AI Gateway

One key for every model

An OpenAI-compatible drop-in for chat, embeddings, transcription, images and video. Change the base URL, keep your code, and run it global or pinned to the EU or the US.

Paid from your AI credits Zero data retention on text EU, US or global

Base URLs
# OpenAI-compatible: chat, embeddings, audio, images, video
https://ai.overblast.app/v1

# pinned to a region
https://ai.overblast.app/eu/v1
https://ai.overblast.app/us/v1

# Anthropic Messages, for Claude Code
https://ai.overblast.app

# every call
Authorization: Bearer ob_live_…

The catalogue

What one key reaches

259chat models
67of them can run in the EU
105of them can run in the US
56image models
43video models

As of 2 October 2026, from the live catalogue. A model is counted once, however many ways there are to call it. Chat counts only the models that can be served with zero data retention, because that is the only way an Overblast key calls one. A video model on both video endpoints is one model.

Quickstart

Change one line

Make a key in the console with the AI gateway permissions it needs (models, pictures, video, speech and transcription, files), put it in OVERBLAST_API_KEY, and point the client you already use at the gateway. Model ids are vendor/model, as in the table below.

  • The OpenAI SDKs for Python and JavaScript, unchanged
  • Claude Code through the Anthropic Messages format
  • Codex through the Responses format
curl https://ai.overblast.app/v1/chat/completions \
  -H "Authorization: Bearer $OVERBLAST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5.5",
    "messages": [{"role": "user", "content": "Say hello in Estonian"}]
  }'
# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://ai.overblast.app/v1",
    api_key=os.environ["OVERBLAST_API_KEY"],
)
reply = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Say hello in Estonian"}],
)
print(reply.choices[0].message.content)
// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://ai.overblast.app/v1',
  apiKey: process.env.OVERBLAST_API_KEY,
});
const reply = await client.chat.completions.create({
  model: 'openai/gpt-6.1-sol',
  messages: [{ role: 'user', content: 'Say hello in Estonian' }],
});
console.log(reply.choices[0].message.content);
# Claude Code adds /v1/messages to the base URL itself
export ANTHROPIC_BASE_URL=https://ai.overblast.app
export ANTHROPIC_AUTH_TOKEN=$OVERBLAST_API_KEY
export ANTHROPIC_MODEL=anthropic/claude-sonnet-5.5
export ANTHROPIC_DEFAULT_HAIKU_MODEL=anthropic/claude-haiku-4.5
export CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1
# a real Anthropic key would be sent instead of yours
unset ANTHROPIC_API_KEY
claude
# ~/.codex/config.toml
[model_providers.overblast]
name = "Overblast"
base_url = "https://ai.overblast.app/v1"
env_key = "OVERBLAST_API_KEY"
wire_api = "responses"

# then, for one run
codex -c model_provider=overblast -c model=openai/gpt-6.1-sol

Regions

Global, or pinned to the EU or the US

Pin a call with the path or with a header. With neither, it is global.

Global

https://ai.overblast.app/v1

The default. Every model in the table, served wherever it runs.

EU

https://ai.overblast.app/eu/v1, or the header X-Region: eu

Served in the EU. 67 chat models can run there today.

US

https://ai.overblast.app/us/v1, or the header X-Region: us

Served in the US. 105 chat models can run there today.

No fallback

A pinned call stays in its region. A model that cannot be served there is refused with an error that names the region and the model, before anything is spent. It is never sent somewhere else instead.

Zero data retention

Every chat, embeddings, Messages and Responses call goes only to endpoints that keep neither the prompt nor the answer, and a model without one is refused. Image, video and transcription calls cannot carry that requirement.

What it does

One endpoint for the whole job

Chat

POST /v1/chat/completions, streaming or not, on any model in the table.

Embeddings

POST /v1/embeddings, for search and retrieval.

Transcription

POST /v1/audio/transcriptions: an audio file in, its text out.

Images

POST /v1/images, on 56 image models.

