> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.singularityapi.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.singularityapi.dev/_mcp/server.

# Models & Pricing

## Chat models

| Model                    | Best for                                                           | Context window | Max output | Input \$/1M | Cached input \$/1M | Output \$/1M |
| ------------------------ | ------------------------------------------------------------------ | -------------- | ---------- | ----------- | ------------------ | ------------ |
| `deepseek-v4-pro`        | Hardest reasoning tasks                                            | 1,000,000      | 384,000    | \$0.392     | \$0.128            | \$0.783      |
| `deepseek-v4.1-flash`    | Newest DeepSeek Flash, fast and cheap (promotional pricing)        | 1,048,576      | 384,000    | \$0.13      | \$0.003            | \$0.50       |
| `deepseek-v4-flash`      | Fast, cheap default workhorse                                      | 1,000,000      | 384,000    | \$0.081     | \$0.007            | \$0.162      |
| `deepseek-v4-flash-0731` | Pinned V4-Flash snapshot                                           | 1,048,576      | 384,000    | \$0.20      | \$0.007            | \$0.50       |
| `deepseek-v3.2`          | Solid general model                                                | 128,000        | 128,000    | \$0.186     | —                  | \$0.280      |
| `kimi-k2.7-code`         | Coding and agentic coding                                          | 262,144        | 262,144    | \$0.639     | \$0.152            | \$3.150      |
| `kimi-k2.6`              | General and long-form                                              | 262,144        | 262,144    | \$0.581     | \$0.128            | \$2.448      |
| `kimi-k3`                | Long-context reasoning and agents                                  | 1,048,576      | 262,144    | \$2.50      | \$0.30             | \$14.00      |
| `glm-5.3`                | General reasoning and agentic tasks                                | 1,048,573      | 131,072    | \$1.17      | \$0.245            | \$3.96       |
| `gpt-5.6-sol`            | Frontier flagship                                                  | 1,000,000      | 128,000    | \$2.40      | \$0.20             | \$14.00      |
| `gpt-5.6-terra`          | Frontier, balanced cost                                            | 1,000,000      | 128,000    | \$1.80      | \$0.20             | \$10.00      |
| `gpt-5.6-luna`           | Frontier, budget                                                   | 1,000,000      | 128,000    | \$0.18      | \$0.02             | \$1.10       |
| `gpt-6-astra`            | GPT-6 flagship, hardest work (promotional pricing)                 | 1,000,000      | 128,000    | \$8.00      | \$1.00             | \$30.00      |
| `gpt-6-sol`              | GPT-6, complex coding and professional tasks (promotional pricing) | 1,000,000      | 128,000    | \$1.80      | \$0.20             | \$8.00       |
| `gpt-6-luna`             | GPT-6, fast high-volume everyday work                              | 1,000,000      | 128,000    | \$0.10      | \$0.01             | \$0.40       |
| `gpt-6.1-sol`            | GPT-6.1, newest flagship for complex coding and professional tasks | 1,000,000      | 128,000    | \$2.00      | \$0.10             | \$10.00      |
| `claude-opus-5-5`        | Claude Opus 5.5, deepest reasoning and agentic work                | 1,000,000      | 128,000    | \$4.00      | \$0.12             | \$20.00      |
| `claude-sonnet-5-5`      | Claude Sonnet 5.5, balanced quality and cost                       | 1,000,000      | 128,000    | \$2.00      | \$0.12             | \$10.00      |
| `claude-haiku-5-5`       | Claude Haiku 5.5, fast and cheap                                   | 1,000,000      | 128,000    | \$0.10      | \$0.006            | \$0.50       |
| `claude-fable-5.1`       | Claude Fable 5.1, frontier-tier Mythos-class model                 | 1,000,000      | 128,000    | \$10.00     | \$0.15             | \$50.00      |

Prices are per million tokens, input and output priced separately. Where a model has a cached-input price, the input tokens the provider reports as cache hits bill at that rate instead of the input rate; the receipt shows the split. `deepseek-v3.2` has no cached tier.

The Claude models cache prompts automatically (no `cache_control` needed) and report cache **writes** as well as reads. Prompt tokens written to the cache on a turn bill at a cache-write price instead of the input price — `claude-opus-5-5` $3.00, `claude-sonnet-5-5` $1.50, `claude-haiku-5-5` $0.075, `claude-fable-5.1` $7.50 per million — and `GET /v1/models` reports it as `cache_write_per_million_usd`. Every other model has no cache-write price (`null`): written prompt tokens simply bill at the input price.

Prices marked *promotional* are introductory and can change; `GET /v1/models` reports `promotional_pricing: true` on them. Occasionally a model runs a short free window — `GET /v1/models` then shows a `free_until` timestamp on it, and requests completed before that moment are not charged.

The GPT models (`gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, and `gpt-6.1-sol`) and the Claude models (`claude-opus-5-5`, `claude-sonnet-5-5`, `claude-haiku-5-5`, and `claude-fable-5.1`) serve [`/v1/responses`](/api/responses) in addition to chat completions. The other chat models serve chat completions only.

`gpt-6.1-sol` always reasons, and its provider serves function tools only on the Responses surface — so a chat-completions request with tools is served through [`/v1/responses`](/api/responses) for you and comes back as an ordinary chat completion (the same way `max` is handled; see the table below). `temperature` other than 1 is rejected on it. Image inputs on the Claude models must be inline `data:` URLs; remote image URLs are rejected.

> **Note**
>
> Requests that omit the output-limit field get a per-model default: 4,096 tokens for `deepseek-v3.2`, 8,192 tokens for every other chat model listed above.

