# Aight > One key to AI that always gives back a little more. > Many models. One API. 10% extra on every recharge. > Aight is a product of Ashva Intelligence Pvt Ltd · CIN U62099HR2026PTC147038 · GSTIN 06ABFCA9973K1Z2 - API: OpenAI-compatible, base URL https://api.getaight.ai/v1 - Models: 139 models (113 text, 10 image, 1 video, 12 speech, 3 embeddings) from Alibaba, Amazon, Anthropic, AWS Bedrock, Azure, Black Forest Labs, Cohere, DeepSeek, Google, Meta, MiniMax, Mistral AI, Moonshot AI, OpenAI, Vertex AI, xAI - Prices: provider list prices, in US$. Balance in US$. - Extra: 10% of every recharge, added to balance. Extra is not refunded. - Recharge: India accounts in ₹ (minimum ₹500, plus GST 18%); accounts outside India in US$ (minimum US$5, plus Processing 3%). - Some models run in India. Higher limits. - API keys open as soon as the email is verified. ## Pages - [Models & pricing](https://getaight.ai/models/): every model with capability, provider, region and price - [Token cost calculator](https://getaight.ai/token-calculator/): monthly cost of a job on every text and embedding model - [Quickstart](https://getaight.ai/docs/): first request in Python and cURL - [API reference](https://getaight.ai/docs/reference/): endpoints, authentication, error codes - [Blog](https://getaight.ai/blog/): AI API errors, model shutdowns and price changes - [Terms](https://getaight.ai/legal/terms.html) · [Refunds](https://getaight.ai/legal/refunds.html) · [Privacy](https://getaight.ai/legal/privacy.html) - [Support](https://getaight.ai/support/): hello@getaight.ai ## Blog - [Best speech to text API (Nov 2026): WER, price, latency](https://getaight.ai/blog/best-speech-to-text-api/): The best speech to text API in November 2026, ranked by benchmark word error rate, price per hour, latency and speaker labels, plus open-weight models. - [Claude Code process exited with code 1: causes and fixes](https://getaight.ai/blog/claude-code-process-exited-with-code-1/): Claude Code process exited with code 1 hides the real error. Find it in VS Code, Desktop, the Agent SDK or the CLI, then match it to a fix for each cause. - [OpenAI Assistants API shutdown: migrate to Responses](https://getaight.ai/blog/openai-assistants-api/): The OpenAI Assistants API shut down on 26 August 2026. What replaced it, a migration guide with Python code, what breaks, and why calls now return 404. - [What is an API key? Meaning, examples and safe use](https://getaight.ai/blog/what-is-an-api-key/): What an API key is, what real keys look like (fake examples), how they're generated, why online generators are a trap, and how to store and rotate AI keys. - [Claude Code dangerously-skip-permissions: risks, safe setup](https://getaight.ai/blog/claude-code-dangerously-skip-permissions/): What Claude Code --dangerously-skip-permissions skips in 2.1.322, what still stops it, auto mode, sandbox and container setups, and the incidents behind it. - [Claude Code MCP servers: setup, token cost and security](https://getaight.ai/blog/claude-code-mcp-servers/): Claude Code MCP servers in 2.1.322: the add, list, scope and remove commands, measured token cost for GitHub, Playwright and Context7, security and fixes. - [Claude vs Claude Code: what each does and which to use](https://getaight.ai/blog/claude-vs-claude-code/): Claude vs Claude Code in November 2026: the chat app vs the coding agent, where each runs, how one plan's shared limits cover both, and which to open when. - [Ollama Claude Code: setup, local models, OpenCode and cost](https://getaight.ai/blog/ollama-claude-code/): Ollama Claude Code setup on Ollama 0.40.16: ollama launch, the context window fix, OpenCode with Ollama, which local models work, and when a GPU pays off. - [Claude Code agent teams: setup, cost and when to use them](https://getaight.ai/blog/claude-code-agent-teams/): Claude Code agent teams in 2.1.322: how they differ from subagents, how to enable the experimental flag, a worked cost example, and when a team is worth it. - [Claude Code hooks: all 33 events and 5 working examples](https://getaight.ai/blog/claude-code-hooks/): Claude Code hooks in 2.1.322: all 33 events with their inputs and outputs, five tested scripts (format, block, notify, log, test gate), security, debugging. - [Claude Code memory: CLAUDE.md, rules, auto memory, templates](https://getaight.ai/blog/claude-code-memory/): Claude Code memory in 2.1.322: CLAUDE.md levels, @imports, .claude/rules, auto memory and MEMORY.md, copy-ready templates, and what each costs in tokens. - [Claude Code Remote Control: setup, plans and security](https://getaight.ai/blog/claude-code-remote-control/): How Claude Code Remote Control works: plans that include it, setup in terminal, VS Code, Desktop and phone, what Anthropic stores, and SSH or cloud options. - [Claude