> ## Documentation Index
> Fetch the complete documentation index at: https://watermark.mintlify.site/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.

A key pays for every request from your credits, at the prices below, on every plan. A model's price is its maker's own list price. For some models the maker no longer sells, it is the maker's last published list price. Where neither applies, or no host can serve a tier at the maker's price, the price is 1.25 times the list price of the lowest-priced main host Morse uses for it. Where a maker's rate is below every host's cost, that rate rises to the lowest one a host can serve. When a request costs Morse less than its price, half of the difference returns to your balance as a rebate a few minutes after the hour it finished in ends. 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.

**Privacy**

**Weights**

Lab

of  models

**Chat**

## 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.

A model has one id, and a row for each [privacy tier](https://watermark.mintlify.site/models.md#what-each-tier-protects) it is sold at. The price of a tier is the same whichever of its providers serves the request. The Providers column lists them, each with the precision it publishes for a chat model's weights, or `unknown` where it publishes none. Morse chooses between them, and `provider.quantizations` limits a request to the providers that serve a precision it names. On `anon` and `private`, the provider that serves a request reads its prompt. On `tee` and `e2ee`, the attestation names the vendor. `GET /v1/models` lists the same tiers and prices for each model.

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.

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://watermark.mintlify.site/billing.md).

## Images

Image generation is not offered to API keys for now. The Morse app still makes images.

## Web search, page reading, research, and transcription

Web search, page reading, research, and transcription are not offered to API keys for now. The Morse app still uses them.

