AI Providers
Straico Models Access 60+ aggregated AI models from 10+ providers through Straico
Straico aggregates AI models from multiple providers into a single platform with unified credits. Access chat, image, video, and audio models without managing multiple API keys.
API Key : Get your API key at platform.straico.com/user-settings
Single credit system for all models
60+ models from 10+ providers
Unified interface
Pay-as-you-go pricing
Model ID Name Description openai/gpt-5.1GPT-5.1 Latest flagship openai/gpt-5GPT-5 Advanced openai/gpt-5-chatGPT-5 Chat Chat optimized openai/gpt-5-miniGPT-5 Mini Compact openai/gpt-5-nanoGPT-5 Nano Smallest openai/gpt-4.1GPT-4.1 Latest GPT-4 openai/gpt-4.1-miniGPT-4.1 Mini Compact GPT-4 openai/gpt-4o-2024-11-20GPT-4o Nov-20 November version openai/gpt-4o-2024-08-06GPT-4o Aug-06 August version openai/gpt-4o-miniGPT-4o Mini Free tier openai/o3o3 Reasoning openai/o3-mini-higho3 Mini High High reasoning openai/o3-mini-mediumo3 Mini Medium Medium reasoning openai/o4-minio4 Mini Latest reasoning openai/o4-mini-higho4 Mini High High reasoning openai/o1o1 Original reasoning openai/o1-higho1 High Enhanced o1
Model ID Name Description anthropic/claude-sonnet-4.5Claude Sonnet 4.5 Balanced anthropic/claude-sonnet-4Claude Sonnet 4 Standard anthropic/claude-opus-4Claude Opus 4 Most capable anthropic/claude-3.7-sonnet:thinkingClaude 3.7 Sonnet Reasoning High reasoning anthropic/claude-3.7-sonnetClaude 3.7 Sonnet Reasoning Medium reasoning anthropic/claude-3-5-haiku-20241022Claude 3.5 Haiku Fast claude-3-haiku-20240307Claude 3 Haiku (Azure) Azure hosted
Model ID Name Description google/gemini-2.5-pro-previewGemini Pro 2.5 Reasoning Advanced google/gemini-2.5-flashGemini 2.5 Flash Fast google/gemini-2.5-flash-liteGemini 2.5 Flash Lite Lightweight google/gemini-2.0-flash-001Gemini Flash 2.0 Previous gen google/gemini-pro-1.5Gemini Pro 1.5 Stable google/gemma-2-27b-itGemma 2 27B Open model
Model ID Name Description x-ai/grok-4-reasoningGrok 4 Reasoning Advanced x-ai/grok-4-fastGrok 4 Fast Speed optimized x-ai/grok-3-betaGrok 3 Beta Previous gen x-ai/grok-3-mini-beta-reasoningGrok 3 Mini Reasoning Compact x-ai/grok-2-1212Grok 2 Legacy
Model ID Name Description meta-llama/llama-4-maverickLlama 4 Maverick Latest meta-llama/llama-3.3-70b-instructLlama 3.3 70B Large meta-llama/llama-3.1-405b-instructLlama 3.1 405B Largest meta-llama/llama-3.1-70b-instructLlama 3.1 70B Efficient meta-llama/llama-3-70b-instruct:nitroLlama 3 70B Nitro Speed boost
Model ID Name Description deepseek/deepseek-v3.1DeepSeek V3.1 Latest deepseek/deepseek-chat-v3-0324DeepSeek V3 0324 March version deepseek/deepseek-chatDeepSeek V3 Standard deepseek/deepseek-r1DeepSeek R1 Reasoning deepseek/deepseek-r1:nitroDeepSeek R1 Nitro Fast reasoning
Model ID Name Description cohere/command-r-plus-08-2024Command R+ Most capable cohere/command-r-08-2024Command R Standard
Model ID Name Description mistralai/mistral-medium-3Mistral Medium 3 Balanced mistralai/codestral-mambaCodestral Mamba Code focused
Model ID Name Description moonshotai/kimi-k2-thinkingKimi K2 Thinking Reasoning moonshotai/kimi-k2-0905Kimi K2 0905 September moonshotai/kimi-k2-0711Kimi K2 0711 July
Model ID Name Description nvidia/llama-3.3-nemotron-super-49b-v1.5-reasoningNemotron Super 49B Reasoning Enhanced nvidia/llama-3.3-nemotron-super-49b-v1Nemotron Super 49B Standard nvidia/llama-3.1-nemotron-ultra-253b-v1Nemotron Ultra 253B Largest