Cowork vs Claude Code vs chat: which to use](https://getaight.ai/blog/claude-cowork-vs-claude-code/): Claude Cowork vs Claude Code vs chat in November 2026: what each one does, where it runs, what it can reach on your computer, plans, shared limits and fit. - [Grok vs Gemini (2026): plans, benchmarks and API prices](https://getaight.ai/blog/grok-vs-gemini/): Grok vs Gemini compared: The X Subscription against Google AI plans, Grok 4.7 against Gemini 4 Argon on benchmarks, and what each API costs per month. - [Groq vs Grok: what each is, what it costs, who owns the name](https://getaight.ai/blog/groq-vs-grok/): Groq vs Grok: Groq runs open models fast on LPU chips, Grok is the SpaceX (ex-xAI) model and app. Prices, whether Grok runs on Groq, and the name dispute. - [Perplexity vs Claude: plans, models and API prices (2026)](https://getaight.ai/blog/perplexity-vs-claude/): Perplexity vs Claude: when a cited search engine beats a general assistant, what each plan costs, which Claude models Perplexity uses, and the API prices. - [Claude vs ChatGPT vs Gemini: plans, strengths, API prices](https://getaight.ai/blog/claude-vs-chatgpt-vs-gemini/): Claude vs ChatGPT vs Gemini compared in one table: $20 plans, top models, context windows, benchmark results and API prices, with a pick for each job. - [Claude vs ChatGPT (2026): plans, coding, writing, research](https://getaight.ai/blog/claude-vs-chatgpt/): Claude vs ChatGPT compared: Free to $500 plans side by side, coding benchmarks dated November 2026, writing, research, images, and API prices for builders. - [Gemini vs ChatGPT (2026): plans, benchmarks and prices](https://getaight.ai/blog/gemini-vs-chatgpt/): Gemini vs ChatGPT by use case: Google AI plans against ChatGPT plans, Gemini 4 Argon vs GPT-6 benchmarks, context windows, integrations and API prices. - [Grok vs ChatGPT (2026): models, plans, benchmarks, API](https://getaight.ai/blog/grok-vs-chatgpt/): Grok vs ChatGPT in November 2026: Grok 4.7 vs GPT-6, live X search, images and video, $0 to $500 plans, independent benchmarks and API prices per 1M tokens. - [Best embedding models (Nov 2026): MTEB scores and prices](https://getaight.ai/blog/best-embedding-models/): The best embedding models in November 2026, with MTEB and RTEB leaderboard ranks, price per 1M tokens, dimensions and max input, plus a test on your data. - [Best LLM API in 2026: 6 providers compared after the demo](https://getaight.ai/blog/best-llm-api/): The best LLM API for your team: OpenAI, Anthropic, Gemini, xAI, DeepSeek and Mistral compared on price, rate limits, billing, data retention and SDKs. - [OpenAI token pricing: every GPT model's price per token](https://getaight.ai/blog/openai-token-pricing/): OpenAI token pricing for every GPT model: input, cached, output, Batch, Flex and Fast rates per 1M tokens, cost per token, tiktoken code and reasoning tokens. - [Zero data retention (ZDR) for LLM APIs: who keeps what](https://getaight.ai/blog/zero-data-retention-llm-api/): Zero data retention (ZDR) for OpenAI, Anthropic, Gemini, Azure and Bedrock: default retention per provider, how to request ZDR, and what breaks under it. - [Claude Code alternatives: 10 coding agents compared](https://getaight.ai/blog/claude-code-alternatives/): Codex CLI, Antigravity CLI, OpenCode, Cline, Kilo Code, Cursor, Copilot, Aider, Amp and Replit compared with Claude Code on monthly cost and model choice. - [Gemini CLI vs Claude Code: free tier, limits and cost (2026)](https://getaight.ai/blog/gemini-cli-vs-claude-code/): Gemini CLI vs Claude Code after Google ended Gemini CLI's free tier: limits, features, benchmarks, Antigravity CLI, and monthly cost for the same work. - [How to get an OpenAI API key: setup, free tier, safety](https://getaight.ai/blog/how-to-get-openai-api-key/): How to get an OpenAI API key: sign-up, phone check, the $5 minimum, project and service account keys, finding a lost key, what's free, and storing it safely. - [Claude API status: is it down, and how to fail over](https://getaight.ai/blog/llm-api-outages/): Check Claude API status in 30 seconds, read 529, 503 and 500 errors, see 2026 outages and uptime for Claude, OpenAI, Gemini and DeepSeek, and fail over. - [OpenAI Whisper API pricing: per minute, hour and 1,000 hours](https://getaight.ai/blog/openai-transcription-api-pricing/): OpenAI Whisper API pricing per minute and hour for whisper-1, gpt-transcribe and live models, the 26 Feb 2027 shutdown, 1,000 hours vs Gemini and Deepgram. - [Claude Code cheat sheet: commands, shortcuts and flags](https://getaight.ai/blog/claude-code-cheat-sheet/): Claude Code cheat sheet for 2.1.326: every slash command, shortcut and CLI flag, CLAUDE.md, hooks, subagents and MCP, and the habits that cut token costs. - [Free LLM API: every free tier and its real limits (2026)](https://getaight.ai/blog/free-llm-api/): Every free LLM API tier checked on 5 Nov 2026: Gemini, Groq, Mistral, Cloudflare, OpenRouter and more, with real daily limits, training terms and catches. - [OpenClaw vs Claude Code: costs, models and security](https://getaight.ai/blog/openclaw-vs-claude-code/): OpenClaw vs Claude Code: a self-hosted assistant in your chat apps against Anthropic's coding agent. What each is, what it costs, which models, and the risks. - [OpenRouter free credits: free models, limits, promo codes](https://getaight.ai/blog/openrouter-free-credits/): What OpenRouter gives away in November 2026: 12 free text models, 50 or 1,000 requests a day, no public promo code, and what paid use costs after its fee. - [What is Cline? The free coding agent and its monthly cost](https://getaight.ai/blog/what-is-cline/): What is Cline: the free, open-source coding agent for VS Code, JetBrains and the terminal. How it works, monthly model costs, best models and Cline vs Cursor. - [API rate limit exceeded: what the 429 means, how to fix it](https://getaight.ai/blog/api-rate-limit-exceeded/): What API rate limit exceeded (HTTP 429) means on OpenAI, Claude, Gemini and DeepSeek, the November 2026 tier limits, and tested retry code for Retry-After. - [Gemini API pricing: every model, free tier and price dates](https://getaight.ai/blog/gemini-api-pricing/): Gemini API pricing for every model, free tier limits and catches, the 1 December and 1 January price rises, and monthly costs set against GPT and Claude. - [OpenAI API guide 2026: models, prices and first request](https://getaight.ai/blog/openai-api/): The OpenAI API explained: how it differs from ChatGPT, GPT-6 prices, a first request in Python and curl, tiers and billing, and switching via base_url. - [OpenCode vs Claude Code: features, models and cost (2026)](https://getaight.ai/blog/opencode-vs-claude-code/): OpenCode vs Claude Code: model choice, permissions and features, the new Claude subscription login in OpenCode 2.2, and one month of work priced both ways. - [OpenCode Zen: pricing, setup and privacy (Nov 2026)](https://getaight.ai/blog/opencode-zen/): OpenCode Zen is now Console pay-as-you-go: model prices, the 4.6% + $0.31 fee, setup in OpenCode 2.2.5, data terms, and when your own API key costs less. - [Best LLM for coding (Nov 2026): scores and prices by job](https://getaight.ai/blog/best-llm-for-coding/): The best LLM for coding in November 2026 for agentic work, code review, autocomplete and quick edits, with benchmark scores and price per 1M tokens. - [Claude Code API key: setup, costs and claude-code-router](https://getaight.ai/blog/claude-code-api-key/): Use Claude Code with an API key instead of a plan: setup, cost per session, Bedrock and Vertex AI, and claude-code-router for other models, with the risks. - [Claude Code vs GitHub Copilot: plans, limits and real cost](https://getaight.ai/blog/claude-code-vs-github-copilot/): Claude Code vs GitHub Copilot after Copilot's move to per-token billing: plans, Claude models in Copilot, agent workflows and the same month's cost on each. - [How to install Codex CLI on macOS, Linux and Windows](https://getaight.ai/blog/install-codex-cli/): Install Codex CLI on macOS, Linux or Windows with the script, npm or Homebrew, sign in with ChatGPT or an API key, set up config.toml and fix common errors. - [What is an AI gateway? BYOK, routing and fees explained](https://getaight.ai/blog/what-is-an-ai-gateway/): What an AI gateway does, how gateways charge (purchase fees, BYOK fees, plans), how LLM routers pick a model, and when going direct to a provider is better. - [Claude API key: get one, store it, fix 401 errors](https://getaight.ai/blog/claude-api-key/): Get a Claude API key in the Claude Console: account, payment, key types, workspaces, rate-limit tiers, Python and TypeScript code, and fixes for 401 errors. - [Codex vs Claude Code: benchmarks, limits and cost (2026)](https://getaight.ai/blog/codex-vs-claude-code/): Codex vs Claude Code in November 2026: Terminal-Bench and Artificial Analysis results, $20 to $500 plans, usage limits, sandboxing and monthly cost. - [Cursor vs Claude Code: workflow, models and monthly cost](https://getaight.ai/blog/cursor-vs-claude-code/): Cursor vs Claude Code after Cursor's October price change: editor or terminal agent, which models each offers, running both together, and monthly costs. - [How to install Claude Code: macOS, Linux, Windows, VS Code](https://getaight.ai/blog/install-claude-code/): How to install Claude Code 2.1.326 on macOS, Linux or Windows (native installer, Homebrew, WinGet, npm), then sign in, update, uninstall and fix errors. - [Alternatives to OpenAI API: cost per job and drop-in code](https://getaight.ai/blog/openai-api-alternatives/): Claude, Gemini, Grok, DeepSeek, Mistral, Kimi