Video, as a job

POST /v1/videos starts a job and answers at once. Poll GET /v1/videos/{id}, then fetch the clip from /content.

Music and sound effects

POST /v1/audio/music on 7 models and POST /v1/audio/sound-effects on 5, each priced before the call. Send a video and it comes back with synced sound.

Messages and Responses

/v1/messages for Claude Code and /v1/responses for Codex, on the same key.

Paid from your AI credits

Every call is paid from your workspace's AI credits, at each model's listed price.

Your keys, in the console

Make, name and revoke API keys in the console, and give each one only what it needs: models, pictures, video, speech or files. Every call is billed to the workspace its key belongs to.

Try it free with Sponsored Tokens

sponsoredtokens.com is a public pool of free AI tokens, paid for by sponsors. Sign in for a key and a weekly allowance on the models the pool pays for, and pay nothing.

sponsoredtokens.com

Models

Every chat model

The chat models an Overblast key can call, as of 2 October 2026. Pass the id as model.

Model and idContextCan pin to
inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flash262KGlobal only
Apodex: Apodex 1.1 Mini (free)apodex/apodex-1.1-mini:free262KGlobal only
Pareto 26.10 Previewunbiased/pareto-26.10-preview1.05MGlobal only
OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro1.05MEU US
OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol1.05MEU US
Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.51MEU US
Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.537KGlobal only
Fireworks: Ember-1fireworks/ember-11.05MGlobal only
Upstage: Solar Mini 4upstage/solar-mini4524KGlobal only
Cohere: Command A+cohere/command-a-plus192KGlobal only
OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-pro1.05MEU US
OpenAI: GPT-6 Lunaopenai/gpt-6-luna1.05MEU US
OpenAI: GPT-6 Sol Proopenai/gpt-6-sol-pro1.05MEU US
OpenAI: GPT-6 Solopenai/gpt-6-sol1.05MEU US
Anthropic: Claude Opus 5.5anthropic/claude-opus-5.51MEU US
Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash1.05MUS
Xiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-pro1.05MUS
SpaceXAI: Grok 4.7x-ai/grok-4.7500KUS
Z.ai: GLM 5.3 FlashXz-ai/glm-5.3-flashx1.05MGlobal only
Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbo128KGlobal only
Inference.net: Schematron V2 Smallinference-net/schematron-v2-small128KGlobal only
inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl262KUS
DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash1.05MUS
Inception: Mercury 2.5inception/mercury-2.5260KGlobal only
OpenAI: GPT-6 Astraopenai/gpt-6-astra1.05MUS
OpenAI: GPT-6 Astra Proopenai/gpt-6-astra-pro1.05MUS
inclusionAI: Ling 3.0 Flash Sante (free)inclusionai/ling-3.0-flash-sante:free262KGlobal only
Google: Gemini 3.8 Flashgoogle/gemini-3.8-flash1.05MGlobal only
IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b131KUS
Tencent: Hy4 previewtencent/hy4-preview1.05MGlobal only
inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin262KUS
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash1.05MUS
DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp1.05MUS
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b8KGlobal only
Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b8KGlobal only
Tencent: Hy-MT2-7Btencent/hy-mt2-7b8KGlobal only
Z.ai: GLM 5.3z-ai/glm-5.31.05MEU US
Qwen: Qwen3.8 27Bqwen/qwen3.8-27b1MUS
Qwen: Qwen3.8 27B (free)qwen/qwen3.8-27b:free262KUS
Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash1.05MGlobal only
ByteDance Seed: Seed 2.1 Turbobytedance-seed/seed-2-1-turbo262KGlobal only
Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b1.05MUS
ByteDance Seed: Seed-2.0-Codebytedance-seed/seed-2.0-code262KGlobal only
DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-08131.05MUS
SpaceXAI: Grok 4.6x-ai/grok-4.6500KUS
NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning262KUS
Upstage: Solar Pro 4upstage/solar-pro4524KGlobal only
Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b131KUS
DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-07311.05MEU US
Thinking Machines: Inkling Smallthinkingmachines/inkling-small524KUS
