.132 | \$0.00072 |
> | Nano Banana 2 Lite `gemini-3.1-flash-lite-image` | `anon` | \$0.048 | \$0.00036 |
> | Nano Banana Pro `gemini-3-pro-image` | `anon` | \$0.204 | \$0.00276 |
> | Qwen-Image-2.1-Turbo (Uncensored) `qwen-image-2.1-turbo-uncensored` | `anon` | \$0.02 | \$0.00 |
> | Qwen-Image-3.0 (Uncensored) `qwen-image-3-uncensored` | `anon` | \$0.04 | \$0.00345 |
> | Qwen-Image-3.0-Pro `qwen-image-3-pro` | `anon` | \$0.09 | \$0.0036 |
> | Qwen-Image-3.0-Pro (Uncensored) `qwen-image-3-pro-uncensored` | `anon` | \$0.09 | \$0.00345 |
> | RealVisXL V5.0 (Uncensored) `realvisxl-5` | `anon` | \$0.01 | \$0.00 |
> | Seedream 4.5 (Uncensored) `seedream-4.5-uncensored` | `anon` | \$0.048 | \$0.00 |
> | Seedream 5.0 Lite (Uncensored) `seedream-5-lite-uncensored` | `anon` | \$0.042 | \$0.00 |
> | Seedream 5.0 Pro `seedream-5-pro` | `anon` | \$0.162 | \$0.0054 |
> | Seedream 5.0 Pro (Uncensored) `seedream-5-pro-uncensored` | `anon` | \$0.11 | \$0.00345 |
> | Z-Image Turbo `z-image-turbo` | `anon` | \$0.024 | \$0.00 |

> [accordion] Web search, page reading, and transcription
>
> | Model | Tier | Endpoint | Per call |
> | - | - | - | - |
> | Parallel Extract `parallel-extract` | `anon` | `/v1/fetch` | \$0.001 |
> | Parallel Extract `parallel-extract-zdr` | `private` | `/v1/fetch` | \$0.001 |
> | Parallel Search `parallel-search` | `anon` | `/v1/search` | \$0.001 |
> | Parallel Search `parallel-search-zdr` | `private` | `/v1/search` | \$0.001 |
> | Whisper Large v3 `whisper-large-v3-tee` | `tee` | `/v1/audio/transcriptions` | \$0.0002 |


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