and open models on Groq, Together and Fireworks, compared on price per job, with drop-in OpenAI SDK code. - [Claude API pricing: every model, cache and Batch rates](https://getaight.ai/blog/claude-api-pricing/): Claude API pricing for every model: input, output, cache and Batch rates per 1M tokens, cost per token, long-context rules, tool fees and three worked bills. - [Claude Code pricing: plans, limits and API costs (Nov 2026)](https://getaight.ai/blog/claude-code-pricing/): Claude Code pricing for Free, Pro, Max, Ultra, Team and Enterprise, the usage limits, and worked monthly API bills for light, daily and heavy coding. - [Codex pricing (Nov 2026): plans, limits and API cost](https://getaight.ai/blog/codex-pricing/): Codex pricing, November 2026: every ChatGPT plan from Free to Pro 500, usage limits, GPT-6.1 Sol API rates, and what light, daily and heavy months cost. - [DeepSeek API pricing 2026: rates, US peak hours, costs](https://getaight.ai/blog/deepseek-api-pricing/): DeepSeek API pricing for V4.1 Flash and V4 Pro at peak and off-peak, in US time, with monthly costs against GPT-6 Luna, Gemini Flash and Claude Haiku. - [OpenRouter alternatives: 9 options compared (Nov 2026)](https://getaight.ai/blog/openrouter-alternatives/): OpenRouter alternatives compared: Requesty, Vercel, Cloudflare, Portkey, Straitly, LiteLLM, Eden AI, direct and Aight on fees, refunds and data terms. - [Claude alternatives for coding: cost per passing task](https://getaight.ai/blog/claude-alternatives-for-coding-cost-per-task/): GPT-6 Sol, Gemini 3.8 Flash, Kimi K3, DeepSeek and Grok against Claude, ranked by what a coding task that passes its tests costs, plus a Python router. - [The cheapest way to use the OpenAI API in 2026](https://getaight.ai/blog/cheapest-way-to-use-openai-api/): Current GPT-5.6, GPT-6 and GPT-6.1 prices, and what really cuts an OpenAI bill: a smaller model, prompt caching, Batch or Flex, with a worked monthly example. - [How much does an LLM API cost per month? 5 examples](https://getaight.ai/blog/llm-api-cost-per-month/): Monthly LLM API cost for a support chatbot, RAG search, coding agent, transcription and image app at October 2026 list prices, with the math and a calculator. - [gpt-4o and gpt-4.1 shut down 14 Jan 2027: migration plan](https://getaight.ai/blog/gpt-4o-gpt-4-1-shutdown-january-2027/): OpenAI shuts down gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini on 14 January 2027. What breaks on gpt-6-luna, what it costs, and a test plan to finish first. - [Gemini 2.5 'no longer available to new users': what to use](https://getaight.ai/blog/gemini-2-5-not-found-no-longer-available-new-users/): Gemini 2.5 Pro and Flash return 404 for new users, and Vertex AI retired them on 20 October. What the errors mean, what to switch to, and what breaks next. - [OpenAI model not found: replacements for every retired model](https://getaight.ai/blog/openai-model-not-found-october-2026-shutdowns/): OpenAI shut down o4-mini, gpt-4.1-nano, gpt-3.5-turbo, gpt-4, o1 and more on 23 October 2026. The replacement for each, what it costs, and the fix. - [DeepSeek V4 Pro vs V4.1 Flash: cost and US peak hours](https://getaight.ai/blog/deepseek-v4-pro-vs-v4-1-flash/): DeepSeek retired V4 Flash and now serves V4.1-Flash-1017. How it compares with V4 Pro, what each costs at peak and off-peak, and the peak windows in US time. - [Claude 'temperature is deprecated' 400 error: the fix](https://getaight.ai/blog/claude-temperature-deprecated-400-error/): Anthropic's API version 2026-10-21 rejects temperature, top_p and top_k with a 400. Which models and versions are affected, and the code changes to fix it. - [Claude API credits: buying them and fixing a failed payment](https://getaight.ai/blog/claude-api-credits-payment-failed/): How Claude API credits work in the Anthropic Console, the error you get at a zero balance, why card payments fail, how to fix them, and other ways to pay. - [OpenAI API key spending limit: how to cap one key](https://getaight.ai/blog/openai-api-key-spending-limit/): OpenAI caps spend per project or organization, never per API key. What each limit blocks, why spend runs past it, and how to give each key a hard cap. - [Cheapest AI API aggregator in 2026: cost per $1 of usage](https://getaight.ai/blog/cheapest-ai-api-aggregator/): Purchase fees, minimums, expiry and refunds compared for OpenRouter, Requesty, Vercel, Cloudflare, Eden AI and Aight, as the real cost of $1 of model usage. - [One API key for Claude, GPT, Gemini, DeepSeek and Grok](https://getaight.ai/blog/one-api-key-claude-gpt-gemini-deepseek-grok/): Call 126 models from 16 makers with one OpenAI-compatible key and one prepaid balance. Setup, prices by model, per-key caps and 10% extra on every recharge. Full model