DeepSeek V4.1 Pro API
by DeepSeek
DeepSeek has not released V4.1 Pro, and there is no date or API price for it yet. DeepSeek V4.1 Flash is callable here today, billed per million tokens with no subscription. V4.1 Pro will be listed on this page with its real rate once it can actually be called.
DeepSeek V4.1 Pro is launching on you.bot soon — one API, one credit balance, pay only for successful calls. Create a free account to get your API key ready and be first to use it when it goes live.
More text models API
Models with similar capabilities you can switch to.
GPT-5.6 Terra
by OpenAI
GPT-5.6 — frontier reasoning and generation through one API.
GPT-5.6 Sol
by OpenAI
GPT-5.6 — frontier reasoning and generation through one API.
Claude Fable 5
by Anthropic
Claude Fable 5 — frontier reasoning and generation through one API.
Claude Sonnet 5
by Anthropic
Claude Sonnet 5 — frontier reasoning and generation through one API.
Kimi K3
by Moonshot AI
Frontier coding, native vision, and 1M-token agents from Moonshot AI.
Claude Fable 5.1
by Anthropic
Anthropic's Claude Fable 5.1 — for demanding reasoning and long-horizon agentic work, with stronger long-running agentic coding, multistep research, and document, spreadsheet and slide work across a 1M-token context.
Claude Opus 5.5
by Anthropic
Anthropic's Claude Opus 5.5 — frontier reasoning for complex coding, research and agentic work, served through one API.
Claude Sonnet 5.5
by Anthropic
Anthropic's Claude Sonnet 5.5 — the balanced Claude for everyday coding, writing and analysis, served through one API.
Claude Haiku 5.5
by Anthropic
Anthropic's Claude Haiku 5.5 — the fastest, lowest-cost Claude for high-volume chat, coding and everyday tasks, served through one API.
Gemini 3.6 Flash
by Google
Google's newest speed-optimized multimodal model — fast text, vision, and reasoning.
Gemini 3.7 Flash
by Google
Google's newest Flash model — a 1M-token context window and up to 65,536 tokens of output, at the same price as 3.6.
Gemini 3.8 Flash
by Google
Google's newest Flash model — a 1M-token context window and up to 65,536 tokens of output, at the same price as 3.7.
Grok 4.7
by Grok
xAI's Grok 4.7 — their frontier model for coding, agentic tasks and knowledge work, with a 500K-token context window.
DeepSeek V4.1 Flash
by DeepSeek
DeepSeek's fast V4.1 model — thinking on by default with a non-thinking mode, a 1M-token context and up to 384K tokens of output, with JSON output, tool calls and image input.
GPT-6 Astra
by OpenAI
OpenAI's GPT-6 Astra — frontier reasoning with a 1M-token context window, served through one API.
GPT-6 Sol
by OpenAI
OpenAI's GPT-6 Sol — the everyday GPT-6: strong reasoning at a fraction of Astra's price, served through one API.
GPT-6 Luna
by OpenAI
OpenAI's GPT-6 Luna — the lightest GPT-6: fast, low-cost answers for high-volume work, served through one API.
GPT-6.1 Sol
by OpenAI
OpenAI's GPT-6.1 Sol — the updated everyday GPT-6: strong reasoning at a low price, served through one API.
Claude Opus 5
by Anthropic
Claude Opus 5 — frontier reasoning and generation through one API.
Claude Opus 4.8
by Anthropic
Claude Opus 4.8 — frontier reasoning and generation through one API.
GPT-5.5
by OpenAI
GPT-5.5 — frontier reasoning and generation through one API.
Claude Haiku 4.5
by Anthropic
Claude Haiku 4.5 — frontier reasoning and generation through one API.
Gemini 3.1 Pro
by Google
Gemini 3.1 Pro — frontier reasoning and generation through one API.
Grok 4.6
by Grok
Grok 4.6 — frontier reasoning and generation through one API.
Grok 4.5
by Grok
Grok 4.5 — frontier reasoning and generation through one API.