# 7API > 7API is an LLM API gateway: one API key for 40 models from Anthropic (Claude), OpenAI (GPT), Google (Gemini), xAI (Grok), DeepSeek, Zhipu AI (GLM) and Moonshot AI (Kimi), including an uncensored AI API with abliterated GLM-5.3 and DeepSeek models. It exposes OpenAI-compatible (Chat Completions, Responses) and Anthropic-compatible (Messages) endpoints at https://7api.st, bills per token from a prepaid USD balance, and charges a separate, lower rate for cached input. Key facts: - OpenAI base URL: https://7api.st/v1 · Anthropic base URL: https://7api.st - Auth: `Authorization: Bearer sk-…` or `x-api-key: sk-…` - Live catalog with prices and limits: https://7api.st/v1/models (no key required) - Every public model works on all three request formats (except claude-sonnet-5-5: Messages only) - Payment: crypto, $5 minimum, balance never expires; sign up at https://7api.st/ (no email; dashboard at https://7api.st/dashboard) or https://t.me/hqclaudebot ## Uncensored and abliterated AI - [Uncensored AI API: abliterated GLM-5.3 and DeepSeek](https://7api.st/uncensored-ai-api.md): Uncensored AI API with abliterated and uncensored LLMs (GLM-5.3 Abliterated, GLM-5.3 Uncensored, DeepSeek V4.1 Flash 1017 Abliterated) on one OpenAI- and Anthropic-compatible key. 1M context, pay per token, no subscription. - [Abliterated AI: what abliteration is and how to use it](https://7api.st/abliterated-ai.md): Abliterated AI models have their refusal behavior removed at the weight level. How abliteration works, how it differs from uncensored fine-tunes, what it costs in capability, and how to call GLM-5.3 Abliterated through an API. - [DeepSeek V4.1 Flash 1017 Abliterated API](https://7api.st/models/deepseek-v4.1-flash-1017-abliterated.md): Abliterated DeepSeek V4.1 Flash 1017 API. DeepSeek V4.1 Flash 1017 Abliterated API (deepseek-v4.1-flash-1017-abliterated) on 7API: $0.15/M tokens, $0.05/M cached input, 1M context, 66K output. OpenAI- and Anthropic-compatible. - [DeepSeek V4.1 Flash 1017 Abliterated Fast API](https://7api.st/models/deepseek-v4.1-flash-1017-abliterated-fast.md): Abliterated DeepSeek V4.1 Flash 1017 API. DeepSeek V4.1 Flash 1017 Abliterated Fast API (deepseek-v4.1-flash-1017-abliterated-fast) on 7API: $0.70/M tokens, $0.16/M cached input, 1M context, 66K output. OpenAI- and Anthropic-compatible. - [GLM 5.3 Uncensored API](https://7api.st/models/glm-5.3-uncensored.md): Uncensored GLM 5.3 API. GLM 5.3 Uncensored API (glm-5.3-uncensored) on 7API: $0.05/M tokens, $0.01/M cached input, 1M context, 66K output. OpenAI- and Anthropic-compatible. - [GLM 5.3 Flash Uncensored API](https://7api.st/models/glm-5.3-flash-uncensored.md): Uncensored GLM 5.3 Flash API. GLM 5.3 Flash Uncensored API (glm-5.3-flash-uncensored) on 7API: $0.025/M tokens, $0.0025/M cached input, 1M context, 66K output. OpenAI- and Anthropic-compatible. - [GLM 5.3 Abliterated API](https://7api.st/models/glm-5.3-abliterated.md): Abliterated GLM 5.3 API. GLM 5.3 Abliterated API (glm-5.3-abliterated) on 7API: $0.80/M tokens, $0.25/M cached input, 1M context, 130K output. OpenAI- and Anthropic-compatible. ## Docs - [Balance, usage, status and invoices](https://7api.st/docs/account-endpoints.md): Check your 7API balance, usage and model health, or create a Heleket top-up invoice using your API key. - [Account and key security](https://7api.st/docs/account-security.md): How 7API accounts work. The API key is the login with no email or password, so this page covers how to store it safely, rotate a leaked key and use subkeys to limit exposure. - [Anthropic-compatible API](https://7api.st/docs/anthropic-compatible-api.md): 7API's Anthropic Messages API