list: https://getaight.ai/llms-full.txt ## Models - nova-micro · Amazon · Text · region United States · input US$0.035 per 1M tokens; output US$0.14 per 1M tokens - gemma-3-4b · Google · Text · region United States · input US$0.04 per 1M tokens; output US$0.08 per 1M tokens - gpt-5-nano · OpenAI · Text · region Global · input US$0.05 per 1M tokens; output US$0.40 per 1M tokens - nemotron-nano-3-30b · AWS Bedrock · Text · region United States · input US$0.06 per 1M tokens; output US$0.24 per 1M tokens - nemotron-nano-9b-v2 · AWS Bedrock · Text · region United States · input US$0.06 per 1M tokens; output US$0.23 per 1M tokens - nova-lite · Amazon · Text · region United States · input US$0.06 per 1M tokens; output US$0.24 per 1M tokens - glm-4.7-flash · AWS Bedrock · Text · region United States · input US$0.07 per 1M tokens; output US$0.40 per 1M tokens - gpt-oss-20b · OpenAI · Text · region United States · input US$0.07 per 1M tokens; output US$0.30 per 1M tokens - gpt-oss-safeguard-20b · OpenAI · Text · region United States · input US$0.07 per 1M tokens; output US$0.20 per 1M tokens - gemma-3-12b · Google · Text · region United States · input US$0.09 per 1M tokens; output US$0.29 per 1M tokens - claude-haiku-5-5 · Anthropic · Text · region Not specified · input US$0.10 per 1M tokens (prompts up to 100K tokens); US$0.50 per 1M tokens (prompts above 100K tokens); output US$0.50 per 1M tokens (prompts up to 100K tokens); US$2.50 per 1M tokens (prompts above 100K tokens) - gpt-4.1-nano · OpenAI · Text · region Global · input US$0.10 per 1M tokens; output US$0.40 per 1M tokens - gpt-6-luna · OpenAI · Text · region Global · input US$0.10 per 1M tokens (prompts up to 272K tokens); US$0.20 per 1M tokens (prompts above 272K tokens); output US$0.50 per 1M tokens (prompts up to 272K tokens); US$0.75 per 1M tokens (prompts above 272K tokens) - ministral-3-3b · AWS Bedrock · Text · region United States · input US$0.10 per 1M tokens; output US$0.10 per 1M tokens - qwen3-next-80b-a3b · Alibaba · Text · region United States · input US$0.14 per 1M tokens; output US$1.20 per 1M tokens - gpt-oss-120b · OpenAI · Text · region Global · input US$0.15 per 1M tokens; output US$0.60 per 1M tokens - gpt-oss-120b-aws · OpenAI · Text · region United States · input US$0.15 per 1M tokens; output US$0.60 per 1M tokens - gpt-oss-safeguard-120b · OpenAI · Text · region United States · input US$0.15 per 1M tokens; output US$0.60 per 1M tokens - ministral-3-8b · AWS Bedrock · Text · region United States · input US$0.15 per 1M tokens; output US$0.15 per 1M tokens - nemotron-super-3-120b · AWS Bedrock · Text · region United States · input US$0.15 per 1M tokens; output US$0.65 per 1M tokens - qwen3-32b · Alibaba · Text · region United States · input US$0.15 per 1M tokens; output US$0.60 per 1M tokens - qwen3-coder-30b-a3b · Alibaba · Text · region United States · input US$0.15 per 1M tokens; output US$0.60 per 1M tokens - llama-4-scout-17b · Meta · Text · region United States · input US$0.17 per 1M tokens; output US$0.66 per 1M tokens - DeepSeek-V4-Flash · DeepSeek · Text · region Global · input US$0.19 per 1M tokens; output US$0.51 per 1M tokens - gpt-5.4-nano · OpenAI · Text · region Global · input US$0.20 per 1M tokens; output US$1.25 per 1M tokens - gpt-5.6-luna · OpenAI · Text · region Global · input US$0.20 per 1M tokens (prompts up to 272K tokens); US$0.40 per 1M tokens (prompts above 272K tokens); output US$1.20 per 1M tokens (prompts up to 272K tokens); US$1.80 per 1M tokens (prompts above 272K tokens) - grok-4-1-fast-non-reasoning · xAI · Text · region Global · input US$0.20 per 1M tokens; output US$0.50 per 1M tokens - grok-4-1-fast-reasoning · xAI · Text · region Global · input US$0.20 per 1M tokens; output US$0.50 per 1M tokens - grok-code-fast-1 · xAI · Text · region Global · input US$0.20 per 1M tokens; output US$1.50 per 1M tokens - ministral-3-14b · AWS Bedrock · Text · region United States · input US$0.20 per 1M tokens; output US$0.20 per 1M tokens - nemotron-nano-12b-v2 · AWS Bedrock · Text · region United States · input US$0.20 per 1M tokens; output US$0.60 per 1M tokens - llama-3.1-8b · Meta · Text · region United States · input US$0.22 per 1M tokens; output US$0.22 per 1M tokens - gemma-3-27b · Google · Text · region United States · input US$0.23 per 1M tokens; output US$0.38 per 1M tokens - llama-4-maverick-17b · Meta · Text · region United States · input US$0.24 per 1M tokens; output US$0.97 per 1M tokens - gemini-3.1-flash-lite · Google · Text · region Global · input US$0.25 per 1M tokens; output US$1.50 per 1M tokens - gpt-5-mini · OpenAI · Text · region Global · input US$0.25 per 1M tokens; output US$2.00 per 1M tokens - gpt-5.1-codex-mini · OpenAI · Text · region Global · input US$0.25 per 1M tokens; output US$2.00 per 1M tokens - Llama-4-Maverick-17B-128E-Instruct-FP8 · Meta · Text · region Global · input US$0.25 per 1M tokens; output US$1.00 per 1M tokens - DeepSeek-V4.1-Flash · DeepSeek · Text · region Global · input US$0.30 per 1M tokens; output US$1.20 per 1M tokens - gemini-2.5-flash · Google · Text · region Global · input US$0.30 per 1M tokens; output US$2.50 per 1M tokens - gemini-3.5-flash-lite · Google · Text · region Global · input US$0.30 per 1M tokens; output US$2.50 per 1M tokens - minimax-m2 · MiniMax · Text · region United States · input US$0.30 per 1M tokens; output US$1.20 per 1M tokens - minimax-m2.1 · MiniMax · Text · region United States · input US$0.30 per 1M tokens; output US$1.20 per 1M tokens - minimax-m2.5 · MiniMax · Text · region United States · input US$0.30 per 1M tokens; output US$1.20 per 1M tokens - nova-2-lite · Amazon · Text · region United States · input US$0.33 per 1M tokens; output US$2.75 per 1M tokens - devstral-2-123b · AWS Bedrock · Text · region United States · input US$0.40 per 1M tokens; output US$2.00 per 1M tokens - gpt-4.1-mini · OpenAI · Text · region Global · input US$0.40 per 1M tokens; output US$1.60 per 1M tokens - magistral-small-2509 · AWS Bedrock · Text · region United States · input US$0.50 per 1M tokens; output US$1.50 per 1M tokens - Mistral-Large-3 · Mistral AI · Text · region Global · input US$0.50 per 1M tokens; output US$1.50 per 1M tokens - mistral-large-3-aws · Mistral AI · Text · region United States · input US$0.50 per 1M tokens; output US$1.50 per 1M tokens - qwen3-coder-next · Alibaba · Text · region United States · input US$0.50 per 1M tokens; output US$1.20 per 1M tokens - qwen3-vl-235b-a22b · Alibaba · Text · region United States · input US$0.53 per 1M tokens; output US$2.66 per 1M tokens - DeepSeek-V3.2 · DeepSeek · Text · region Global · input US$0.58 per 1M tokens; output US$1.68 per 1M tokens - DeepSeek-V3.2-Speciale · DeepSeek · Text · region Global · input US$0.58 per 1M tokens; output US$1.68 per 1M tokens - glm-4.7 · AWS Bedrock · Text · region United States · input US$0.60 per 1M tokens; output US$2.20 per 1M tokens - kimi-k2-thinking · Moonshot AI · Text · region United States · input US$0.60 per 1M tokens; output US$2.50 per 1M tokens - Kimi-K2.5 · Moonshot AI · Text · region Global · input US$0.60 per 1M tokens; output US$3.00 per 1M tokens - kimi-k2.5-aws · Moonshot AI · Text · region United States · input US$0.60 per 1M tokens; output US$3.00 per 1M tokens - deepseek-v3.2-aws · DeepSeek · Text · region United States · input US$0.62 per 1M tokens; output US$1.85 per 1M tokens - Llama-3.3-70B-Instruct · Meta · Text · region Global · input US$0.71 per 1M tokens; output US$0.71 per 1M tokens - llama-3.1-70b · Meta · Text · region United States · input US$0.72 per 1M tokens; output US$0.72 per 1M tokens - llama-3.3-70b · Meta · Text · region United States · input US$0.72 per 1M tokens; output US$0.72 per 1M tokens - nova-pro · Amazon · Text · region United States · input US$0.80 per 1M tokens; output US$3.20 per 1M tokens - gpt-5.4-mini · OpenAI · Text · region India · input US$0.90 per 1M tokens; output US$5.40 per 1M tokens - Kimi-K2.6 · Moonshot AI · Text · region Global · input US$0.95 per 1M tokens; output US$4.00 per 1M tokens - Kimi-K2.7-Code · Moonshot AI · Text · region Global · input US$0.95 per 1M tokens; output US$4.00 per 1M tokens - claude-haiku-4-5 · Anthropic · Text · region Not specified · input US$1.00 per 1M tokens; output US$5.00 per 1M tokens - glm-5 · AWS Bedrock · Text · region United States · input US$1.00 per 1M tokens; output US$3.20 per 1M tokens - gpt-6.1-terra · OpenAI · Text · region Global · input US$1.00 per 1M tokens (prompts up to 272K tokens); US$2.00 per 1M tokens (prompts above 272K tokens); output US$5.00 per 1M tokens (prompts up to 272K tokens); US$7.50 per 1M tokens (prompts above 272K tokens) - gemini-2.5-pro · Google · Text · region Global · input US$1.25 per 1M tokens (prompts up to 200K tokens); US$2.50 per 1M tokens (prompts above 200K tokens); output US$10.00 per 1M tokens (prompts up to 200K tokens); US$15.00 per 1M tokens (prompts above 200K tokens) - gpt-5 · OpenAI · Text · region Global · input US$1.25 per 1M tokens; output US$10.00 per 1M tokens - gpt-5-codex · OpenAI · Text · region Global · input US$1.25 per 1M tokens; output US$10.00 per 1M tokens - gpt-5.1 · OpenAI · Text · region Global · input US$1.25 per 1M tokens; output US$10.00 per 1M tokens - gpt-5.1-codex · OpenAI · Text · region Global · input US$1.25 per 1M tokens; output US$10.00 per 1M tokens - gpt-5.1-codex-max · OpenAI · Text · region Global · input US$1.25 per 1M tokens; output US$10.00 per 1M tokens - grok-4.3 · xAI · Text · region Global · input US$1.25 per 1M tokens (prompts up to 128K tokens); US$2.50 per 1M tokens (prompts above 128K