Model ID Name Description qwen/qwen3-235b-a22b-reasoningQwen3 235B Reasoning Advanced qwen/qwen3-coderQwen3 Coder Code focused qwen/qwen-2.5-72b-instructQwen 2.5 72B Large qwen/qwen-2.5-vl-32b-instructQwen 2.5 VL 32B Vision-language qwen/qwen2-vl-72b-instructQwen2 VL 72B Vision qwen/qwen-2-72b-instructQwen 2 72B Previous gen
Model ID Name Description perplexity/sonar-deep-research-reasoningSonar Deep Research Research focused perplexity/sonarSonar Standard
Model ID Name Description minimax/minimax-m2MiniMax M2 Chinese model microsoft/phi-4Microsoft Phi 4 Compact zhipu/glm-4.6GLM 4.6 Chinese model zhipu/glm-4.5v-reasoningGLM 4.5V Reasoning Vision cognitivecomputations/dolphin-2.6-mixtral-8x7bDolphin 2.6 Mixtral Uncensored alpindale/goliath-120bGoliath 120B Large merged gryphe/mythomax-l2-13b-8kMythoMax L2 13B Creative wizardlm/wizardlm-2-8x22bWizardLM-2 8x22B Instruction
Model ID Name openai/dall-e-3DALL-E 3 gpt-image-1-azureGPT Image 1 (Azure)
Model ID Name flux/1.1Flux 1.1 flux-1-kontext-proFlux Kontext Pro
Model ID Name fal-ai/ideogram-v3Ideogram V3 ideogram/V_2AIdeogram V2A ideogram/V_2A_TURBOIdeogram V2A Turbo ideogram/V_2Ideogram V2 ideogram/V_2_TURBOIdeogram V2 Turbo
Model ID Name fal-ai/imagen4/previewImagen 4
Model ID Name fal-ai/recraft-v3Recraft V3 fal-ai/bagelBagel nano-banana-text-to-imageNano Banana qwen-image-text-to-imageQwen Image
Model ID Name Description fal-ai/veo-2Google Veo 2 High quality runway/gen-4-turboRunway Gen 4 Turbo Professional runway/gen-3-alpha-turboRunway Gen 3 Alpha Turbo Fast fal-ai/kling-2.1-image-to-videoKling 2.1 Image to video fal-ai/vidu-q1Vidu Q1 Text to video
Model ID Name Description eleven_v3ElevenLabs V3 TTS Premium quality eleven_multilingual_v2ElevenLabs Multilingual V2 Multi-language tts-1OpenAI TTS-1 Standard
Model ID Description openai/gpt-4o-miniGPT-4o Mini free tier
Pay with Straico credits across all models:
No separate billing
Easy budget tracking
Flexible allocation
Access specialized models:
Reasoning models
Code generation
Vision-language
Creative writing
Beyond text and images:
ElevenLabs TTS
Runway video
Google Veo
Straico aggregates pricing competitively, often with volume discounts.
// Model: openai/gpt-5 =AITEXT("Create a marketing strategy for a SaaS product") // Model: ideogram/V_2A =AIIMAGE("Minimalist logo design for a tech startup, vector style") // Model: fal-ai/veo-2 =AIVIDEO("Product showcase with rotating camera, professional lighting") // Model: eleven_v3 =AISPEECH("Welcome to our product demonstration") Need Recommended Models General text openai/gpt-4o-mini, anthropic/claude-3-5-haiku Complex reasoning openai/o3, deepseek/deepseek-r1 Code generation qwen/qwen3-coder, mistralai/codestral-mamba Creative writing gryphe/mythomax-l2-13b-8k Research perplexity/sonar-deep-research-reasoning Image generation ideogram/V_2A, flux/1.1 Video generation fal-ai/veo-2, runway/gen-4-turbo Voice synthesis eleven_v3, eleven_multilingual_v2
Track your Straico credit usage in the dashboard to optimize spending.
Use Straico's playground to test models before integrating.
Straico uses a credit-based system:
Purchase credits in bulk
Each model has a credit cost per token/generation
Volume discounts available
Check Straico's pricing page for current credit costs per model, as they update periodically.