## Every price as a table

> [accordion] Chat models
>
> | Model | Tier | Providers | Context | Input | Cached input | Output |
> | - | - | - | - | - | - | - |
> | DeepSeek R1 `deepseek/deepseek-r1` | `private` | `novita` (fp8) | 64K | \$0.875 | \$0.875 | \$3.125 |
> | DeepSeek R1 0528 `deepseek/deepseek-r1-0528` | `private` | `deepinfra` (fp4) | 164K | \$0.55 | \$0.35 | \$2.19 |
> | DeepSeek V3 `deepseek/deepseek-v3` | `private` | `deepinfra` (fp4) | 164K | \$0.32 | \$0.32 | \$1.10 |
> | DeepSeek V3.1 `deepseek/deepseek-v3.1` | `private` | `deepinfra` (fp4) | 164K | \$0.56 | \$0.13 | \$1.68 |
> | DeepSeek V3.2 `deepseek/deepseek-v3.2` | `private` | `deepinfra` (fp4) | 164K | \$0.28 | \$0.13 | \$0.42 |
> | DeepSeek V4 Flash 0423 `deepseek/deepseek-v4-flash` | `private` | `deepinfra` (fp8) | 1M | \$0.14 | \$0.018 | \$0.28 |
> | DeepSeek V4 Flash 0731 `deepseek/deepseek-v4-flash-0731` | `private` | `novita` (fp8), `deepinfra` (fp8), `wafer` (nvfp4), `morph` (bf16) | 1M | \$0.44 | \$0.028 | \$1.32 |
> | DeepSeek V4 Flash 0731 `deepseek/deepseek-v4-flash-0731` | `tee` | `phala` (unknown) | 1M | \$0.55 | \$0.035 | \$1.65 |
> | DeepSeek V4 Flash 0731 `deepseek/deepseek-v4-flash-0731` | `e2ee` | `phala` (unknown) | 1M | \$0.55 | \$0.035 | \$1.65 |
> | DeepSeek V4 Flash Vision Exp `deepseek/deepseek-v4-flash-vision-exp` | `private` | `deepinfra` (fp8) | 1M | \$0.55 | \$0.0175 | \$1.65 |
> | DeepSeek V4 Pro `deepseek/deepseek-v4-pro-0813` | `private` | `deepinfra` (fp8), `novita` (fp8) | 1M | \$1.32 | \$0.13 | \$3.96 |
> | DeepSeek V4 Pro 0423 `deepseek/deepseek-v4-pro` | `private` | `deepinfra` (fp8) | 1M | \$1.625 | \$0.125 | \$3.25 |
> | DeepSeek V4.1 Flash `deepseek/deepseek-v4.1-flash` | `private` | `deepinfra` (fp8), `novita` (fp8), `wafer` (mxfp4), `morph` (fp8) | 1M | \$0.30 | \$0.006 | \$1.20 |
> | DeepSeek V4.1 Flash 1017 `deepseek/deepseek-v4.1-flash-1017` | `private` | `deepinfra` (fp8), `novita` (fp8), `wafer` (mxfp4), `morph` (fp8) | 1M | \$0.30 | \$0.006 | \$1.20 |
> | DeepSeek V4.1 Flash 1017 `deepseek/deepseek-v4.1-flash-1017` | `e2ee` | `tinfoil` (unknown) | 1M | \$0.75 | \$0.0125 | \$1.8125 |
> | DeepSeek V4.1 Flash 1017 Uncensored `deepseek-ai/deepseek-v4.1-flash-1017-abliterated` | `e2ee` | `near` (unknown) | 1M | \$0.375 | \$0.0075 | \$1.50 |
> | Gemma 3 12B `google/gemma-3-12b-it` | `private` | `deepinfra` (bf16) | 131K | \$0.0625 | \$0.0625 | \$0.1875 |
> | Gemma 3 27B `google/gemma-3-27b-it` | `private` | `deepinfra` (fp8) | 131K | \$0.10 | \$0.10 | \$0.20 |
> | Gemma 3 4B `google/gemma-3-4b-it` | `private` | `deepinfra` (bf16) | 131K | \$0.0625 | \$0.0625 | \$0.125 |
> | Gemma 4 26B A4B `google/gemma-4-26b-a4b-it` | `private` | `deepinfra` (fp8) | 262K | \$0.15 | \$0.07 | \$0.60 |
> | Gemma 4 31B `google/gemma-4-31b-it` | `private` | `deepinfra` (fp4 or fp8) | 262K | \$0.25 | \$0.25 | \$0.50 |
> | GLM 4.5 Air `z-ai/glm-4.5-air` | `private` | `novita` (bf16) | 131K | \$0.20 | \$0.03 | \$1.10 |
> | GLM 4.5V `z-ai/glm-4.5v` | `private` | `novita` (fp8) | 66K | \$0.60 | \$0.11 | \$1.80 |
> | GLM 4.6 `z-ai/glm-4.6` | `private` | `deepinfra` (fp4), `novita` (bf16) | 203K | \$0.60 | \$0.11 | \$2.20 |