tokens); output US$2.50 per 1M tokens (prompts up to 128K tokens); US$5.00 per 1M tokens (prompts above 128K tokens) - deepseek-r1 · DeepSeek · Text · region United States · input US$1.35 per 1M tokens; output US$5.40 per 1M tokens - gemini-3.5-flash · Google · Text · region Global · input US$1.50 per 1M tokens; output US$9.00 per 1M tokens - gemini-3.6-flash · Google · Text · region Global · input US$1.50 per 1M tokens; output US$7.50 per 1M tokens - gemini-3.7-flash · Google · Text · region Global · input US$1.50 per 1M tokens; output US$7.50 per 1M tokens - gemini-3.8-flash · Google · Text · region Global · input US$1.50 per 1M tokens; output US$7.50 per 1M tokens - mistral-medium-3-5 · Mistral AI · Text · region Global · input US$1.50 per 1M tokens; output US$7.50 per 1M tokens - DeepSeek-V4-Pro · DeepSeek · Text · region Global · input US$1.74 per 1M tokens; output US$3.48 per 1M tokens - gpt-5.2 · OpenAI · Text · region Global · input US$1.75 per 1M tokens; output US$14.00 per 1M tokens - gpt-5.2-codex · OpenAI · Text · region Global · input US$1.75 per 1M tokens; output US$14.00 per 1M tokens - gpt-5.3-codex · OpenAI · Text · region Global · input US$1.75 per 1M tokens; output US$14.00 per 1M tokens - claude-sonnet-5 · Anthropic · Text · region Not specified · input US$2.00 per 1M tokens; output US$10.00 per 1M tokens - claude-sonnet-5-5 · Anthropic · Text · region Not specified · input US$2.00 per 1M tokens; output US$10.00 per 1M tokens - gemini-3.1-pro-preview · Google · Text · region Global · input US$2.00 per 1M tokens (prompts up to 200K tokens); US$4.00 per 1M tokens (prompts above 200K tokens); output US$12.00 per 1M tokens (prompts up to 200K tokens); US$18.00 per 1M tokens (prompts above 200K tokens) - gpt-4.1 · OpenAI · Text · region Global · input US$2.00 per 1M tokens; output US$8.00 per 1M tokens - gpt-5.6-terra · OpenAI · Text · region Global · input US$2.00 per 1M tokens (prompts up to 272K tokens); US$4.00 per 1M tokens (prompts above 272K tokens); output US$12.00 per 1M tokens (prompts up to 272K tokens); US$18.00 per 1M tokens (prompts above 272K tokens) - gpt-6-sol · OpenAI · Text · region Global · input US$2.00 per 1M tokens (prompts up to 272K tokens); US$4.00 per 1M tokens (prompts above 272K tokens); output US$10.00 per 1M tokens (prompts up to 272K tokens); US$15.00 per 1M tokens (prompts above 272K tokens) - gpt-6.1-sol · OpenAI · Text · region Global · input US$2.00 per 1M tokens (prompts up to 272K tokens); US$4.00 per 1M tokens (prompts above 272K tokens); output US$10.00 per 1M tokens (prompts up to 272K tokens); US$15.00 per 1M tokens (prompts above 272K tokens) - grok-4.6 · xAI · Text · region Global · input US$2.00 per 1M tokens (prompts up to 128K tokens); US$4.00 per 1M tokens (prompts above 128K tokens); output US$6.00 per 1M tokens (prompts up to 128K tokens); US$12.00 per 1M tokens (prompts above 128K tokens) - grok-4.7 · xAI · Text · region Global · input US$2.00 per 1M tokens (prompts up to 128K tokens); US$4.00 per 1M tokens (prompts above 128K tokens); output US$6.00 per 1M tokens (prompts up to 128K tokens); US$12.00 per 1M tokens (prompts above 128K tokens) - MAI-Thinking-1 · Azure · Text · region Global · input US$2.00 per 1M tokens; output US$8.00 per 1M tokens - pixtral-large-2502 · AWS Bedrock · Text · region United States · input US$2.00 per 1M tokens; output US$6.00 per 1M tokens - cohere-command-a · Cohere · Text · region Global · input US$2.50 per 1M tokens; output US$10.00 per 1M tokens - gpt-4o · OpenAI · Text · region Global · input US$2.50 per 1M tokens; output US$10.00 per 1M tokens - gpt-5.4 · OpenAI · Text · region Global · input US$2.50 per 1M tokens (prompts up to 272K tokens); US$5.00 per 1M tokens (prompts above 272K tokens); output US$15.00 per 1M tokens (prompts up to 272K tokens); US$22.50 per 1M tokens (prompts above 272K tokens) - claude-sonnet-4-6 · Anthropic · Text · region Not specified · input US$3.00 per 1M tokens; output US$15.00 per 1M tokens - kimi-k3 · Moonshot AI · Text · region United States · input US$3.30 per 1M tokens; output US$16.50 per 1M tokens - claude-opus-5-5 · Anthropic · Text · region Not specified · input US$4.00 per 1M tokens; output US$20.00 per 1M tokens - gemini-4-argon · Google · Text · region Global · input US$4.00 per 1M tokens; output US$20.00 per 1M tokens - gpt-5.6-sol · OpenAI · Text · region Global · input US$4.00 per 1M tokens (prompts up to 272K tokens); US$8.00 per 1M tokens (prompts above 272K tokens); output US$20.00 per 1M tokens (prompts up to 272K tokens); US$30.00 per 1M tokens (prompts above 272K tokens) - claude-opus-4-8 · Anthropic · Text · region Not specified · input US$5.00 per 1M tokens; output US$25.00 per 1M tokens - claude-opus-5 · Anthropic · Text · region Not specified · input US$5.00 per 1M