Anthropic: Claude Opus 5anthropic/claude-opus-51MEU US
inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash262KUS
Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash1.05MUS
Google: Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite1.05MEU US
Thinking Machines: Inklingthinkingmachines/inkling524KUS
MoonshotAI: Kimi K3moonshotai/kimi-k31.05MUS
OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro1.05MEU
OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna1.05MEU US
OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-pro1.05MEU
OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terra1.05MEU US
OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-pro1.05MEU
OpenAI: GPT-5.6 Solopenai/gpt-5.6-sol1.05MEU US
SpaceXAI: Grok 4.5x-ai/grok-4.5500KGlobal only
Tencent: Hy3tencent/hy3262KUS
Anthropic: Claude Sonnet 5anthropic/claude-sonnet-51MEU US
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-image66KGlobal only
Google: Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image131KGlobal only
Google: Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image131KGlobal only
Z.ai: GLM 5.2z-ai/glm-5.21.05MEU US
MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code262KEU
NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety131KUS
NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b262KUS
MiniMax: MiniMax M3minimax/minimax-m31.05MUS
StepFun: Step 3.7 Flashstepfun/step-3.7-flash262KGlobal only
Anthropic: Claude Opus 4.8anthropic/claude-opus-4.81MEU US
SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1256KGlobal only
Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash1.05MUS
Perceptron: Perceptron Mk1perceptron/perceptron-mk133KGlobal only
Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite1.05MEU US
SpaceXAI: Grok 4.3x-ai/grok-4.31MGlobal only
Mistral: Mistral Medium 3.5mistralai/mistral-medium-3-5262KEU
Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b262KUS
Qwen: Qwen3.6 27Bqwen/qwen3.6-27b262KUS
OpenAI: GPT-5.5openai/gpt-5.51.05MEU US
DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro1.05MUS
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash1.05MUS
Xiaomi: MiMo-V2.5-Proxiaomi/mimo-v2.5-pro1.05MGlobal only
Xiaomi: MiMo-V2.5xiaomi/mimo-v2.51.05MGlobal only
MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6262KEU US
Anthropic: Claude Opus 4.7anthropic/claude-opus-4.71MEU US
Z.ai: GLM 5.1z-ai/glm-5.1205KGlobal only
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it262KUS
Google: Gemma 4 31Bgoogle/gemma-4-31b-it262KUS
Z.ai: GLM 5V Turboz-ai/glm-5v-turbo203KGlobal only
SpaceXAI: Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent2MGlobal only
SpaceXAI: Grok 4.20x-ai/grok-4.202MGlobal only
Reka Edgerekaai/reka-edge16KGlobal only
MiniMax: MiniMax M2.7minimax/minimax-m2.7205KGlobal only
OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano400KUS
OpenAI: GPT-5.4 Miniopenai/gpt-5.4-mini400KUS
Mistral: Mistral Small 4mistralai/mistral-small-2603262KEU US
Z.ai: GLM 5 Turboz-ai/glm-5-turbo203KGlobal only
NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b262KUS
ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-lite262KGlobal only
Qwen: Qwen3.5-9Bqwen/qwen3.5-9b262KUS
OpenAI: GPT-5.4 Proopenai/gpt-5.4-pro1.05MGlobal only
OpenAI: GPT-5.4openai/gpt-5.41.05MEU US
Inception: Mercury 2inception/mercury-2128KGlobal only
ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini262KGlobal only
Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b262KUS
Qwen: Qwen3.5-27Bqwen/qwen3.5-27b262KUS
Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b262KGlobal only
OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codex400KGlobal only
Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview1.05MGlobal only
Anthropic: Claude Sonnet 4.6anthropic/claude-sonnet-4.61MEU US
Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b262KUS
MiniMax: MiniMax M2.5minimax/minimax-m2.5205KGlobal only
Z.ai: GLM 5z-ai/glm-5205KGlobal only
Anthropic: Claude Opus 4.6anthropic/claude-opus-4.61MEU
Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next262KGlobal only
StepFun: Step 3.5 Flashstepfun/step-3.5-flash262KGlobal only
MoonshotAI: Kimi K2.5moonshotai/kimi-k2.5262KUS