> | GLM 4.6V `z-ai/glm-4.6v` | `private` | `novita` (bf16) | 131K | \$0.30 | \$0.055 | \$0.90 |
> | GLM 4.7 `z-ai/glm-4.7` | `private` | `deepinfra` (fp4), `novita` (fp8) | 203K | \$0.60 | \$0.11 | \$2.20 |
> | GLM 4.7 Flash `z-ai/glm-4.7-flash` | `private` | `novita` (bf16) | 200K | \$0.0875 | \$0.0125 | \$0.50 |
> | GLM 5 `z-ai/glm-5` | `private` | `novita` (fp8) | 203K | \$1.00 | \$0.20 | \$3.20 |
> | GLM 5.1 `z-ai/glm-5.1` | `private` | `novita` (fp8) | 205K | \$1.40 | \$0.26 | \$4.40 |
> | GLM 5.2 `z-ai/glm-5.2` | `private` | `deepinfra` (fp4), `wafer` (nvfp4), `novita` (fp8) | 1M | \$1.40 | \$0.26 | \$4.40 |
> | GLM 5.2 `z-ai/glm-5.2` | `e2ee` | `phala` (fp8) | 1M | \$1.40 | \$0.26 | \$4.40 |
> | GLM 5.3 `z-ai/glm-5.3` | `private` | `deepinfra` (fp4), `wafer` (nvfp4), `novita` (fp8) | 1M | \$1.40 | \$0.26 | \$4.40 |
> | GLM 5.3 `z-ai/glm-5.3` | `tee` | `phala` (unknown) | 1M | \$1.40 | \$0.26 | \$4.40 |
> | GLM 5.3 `z-ai/glm-5.3` | `e2ee` | `tinfoil` (nvfp4) | 1M | \$2.25 | \$0.5625 | \$7.1875 |
> | GLM 5.3 Flash `z-ai/glm-5.3-flash` | `private` | `isoquant` (unknown), `wafer` (nvfp4), `deepinfra` (fp4) | 1M | \$0.15 | \$0.03 | \$0.50 |
> | GLM 5.3 Flash `z-ai/glm-5.3-flash` | `tee` | `near` (fp8), `phala` (nvfp4) | 1M | \$0.15 | \$0.03 | \$0.50 |
> | GLM 5.3 Flash `z-ai/glm-5.3-flash` | `e2ee` | `near` (fp8), `phala` (nvfp4) | 1M | \$0.15 | \$0.03 | \$0.50 |
> | gpt-oss-120b `openai/gpt-oss-120b` | `private` | `deepinfra` (bf16) | 131K | \$0.04625 | \$0.04625 | \$0.2125 |
> | gpt-oss-120b `openai/gpt-oss-120b` | `tee` | `phala` (unknown) | 131K | \$0.1875 | \$0.1875 | \$0.75 |
> | gpt-oss-120b `openai/gpt-oss-120b` | `e2ee` | `phala` (unknown) | 131K | \$0.1875 | \$0.1875 | \$0.75 |
> | gpt-oss-20b `openai/gpt-oss-20b` | `private` | `deepinfra` (bf16) | 131K | \$0.0375 | \$0.0375 | \$0.175 |
> | Granite 4.2 8B `ibm-granite/granite-4.2-8b` | `private` | `deepinfra` (bf16) | 131K | \$0.075 | \$0.01875 | \$0.3125 |
> | Hy3 `tencent/hy3` | `private` | `novita` (unknown) | 262K | \$0.175 | \$0.04375 | \$0.725 |
> | Hy4 Preview `tencent/hy4-preview` | `private` | `deepinfra` (fp4), `novita` (fp8) | 1M | \$0.834 | \$0.042 | \$2.501 |
> | Inkling-Small `thinkingmachines/inkling-small` | `private` | `deepinfra` (fp8) | 524K | \$0.5625 | \$0.125 | \$1.50 |
> | Kimi K2 `moonshotai/kimi-k2` | `private` | `novita` (fp8) | 131K | \$0.60 | \$0.57 | \$2.50 |
> | Kimi K2 0905 `moonshotai/kimi-k2-0905` | `private` | `novita` (fp8) | 262K | \$0.75 | \$0.75 | \$3.125 |
> | Kimi K2 Thinking `moonshotai/kimi-k2-thinking` | `private` | `novita` (bf16) | 262K | \$0.75 | \$0.1875 | \$3.125 |
> | Kimi K2.5 `moonshotai/kimi-k2.5` | `private` | `novita` (unknown) | 262K | \$0.75 | \$0.125 | \$3.75 |
> | Kimi K2.6 `moonshotai/kimi-k2.6` | `private` | `novita` (unknown), `deepinfra` (fp4) | 262K | \$0.95 | \$0.16 | \$4.00 |
> | Kimi K2.6 `moonshotai/kimi-k2.6` | `tee` | `phala` (unknown) | 262K | \$1.3625 | \$0.4625 | \$5.75 |
> | Kimi K2.6 `moonshotai/kimi-k2.6` | `e2ee` | `phala` (unknown) | 262K | \$1.3625 | \$0.4625 | \$5.75 |
> | Kimi K2.7 Code `moonshotai/kimi-k2.7-code` | `private` | `novita` (int4) | 262K | \$0.95 | \$0.19 | \$4.00 |
> | Kimi K3 `moonshotai/kimi-k3` | `private` | `morph` (fp8), `wafer` (mxfp4), `deepinfra` (mxfp4) | 1M | \$3.00 | \$0.30 | \$15.00 |