tokens; output US$25.00 per 1M tokens - gpt-5.5 · OpenAI · Text · region Global · input US$5.00 per 1M tokens (prompts up to 272K tokens); US$10.00 per 1M tokens (prompts above 272K tokens); output US$30.00 per 1M tokens (prompts up to 272K tokens); US$45.00 per 1M tokens (prompts above 272K tokens) - claude-fable-5 · Anthropic · Text · region Not specified · input US$10.00 per 1M tokens; output US$50.00 per 1M tokens - claude-fable-5-1 · Anthropic · Text · region Not specified · input US$10.00 per 1M tokens; output US$50.00 per 1M tokens - gpt-6-astra · OpenAI · Text · region Global · input US$10.00 per 1M tokens (prompts up to 272K tokens); US$20.00 per 1M tokens (prompts above 272K tokens); output US$50.00 per 1M tokens (prompts up to 272K tokens); US$75.00 per 1M tokens (prompts above 272K tokens) - gpt-5-pro · OpenAI · Text · region Global · input US$15.00 per 1M tokens; output US$120.00 per 1M tokens - gpt-5.4-pro · OpenAI · Text · region Global · input US$30.00 per 1M tokens (prompts up to 272K tokens); US$60.00 per 1M tokens (prompts above 272K tokens); output US$180.00 per 1M tokens (prompts up to 272K tokens); US$270.00 per 1M tokens (prompts above 272K tokens) - text-embedding-3-small · OpenAI · Embeddings · region Global · input US$0.02 per 1M tokens; output not applicable - text-embedding-3-large · OpenAI · Embeddings · region Global · input US$0.13 per 1M tokens; output not applicable - gemini-embedding-001 · Google · Embeddings · region Global · input US$0.15 per 1M tokens; output not applicable - gpt-transcribe · OpenAI · Speech · region Global · price unavailable - whisper · OpenAI · Speech · region Not specified · price unavailable - lyria-3-clip · Vertex AI · Speech · region Global · price unavailable - lyria-3-pro · Vertex AI · Speech · region Global · price unavailable - gpt-audio-mini · OpenAI · Speech · region United States · input US$0.60 per 1M tokens; US$10.00 per 1M audio tokens; output US$2.40 per 1M tokens; US$20.00 per 1M audio tokens - gemini-3.8-flash-tts · Google · Speech · region Global · input US$1.00 per 1M tokens; output US$18.00 per 1M audio tokens - gpt-4o-mini-transcribe · OpenAI · Speech · region Global · input US$1.25 per 1M tokens; US$3.00 per 1M audio tokens; output US$5.00 per 1M tokens - gemini-3.5-transcribe · Google · Speech · region Global · input US$2.00 per 1M tokens; US$2.00 per 1M audio tokens; output US$12.00 per 1M tokens - gpt-4o-transcribe-diarize · OpenAI · Speech · region Global · input US$2.50 per 1M tokens; US$6.00 per 1M audio tokens; output US$10.00 per 1M tokens - gpt-audio · OpenAI · Speech · region United States · input US$2.50 per 1M tokens; US$40.00 per 1M audio tokens; output US$10.00 per 1M tokens; US$80.00 per 1M audio tokens - gpt-audio-1.5 · OpenAI · Speech · region United States · input US$2.50 per 1M tokens; US$32.00 per 1M audio tokens; output US$10.00 per 1M tokens; US$64.00 per 1M audio tokens - gpt-4o-mini-tts · OpenAI · Speech · region United States · input US$85.00 per 1M tokens; output not applicable - FLUX-1.1-pro · Black Forest Labs · Images · region Global · input not applicable; output US$0.04 per image - FLUX.1-Kontext-pro · Black Forest Labs · Images · region Global · input not applicable; output US$0.04 per image - gemini-3.1-flash-image · Google · Images · region Global · input US$0.50 per 1M tokens; output US$3.00 per 1M tokens; US$60.00 per 1M image tokens - gemini-nano-banana-2.1 · Google · Images · region Global · input US$1.50 per 1M tokens; output US$7.50 per 1M tokens; US$30.00 per 1M image tokens - gemini-3-pro-image · Google · Images · region Global · input US$2.00 per 1M tokens (prompts up to 200K tokens); US$4.00 per 1M tokens (prompts above 200K tokens); output US$12.00 per 1M tokens (prompts up to 200K tokens); US$18.00 per 1M tokens (prompts above 200K tokens); US$125.00 per 1M image tokens - gpt-image-1-mini · OpenAI · Images · region United States · input US$2.00 per 1M tokens; US$2.50 per 1M image tokens; output US$8.00 per 1M image tokens - gpt-image-1.5 · OpenAI · Images · region United States · input US$5.00 per 1M tokens; US$8.00 per 1M image tokens; output US$10.00 per 1M tokens; US$32.00 per 1M image tokens - gpt-image-2 · OpenAI · Images · region United States · input US$5.00 per 1M tokens; US$8.00 per 1M image tokens; output US$30.00 per 1M image tokens - gpt-image-2.5-flare · OpenAI · Images · region United States · input US$5.00 per 1M tokens; US$8.00 per 1M image tokens; output US$30.00 per 1M image tokens - gpt-image-2.5-sunburst · OpenAI · Images · region United States · input US$5.00 per 1M tokens; US$8.00 per 1M image tokens; output US$30.00 per 1M image tokens - gemini-omni-1.2-flash · Google · Video · region Global · input US$1.50 per 1M tokens; output US$9.00 per 1M tokens; US$12.00 per 1M video tokens