at https://7api.st/v1/messages. Works with the Anthropic SDK and Claude Code, supports streaming, tools, extended thinking, prompt caching and token counting for every model. - [Authentication](https://7api.st/docs/authentication.md): Authenticate to the 7API API with an Authorization Bearer header or an x-api-key header. Key format, error responses, key rotation and subkeys. - [Errors](https://7api.st/docs/errors.md): Every HTTP status the 7API API returns (400, 401, 402, 403, 404, 413, 415, 429, 5xx), what each means and whether to retry, with the JSON error shapes for OpenAI and Anthropic clients. - [7API documentation](https://7api.st/docs/index.md): 7API documentation. One API key for Claude, GPT, Gemini, Grok, DeepSeek, GLM and Kimi through OpenAI- and Anthropic-compatible endpoints at https://7api.st. - [Model IDs and aliases](https://7api.st/docs/model-ids.md): The exact model strings 7API accepts, including vendor-prefixed spellings, the claude- prefix for Claude-only clients, dotted vs dashed versions and the [1m] context suffix. - [List models (GET /v1/models)](https://7api.st/docs/models-endpoint.md): GET https://7api.st/v1/models returns every available model with context window, output limit, vision and reasoning capabilities, and per-token pricing. No key required. - [OpenAI-compatible API](https://7api.st/docs/openai-compatible-api.md): 7API's OpenAI-compatible Chat Completions and Responses endpoints. Base URL https://7api.st/v1, supported parameters, tool calling, vision, structured output and SDK examples. - [Pricing and billing](https://7api.st/docs/pricing-and-billing.md): How 7API billing works. Prepaid USD balance, pay-per-token rates per model, discounted cached input, crypto top-ups from $5 with bonus credit up to 16%, and what happens to failed requests. - [Prompt caching](https://7api.st/docs/prompt-caching.md): How 7API bills cached input tokens at a separate, much lower rate, how cache hits are reported in OpenAI and Anthropic usage fields, and how to get high cache-hit rates with coding agents. - [Quickstart](https://7api.st/docs/quickstart.md): Get a 7API key and connect Claude Code, OpenCode, Codex CLI, Cline, Roo Code, Oh My Pi or CommandCode in a few minutes. Raw API examples for curl, the OpenAI SDK and the Anthropic SDK at the end. - [Rate limits and request size](https://7api.st/docs/rate-limits.md): 7API main-key and subkey rate limits, including separate shared subkey limits of 600 requests per minute and 128 concurrent requests, metadata endpoint limits and request size limits. - [Reasoning effort](https://7api.st/docs/reasoning-effort.md): Control how long 7API models think. reasoning_effort, reasoning.effort, output_config.effort and thinking, plus the effort levels accepted by Claude, GPT, GLM, DeepSeek and Kimi models. - [Streaming](https://7api.st/docs/streaming.md): Stream tokens from 7API with server-sent events on Chat Completions, Responses and Anthropic Messages. Usage in the final chunk, keep-alive comments and mid-stream error events. - [Subkeys](https://7api.st/docs/subkeys.md): Create separately funded 7API API keys for teammates or customers. Move balance in and out, track spend per key and revoke instantly with the /v1/subkeys API. ## Integration guides - [Use Claude Code with 7API](https://7api.st/docs/guides/claude-code.md): Configure Claude Code to use 7API. Set ANTHROPIC_BASE_URL to https://7api.st in settings.json, then switch between Claude, GPT, GLM, DeepSeek, Kimi and Grok models with /model. - [Use Codex CLI with 7API](https://7api.st/docs/guides/codex.md): Configure OpenAI Codex CLI to use 7API through the Responses API. A config.toml for GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna with 1.05M-token context and auto-compaction. - [Use CommandCode with 7API](https://7api.st/docs/guides/commandcode.md): Connect CommandCode to 7API with /connect and BYOK. Models are discovered automatically from https://7api.st/v1. - [Cursor setup no longer works](https://7api.st/docs/guides/cursor.md): Cursor has patched cursor-byok, and this setup no longer works. Use another harness, such as OpenCode, Oh My Pi (OMP), or another compatible client. Previous steps are kept only for historical reference. - [Use Oh My Pi (OMP) with 7API](https://7api.st/docs/guides/oh-my-pi.md): A models.yml for Oh My Pi with every 7API model, its context limits, the right request format per model and its reasoning-effort scale. - [Use OpenCode with 7API](https://7api.st/docs/guides/opencode.md): A ready-made opencode.json for 7API with every model, its context window, output limit and reasoning-effort variants. Works with GPT, Claude, GLM, DeepSeek, Kimi and Grok. - [Use Cline, Roo Code and Continue with 7API](https://7api.st/docs/guides/vscode.md): Connect VS Code AI extensions (Cline, Roo Code, Continue) to 7API. Use the Anthropic provider for Claude models and the OpenAI-compatible provider for GPT, GLM, DeepSeek, Kimi and Grok. ## Models - [Models and pricing](https://7api.st/pricing.md): All models with limits and prices - [Claude API — Opus 5.5, Sonnet 5.5 and Haiku 5.5](https://7api.st/models/claude.md): Use Anthropic Claude models (Opus 5.5, Opus 5, Sonnet 5.5, Haiku 5.5) through one pay-per-token API key. Works with Claude Code and the Anthropic SDK. - [GPT-6 API — Astra, Sol and Luna](https://7api.st/models/gpt.md): Use OpenAI GPT-6.2 Astra, GPT-6 Astra, GPT-6.2 Sol, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna and GPT-5.6 through one pay-per-token API key with the Responses or Chat Completions API. Works with Codex CLI. - [GLM-5.3 API — standard, Flash, Uncensored and Abliterated](https://7api.st/models/glm.md): GLM-5.3 and GLM-5.3 Flash API with 1M-token context, including uncensored and abliterated variants. OpenAI- and Anthropic-compatible, pay per token, cached input from $0.0025/M. - [DeepSeek V4.1 and V4 Pro API](https://7api.st/models/deepseek.md): DeepSeek V4.1 Flash, V4.1 Flash 1017 (vision), V4 Pro and uncensored and abliterated variants through one OpenAI- and Anthropic-compatible API. 1M-token context, from $0.02/M tokens. - [Kimi K3 and K3.1 Pro API](https://7api.st/models/kimi.md): Moonshot AI Kimi K3 and Kimi K3.1 Pro (vision) API with 1M-token context and low/high/max reasoning. OpenAI- and Anthropic-compatible, pay per token. - [Grok 4.7 API](https://7api.st/models/grok.md): xAI Grok 4.7, 4.6 and 4.5 through one OpenAI- and Anthropic-compatible API key. Up to 500K-token context, pay per token. - [Gemini 4 Carbon and Argon API](https://7api.st/models/gemini.md): Google Gemini 4 Carbon and Argon through an OpenAI- and Anthropic-compatible API with image input. Pay per token with one 7API key. ## Data - [LLM benchmarks](https://7api.st/benchmarks.md): Independent LLM benchmarks for 14 models on 7API: Artificial Analysis Intelligence Index scores, by effort level, next to per-token prices for Claude, GPT, Gemini, Kimi, GLM, DeepSeek and Grok. ## Optional - [Gemini 4 Carbon](https://7api.st/models/gemini-4-carbon.md): `gemini-4-carbon`, $0.50/M, cached $0.05/M, 1.05M context - [Gemini 4 Argon](https://7api.st/models/gemini-4-argon.md): `gemini-4-argon`, $0.30/M, cached $0.05/M, 128K context - [GPT-6 Astra](https://7api.st/models/gpt-6-astra.md): `gpt-6-astra`, $0.65/M, cached $0.06/M, 1.05M context - [GPT-6.2 