> | Kimi K3 `moonshotai/kimi-k3` | `e2ee` | `phala` (unknown) | 1M | \$3.00 | \$0.30 | \$15.00 |
> | Kimi K3.1 Pro `moonshotai/kimi-k3.1-pro` | `private` | `novita` (unknown), `wafer` (mxfp4), `deepinfra` (bf16) | 1M | \$2.00 | \$0.20 | \$10.00 |
> | Kimi K3.1 Pro `moonshotai/kimi-k3.1-pro` | `tee` | `phala` (unknown) | 1M | \$2.00 | \$0.20 | \$10.00 |
> | Kimi K3.1 Pro `moonshotai/kimi-k3.1-pro` | `e2ee` | `tinfoil` (mxfp4) | 262K | \$5.00 | \$0.50 | \$25.00 |
> | L3.1 70B Euryale v2.2 `sao10k/l3.1-70b-euryale-v2.2` | `private` | `deepinfra` (fp8) | 131K | \$1.0625 | \$1.0625 | \$1.0625 |
> | Ling 3.0 Flash `inclusionai/ling-3.0-flash` | `private` | `novita` (unknown), `deepinfra` (bf16) | 262K | \$0.075 | \$0.015 | \$0.225 |
> | Ling 3.0 Flash Fin `inclusionai/ling-3.0-flash-fin` | `private` | `novita` (unknown) | 262K | \$0.09375 | \$0.01875 | \$0.275 |
> | Ling 3.0 Flash VL `inclusionai/ling-3.0-flash-vl` | `private` | `deepinfra` (fp16) | 131K | \$0.075 | \$0.015 | \$0.225 |
> | Ling 3.1 Flash `inclusionai/ling-3.1-flash` | `private` | `novita` (unknown) | 1M | \$0.375 | \$0.075 | \$1.125 |
> | Llama 3.1 8B `meta-llama/llama-3.1-8b-instruct` | `private` | `deepinfra` (fp8) | 131K | \$0.025 | \$0.025 | \$0.05 |
> | Llama 3.3 70B `meta-llama/llama-3.3-70b-instruct` | `private` | `deepinfra` (fp8) | 131K | \$0.125 | \$0.125 | \$0.40 |
> | Llama 4 Scout `meta-llama/llama-4-scout` | `private` | `deepinfra` (fp8) | 328K | \$0.125 | \$0.125 | \$0.375 |
> | MiMo V2.6 Flash `xiaomi/mimo-v2.6-flash` | `private` | `deepinfra` (fp8), `novita` (fp8) | 1M | \$0.14 | \$0.0028 | \$0.28 |
> | MiMo V2.6 Pro `xiaomi/mimo-v2.6-pro` | `private` | `deepinfra` (fp8), `novita` (fp8) | 1M | \$0.435 | \$0.0036 | \$0.87 |
> | MiniMax M2.5 `minimax/minimax-m2.5` | `private` | `novita` (unknown) | 205K | \$0.375 | \$0.0375 | \$1.50 |
> | MiniMax M2.7 `minimax/minimax-m2.7` | `private` | `novita` (unknown) | 205K | \$0.375 | \$0.075 | \$1.50 |
> | MiniMax M3 `minimax/minimax-m3` | `private` | `deepinfra` (fp8), `novita` (unknown) | 524K | \$0.30 | \$0.06 | \$1.20 |
> | Prompt over 512,000 tokens | | | | \$0.60 | \$0.12 | \$2.40 |
> | MiniMax M3.1 Flash `minimax/minimax-m3.1-flash` | `private` | `novita` (unknown), `wafer` (unknown) | 1M | \$0.15 | \$0.015 | \$0.60 |
> | Mistral Nemo `mistralai/mistral-nemo` | `private` | `deepinfra` (fp8) | 131K | \$0.03625 | \$0.03625 | \$0.0375 |
> | Mistral Small 3 2501 `mistralai/mistral-small-24b-instruct-2501` | `private` | `deepinfra` (fp8) | 33K | \$0.10 | \$0.10 | \$0.30 |
> | Mistral Small 3.2 `mistralai/mistral-small-3.2-24b-instruct` | `private` | `deepinfra` (fp8) | 128K | \$0.10 | \$0.10 | \$0.30 |
> | Muse Glimmer 30B `meta/muse-glimmer-30b` | `private` | `deepinfra` (bf16) | 131K | \$0.375 | \$0.05 | \$1.50 |
> | Nemotron 3 Super `nvidia/nemotron-3-super-120b-a12b` | `private` | `deepinfra` (bf16) | 262K | \$0.09375 | \$0.09375 | \$0.50 |
> | Nemotron 3 Ultra `nvidia/nemotron-3-ultra-550b-a55b` | `private` | `deepinfra` (fp4) | 262K | \$0.625 | \$0.125 | \$2.75 |
> | Nemotron 3.5 Lightning `nvidia/nemotron-3.5-lightning` | `private` | `deepinfra` (bf16) | 262K | \$0.075 | \$0.0375 | \$0.20 |