## Reasoning effort by model

Every chat model takes the OpenAI `reasoning_effort` field (`reasoning.effort` on [`/v1/responses`](/api/responses)) to set its thinking level. The accepted values differ per model. A value the model does not accept is rejected with a 400 — `Invalid request.` when the platform catches it, `The selected model could not complete the request.` when the provider does — and nothing is charged either way. Verified against production on 2026-09-24; the `gpt-6.1-sol` and Claude rows on 2026-10-21.

| Model                                                                                   | Accepted values                                                                                   | Field omitted       | Notes                                                                                                                                                                 |
| --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `deepseek-v4-pro`, `deepseek-v4.1-flash`, `deepseek-v4-flash`, `deepseek-v4-flash-0731` | `none`, `minimal`, `low`, `medium`, `high`                                                        | reasoning off       | `minimal` and above turn reasoning on; `none` keeps it off                                                                                                            |
| `deepseek-v3.2`                                                                         | `none`, `minimal`, `low`, `medium`, `high`                                                        | reasoning off       | only `medium` and `high` produce reasoning; `none`, `minimal`, and `low` behave like omitting the field                                                               |
| `kimi-k2.7-code`, `kimi-k2.6`                                                           | `none`, `low`, `medium`, `high`                                                                   | reasoning on        | `none` turns reasoning off; `minimal` is rejected                                                                                                                     |
| `kimi-k3`                                                                               | `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`                                        | reasoning on        | `none` turns reasoning off                                                                                                                                            |
| `glm-5.3`                                                                               | `low`, `medium`, `high`                                                                           | reasoning on        | `low` turns reasoning off (zero reasoning tokens); `none` and `minimal` are rejected                                                                                  |
| `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`                                          | `none`, `low`, `medium`, `high`, `xhigh` on chat completions; those plus `max` on `/v1/responses` | provider default    | `none` turns reasoning off; `minimal` is rejected on both endpoints                                                                                                   |
| `gpt-6-sol`, `gpt-6-luna`                                                               | `none`, `low`, `medium`, `high`, `xhigh`, `max` on both endpoints                                 | provider default    | `none` turns reasoning off; `minimal` is rejected; `max` on chat completions is served through the Responses surface for you                                          |
| `gpt-6-astra`                                                                           | `low`, `medium`, `high`, `xhigh`, `max` on both endpoints                                         | provider default    | always reasons — `none` and `minimal` are rejected; `max` on chat completions is served through the Responses surface for you                                         |
| `gpt-6.1-sol`                                                                           | `low`, `medium`, `high`, `xhigh`, `max` on both endpoints                                         | provider default    | always reasons — `none` and `minimal` are rejected; `max` on chat completions is served through the Responses surface for you; `temperature` other than 1 is rejected |
| `claude-opus-5-5`, `claude-sonnet-5-5`, `claude-haiku-5-5`                              | any value is accepted (`none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`)                | reasoning on (high) | the provider does not validate the value; `max` produces the most reasoning tokens                                                                                    |
| `claude-fable-5.1`                                                                      | any value is accepted (`none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`)                | reasoning off       | the provider does not validate the value; set an effort to turn reasoning on                                                                                          |

Reasoning tokens are billed as output tokens at the model's output rate and are included in `usage.completion_tokens`; the receipt shows the exact charge. The DeepSeek, Kimi, and GLM models return their thinking as `message.reasoning_content` (and `delta.reasoning_content` in streams) next to the normal `content`. The GPT models never return reasoning text — only the count in `usage.completion_tokens_details.reasoning_tokens`. The Claude models return reasoning text inconsistently (sometimes `message.reasoning` / `reasoning_content`, sometimes nothing) while always billing the reasoning tokens; do not depend on the text being present.

## Image generation models

Four models serve [`POST /v1/images/generations`](/api/image-generation). Image requests are never billed by tokens — the price is fixed by the request itself and the receipt settles at exactly that amount.

### FLUX — billed per megapixel

| Model            | Best for                    | Price                 |
| ---------------- | --------------------------- | --------------------- |
| `flux-1-schnell` | Fast, cheap generations     | \$0.002 per megapixel |
| `flux-pro-1.1`   | Higher-fidelity generations | \$0.04 per megapixel  |

FLUX models accept any `WIDTHxHEIGHT` size with each side 256–2560 px and an area up to 4 megapixels, billed as `ceil(width × height / 2²⁰)` megapixels — a `1024x1024` image is 1 MP; `1600x1024` rounds up to 2 MP.

### GPT Image — billed per image (quality × size)

**`gpt-image-2`**

| Quality | 1024×1024 | 1024×1536 | 1536×1024 |
| ------- | --------- | --------- | --------- |
| low     | \$0.005   | \$0.004   | \$0.004   |
| medium  | \$0.043   | \$0.031   | \$0.031   |
| high    | \$0.151   | \$0.125   | \$0.125   |

**`gpt-image-1.5`**

| Quality | 1024×1024 | 1024×1536 | 1536×1024 |
| ------- | --------- | --------- | --------- |
| low     | \$0.008   | \$0.009   | \$0.009   |
| medium  | \$0.024   | \$0.040   | \$0.040   |
| high    | \$0.113   | \$0.100   | \$0.100   |

Omitted `size` and `quality` default to `1024x1024` and `high`. Requesting `n` images multiplies the per-image price by `n` (up to 4). See [Image Generation](/api/image-generation) for the full parameter reference.

Both GPT Image models also serve [`POST /v1/images/edits`](/api/image-editing), sharing this same per-image (quality × size) grid: an edit costs exactly what a generation of the same quality, size, and n costs. FLUX models do not support editing.

> **Note**
>
> `GET /v1/models` is the authoritative live list, including current pricing. Prices on this page are current as of 2026-09-24. See [Models & Receipts](/api/models-receipts) for the endpoint reference.