Astra](https://7api.st/models/gpt-6.2-astra.md): `gpt-6.2-astra`, $0.65/M, cached $0.06/M, 1.05M context - [GPT-6.1 Sol](https://7api.st/models/gpt-6.1-sol.md): `gpt-6.1-sol`, $0.15/M, cached $0.04/M, 1.05M context - [GPT-6.2 Sol](https://7api.st/models/gpt-6.2-sol.md): `gpt-6.2-sol`, $0.15/M, cached $0.04/M, 1.05M context - [GPT-6 Sol](https://7api.st/models/gpt-6-sol.md): `gpt-6-sol`, $0.15/M, cached $0.04/M, 1.05M context - [GPT-6 Luna](https://7api.st/models/gpt-6-luna.md): `gpt-6-luna`, $0.05/M, cached $0.01/M, 1.05M context - [GPT-5.6 Sol](https://7api.st/models/gpt-5.6-sol.md): `gpt-5.6-sol`, $0.45/M, cached $0.04/M, 1M context - [GPT-5.6 Terra](https://7api.st/models/gpt-5.6-terra.md): `gpt-5.6-terra`, $0.45/M, cached $0.04/M, 1M context - [GPT-5.6 Luna](https://7api.st/models/gpt-5.6-luna.md): `gpt-5.6-luna`, $0.45/M, cached $0.04/M, 1M context - [GPT-5.5](https://7api.st/models/gpt-5.5.md): `gpt-5.5`, $0.45/M, cached $0.04/M, 1M context - [Claude Fable 5.2](https://7api.st/models/claude-fable-5-2.md): `claude-fable-5-2`, $0.80/M, cached $0.08/M, 1M context - [Claude Opus 5.5 Max](https://7api.st/models/claude-opus-5-5-max.md): `claude-opus-5-5-max`, $0.70/M, cached $0.07/M, 1M context - [Claude Opus 5.5](https://7api.st/models/claude-opus-5-5.md): `claude-opus-5-5`, $0.70/M, cached $0.07/M, 1M context - [Claude Opus 5](https://7api.st/models/claude-opus-5.md): `claude-opus-5`, $0.50/M, cached $0.05/M, 1M context - [Claude Opus 4.8](https://7api.st/models/claude-opus-4-8.md): `claude-opus-4-8`, $0.50/M, cached $0.05/M, 1M context - [Claude Opus 4.7](https://7api.st/models/claude-opus-4-7.md): `claude-opus-4-7`, $0.50/M, cached $0.05/M, 1M context - [Claude Opus 4.6](https://7api.st/models/claude-opus-4-6.md): `claude-opus-4-6`, $0.50/M, cached $0.05/M, 1M context - [Claude Sonnet 5.5](https://7api.st/models/claude-sonnet-5-5.md): `claude-sonnet-5-5`, $0.50/M, cached $0.06/M, 1M context - [Claude Sonnet 5](https://7api.st/models/claude-sonnet-5.md): `claude-sonnet-5`, $0.50/M, cached $0.05/M, 1M context - [Claude Haiku 5.5](https://7api.st/models/claude-haiku-5-5.md): `claude-haiku-5-5`, $0.03/M, cached $0.01/M, 1M context - [Grok 4.7](https://7api.st/models/grok-4.7.md): `grok-4.7`, $0.10/M, cached $0.02/M, 500K context - [Grok 4.6](https://7api.st/models/grok-4.6.md): `grok-4.6`, $0.10/M, cached $0.02/M, 500K context - [Grok 4.5](https://7api.st/models/grok-4.5.md): `grok-4.5`, $0.10/M, cached $0.02/M, 200K context - [DeepSeek V4.1 Flash](https://7api.st/models/deepseek-v4.1-flash.md): `deepseek-v4.1-flash`, $0.02/M, cached $0.005/M, 1M context - [DeepSeek V4.1 Flash 1017](https://7api.st/models/deepseek-v4.1-flash-1017.md): `deepseek-v4.1-flash-1017`, $0.02/M, cached $0.005/M, 1M context - [DeepSeek V4.1 Flash 1017 HQ](https://7api.st/models/deepseek-v4.1-flash-1017-hq.md): `deepseek-v4.1-flash-1017-hq`, $0.05/M, cached $0.01/M, 1M context - [DeepSeek V4 Flash](https://7api.st/models/deepseek-v4-flash-0731.md): `deepseek-v4-flash-0731`, $0.03/M, cached $0.0027/M, 1M context - [DeepSeek V4 Pro](https://7api.st/models/deepseek-v4-pro-0813.md): `deepseek-v4-pro-0813`, $0.25/M, cached $0.05/M, 1M context - [GLM 5.2](https://7api.st/models/glm-5.2.md): `glm-5.2`, $0.06/M, cached $0.017/M, 1M context - [GLM 5.3](https://7api.st/models/glm-5.3.md): `glm-5.3`, $0.05/M, cached $0.01/M, 1M context - [GLM 5.3 Flash](https://7api.st/models/glm-5.3-flash.md): `glm-5.3-flash`, $0.025/M, cached $0.0025/M, 1M context - [Kimi K3](https://7api.st/models/kimi-k3.md): `kimi-k3`, $0.15/M, cached $0.03/M, 1M context - [Kimi K3.1 Pro](https://7api.st/models/kimi-k3.1-pro.md): `kimi-k3.1-pro`, $0.30/M, cached $0.05/M, 1M context