> | Nemotron 3.5 Super VL `nvidia/nemotron-3.5-super-vl` | `private` | `deepinfra` (fp4) | 262K | \$0.1875 | \$0.025 | \$0.625 |
> | Qwen2.5 72B Instruct `qwen/qwen-2.5-72b-instruct` | `private` | `deepinfra` (fp8) | 33K | \$0.45 | \$0.45 | \$0.50 |
> | Qwen2.5 7B Instruct `qwen/qwen-2.5-7b-instruct` | `tee` | `phala` (unknown) | 33K | \$0.125 | \$0.125 | \$0.25 |
> | Qwen2.5 7B Instruct `qwen/qwen-2.5-7b-instruct` | `e2ee` | `phala` (unknown) | 33K | \$0.125 | \$0.125 | \$0.25 |
> | Qwen3 14B `qwen/qwen3-14b` | `private` | `deepinfra` (fp8) | 41K | \$0.35 | \$0.35 | \$1.40 |
> | Qwen3 235B A22B Instruct 2507 `qwen/qwen3-235b-a22b-2507` | `private` | `deepinfra` (fp8) | 262K | \$0.23 | \$0.23 | \$0.92 |
> | Qwen3 30B A3B `qwen/qwen3-30b-a3b` | `private` | `deepinfra` (fp8) | 41K | \$0.20 | \$0.20 | \$0.80 |
> | Qwen3 32B `qwen/qwen3-32b` | `private` | `deepinfra` (fp8) | 41K | \$0.16 | \$0.16 | \$0.64 |
> | Qwen3 Coder 480B A35B `qwen/qwen3-coder` | `private` | `deepinfra` (fp4) | 262K | \$0.375 | \$0.125 | \$1.25 |
> | Qwen3 Next 80B A3B Instruct `qwen/qwen3-next-80b-a3b-instruct` | `private` | `deepinfra` (fp8) | 262K | \$0.15 | \$0.15 | \$1.20 |
> | Qwen3 VL 235B A22B `qwen/qwen3-vl-235b-a22b-instruct` | `private` | `deepinfra` (fp8) | 262K | \$0.40 | \$0.40 | \$1.60 |
> | Qwen3 VL 30B A3B `qwen/qwen3-vl-30b-a3b-instruct` | `private` | `deepinfra` (fp8) | 262K | \$0.20 | \$0.20 | \$0.80 |
> | Qwen3.5 122B A10B `qwen/qwen3.5-122b-a10b` | `private` | `novita` (bf16) | 262K | \$0.40 | \$0.40 | \$3.20 |
> | Qwen3.5 27B `qwen/qwen3.5-27b` | `private` | `novita` (bf16) | 262K | \$0.30 | \$0.30 | \$2.40 |
> | Qwen3.5 35B A3B `qwen/qwen3.5-35b-a3b` | `private` | `deepinfra` (fp8), `novita` (bf16) | 262K | \$0.25 | \$0.25 | \$2.00 |
> | Qwen3.5 397B A17B `qwen/qwen3.5-397b-a17b` | `private` | `deepinfra` (fp8), `novita` (unknown) | 262K | \$0.60 | \$0.60 | \$3.60 |
> | Qwen3.5 9B `qwen/qwen3.5-9b` | `private` | `deepinfra` (bf16) | 262K | \$0.125 | \$0.125 | \$0.1875 |
> | Qwen3.6 27B `qwen/qwen3.6-27b` | `private` | `deepinfra` (fp8), `novita` (bf16) | 262K | \$0.60 | \$0.60 | \$3.60 |
> | Qwen3.6 35B A3B `qwen/qwen3.6-35b-a3b` | `private` | `deepinfra` (fp8), `novita` (bf16) | 262K | \$0.375 | \$0.375 | \$2.25 |
> | Qwen3.6 35B A3B `qwen/qwen3.6-35b-a3b` | `tee` | `phala` (unknown) | 262K | \$0.375 | \$0.375 | \$2.25 |
> | Qwen3.6 35B A3B `qwen/qwen3.6-35b-a3b` | `e2ee` | `near` (fp8) | 262K | \$0.375 | \$0.375 | \$2.25 |
> | Qwen3.8 27B `qwen/qwen3.8-27b` | `private` | `deepinfra` (bf16), `novita` (unknown), `wafer` (fp8) | 262K | \$0.50 | \$0.10 | \$3.00 |
> | Qwen3.8 27B `qwen/qwen3.8-27b` | `tee` | `phala` (unknown) | 1M | \$0.50 | \$0.10 | \$3.00 |
> | Qwen3.8 27B `qwen/qwen3.8-27b` | `e2ee` | `near` (fp8) | 262K | \$0.50 | \$0.10 | \$3.00 |
> | Qwen3.8 Max `qwen/qwen3.8-2.4t-a95b` | `private` | `novita` (unknown) | 1M | \$2.00 | \$0.25 | \$6.00 |
> | Step 3.7 Flash `stepfun/step-3.7-flash` | `private` | `novita` (fp8) | 262K | \$0.20 | \$0.04 | \$1.15 |
> | WizardLM-2 8x22B `microsoft/wizardlm-2-8x22b` | `private` | `novita` (bf16) | 66K | \$0.775 | \$0.775 | \$0.775 |


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