Writer: Palmyra X5writer/palmyra-x51.04MGlobal only
Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash200KGlobal only
OpenAI: GPT-5.2-Codexopenai/gpt-5.2-codex400KGlobal only
ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash262KGlobal only
ByteDance Seed: Seed 1.6bytedance-seed/seed-1.6262KGlobal only
MiniMax: MiniMax M2.1minimax/minimax-m2.1205KGlobal only
Z.ai: GLM 4.7z-ai/glm-4.7205KUS
Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview1.05MGlobal only
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b262KUS
OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chat128KGlobal only
OpenAI: GPT-5.2openai/gpt-5.2400KGlobal only
Mistral: Devstral 2 2512mistralai/devstral-2512262KEU
Relace: Relace Searchrelace/relace-search256KGlobal only
Z.ai: GLM 4.6Vz-ai/glm-4.6v131KGlobal only
OpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-max400KGlobal only
Amazon: Nova 2 Liteamazon/nova-2-lite-v11MEU
Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512262KEU
Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512262KEU
Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512131KEU
Mistral: Mistral Large 3 2512mistralai/mistral-large-2512262KEU
DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2164KUS
Anthropic: Claude Opus 4.5anthropic/claude-opus-4.5200KEU
OpenAI: GPT-5.1openai/gpt-5.1400KEU
OpenAI: GPT-5.1-Codexopenai/gpt-5.1-codex400KGlobal only
OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini400KGlobal only
MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking262KGlobal only
Amazon: Nova Premier 1.0amazon/nova-premier-v11MGlobal only
Perplexity: Sonar Pro Searchperplexity/sonar-pro-search200KGlobal only
Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-250733KEU
OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b131KGlobal only
MiniMax: MiniMax M2minimax/minimax-m2205KGlobal only
Anthropic: Claude Haiku 4.5anthropic/claude-haiku-4.5200KEU US
Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct262KGlobal only
Google: Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-image33KGlobal only
Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking262KGlobal only
Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct262KUS
Z.ai: GLM 4.6z-ai/glm-4.6205KUS
Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.51MEU US
DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp164KGlobal only
TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1131KGlobal only
Relace: Relace Apply 3relace/relace-apply-3256KGlobal only
Qwen: Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking131KGlobal only
Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct262KUS
DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus164KGlobal only
Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking262KGlobal only
Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct262KUS
MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905262KGlobal only
Nous: Hermes 4 405Bnousresearch/hermes-4-405b131KGlobal only
DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1164KUS
Mistral: Mistral Medium 3.1mistralai/mistral-medium-3.1131KEU
Z.ai: GLM 4.5Vz-ai/glm-4.5v66KGlobal only
OpenAI: GPT-5openai/gpt-5400KEU
OpenAI: GPT-5 Miniopenai/gpt-5-mini400KEU
OpenAI: GPT-5 Nanoopenai/gpt-5-nano400KEU
OpenAI: gpt-oss-120bopenai/gpt-oss-120b131KEU US
OpenAI: gpt-oss-20bopenai/gpt-oss-20b131KEU US
Anthropic: Claude Opus 4.1anthropic/claude-opus-4.1200KGlobal only
Mistral: Codestral 2508mistralai/codestral-2508256KEU
Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct262KGlobal only
Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507262KGlobal only
Z.ai: GLM 4.5z-ai/glm-4.5131KGlobal only
Z.ai: GLM 4.5 Airz-ai/glm-4.5-air131KGlobal only
Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507131KGlobal only
Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coder262KUS
ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b128KGlobal only
Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite1.05MEU
Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507262KUS
MoonshotAI: Kimi K2 0711moonshotai/kimi-k2131KGlobal only
Venice: Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-edition128KGlobal only
Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct131KGlobal only
Morph: Morph V3 Largemorph/morph-v3-large262KGlobal only
Morph: Morph V3 Fastmorph/morph-v3-fast82KGlobal only
Baidu: ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47b123KGlobal only
Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct256KEU US
MiniMax: MiniMax M1minimax/minimax-m11MGlobal only
Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash1.05MEU
Google: Gemini 2.5 Progoogle/gemini-2.5-pro1.05MEU US
Google: Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview1.05MGlobal only
DeepSeek: R1 0528deepseek/deepseek-r1-0528164KUS
Anthropic: Claude Sonnet 4anthropic/claude-sonnet-4200KEU
Mistral: Mistral Medium 3mistralai/mistral-medium-3131KEU
Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12b164KUS
Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3b131KUS
Qwen: Qwen3 14Bqwen/qwen3-14b131KUS
Qwen: Qwen3 32Bqwen/qwen3-32b131KUS
OpenAI: GPT-4.1openai/gpt-4.11.05MEU
OpenAI: GPT-4.1 Miniopenai/gpt-4.1-mini1.05MEU
OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano1.05MEU
Meta: Llama 4 Maverickmeta-llama/llama-4-maverick1.05MUS
Meta: Llama 4 Scoutmeta-llama/llama-4-scout1.31MUS
DeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324164KGlobal only
Google: Gemma 3 4Bgoogle/gemma-3-4b-it131KUS
Google: Gemma 3 12Bgoogle/gemma-3-12b-it131KUS
Reka Flash 3rekaai/reka-flash-366KGlobal only
Google: Gemma 3 27Bgoogle/gemma-3-27b-it131KUS
TheDrummer: Skyfall 36B V2thedrummer/skyfall-36b-v233KGlobal only
Perplexity: Sonar Reasoning Properplexity/sonar-reasoning-pro128KGlobal only
Perplexity: Sonar Properplexity/sonar-pro200KGlobal only
Perplexity: Sonar Deep Researchperplexity/sonar-deep-research128KGlobal only
Mistral: Sabamistralai/mistral-saba33KEU
Qwen: Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct128KGlobal only
Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-250133KUS
Perplexity: Sonarperplexity/sonar127KGlobal only
DeepSeek: R1deepseek/deepseek-r164KGlobal only
Microsoft: Phi 4microsoft/phi-416KUS
DeepSeek: DeepSeek V3deepseek/deepseek-chat164KUS
Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b131KGlobal only
Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct131KUS
Amazon: Nova Lite 1.0amazon/nova-lite-v1300KEU
Amazon: Nova Micro 1.0amazon/nova-micro-v1128KEU
Amazon: Nova Pro 1.0amazon/nova-pro-v1300KEU
Mistral Large 2407mistralai/mistral-large-2407131KEU
TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b1.02MGlobal only
Magnum v4 72Banthracite-org/magnum-v4-72b33KGlobal only
Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct33KGlobal only
Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct131KGlobal only
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct33KUS
Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b131KUS
Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b131KUS
Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b131KUS
Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b8KUS
OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06128KGlobal only
Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct131KUS
Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct131KUS
Mistral: Mistral Nemomistralai/mistral-nemo131KEU US
OpenAI: GPT-4o-miniopenai/gpt-4o-mini128KEU
Google: Gemma 2 27Bgoogle/gemma-2-27b-it8KGlobal only
OpenAI: GPT-4oopenai/gpt-4o128KGlobal only
OpenAI: GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13128KGlobal only
Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct66KEU
WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b66KGlobal only
Mistral Largemistralai/mistral-large128KEU
OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-06134KGlobal only
OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k16KGlobal only
Mancer: Weaver (alpha)mancer/weaver8KGlobal only
ReMM SLERP 13Bundi95/remm-slerp-l2-13b6KGlobal only
MythoMax 13Bgryphe/mythomax-l2-13b8KUS
OpenAI: GPT-4openai/gpt-48KGlobal only

Every model with its price, images and video included

Get a key and change one line

Make an API key in the console and point your client at https://ai.overblast.app/v1.

API reference · status.overblast.app · The Overblast API