One API.
Every frontier model.
Forge is the unified gateway for 200+ AI models. Switch providers with a string, route by price or latency, and ship without rewriting a line of code.
$ curl https://api.forge.dev/v1/chat/completions \
-H "Authorization: Bearer $FORGE_KEY" \
-d '{
"model": "anthropic/claude-4.5-sonnet",
"route": "cheapest",
"messages": [
{ "role": "user", "content": "Plan a 3-day Lisbon trip." }
]
}'
{
"id": "fr_01J9X…",
"model": "anthropic/claude-4.5-sonnet",
"choices": [{ "message": {
"role": "assistant",
"content": "Day 1 — Alfama & Fado…"
}}],
"usage": { "prompt": 32, "completion": 412 },
"cost_usd": 0.0046
}Text, vision, audio, image & video — one contract.
A curated view of the frontier models you can route through Forge. Pricing and availability are representative — actual runtime models are configured in your dashboard.
Text & reasoning
8 models| Model | Vendor | Context | In / 1M | Out / 1M | Description |
|---|---|---|---|---|---|
| GPT-5 | OpenAI | 400K | $5.00 | $20.00 | Frontier reasoning with native tool use, extended thinking and multimodal input. |
| Claude 4.5 Sonnet | Anthropic | 1M | $3.00 | $15.00 | Best-in-class coding agent with 1M-token context and computer-use tools. |
| Gemini 3 Pro | 2M | $1.25 | $10.00 | Massive 2M-token window and native video / audio reasoning at production speed. | |
| Llama 4 405B | Meta | 256K | $0.90 | $0.90 | Open-weights frontier model with strong agentic performance and symmetric pricing. |
| DeepSeek R2 | DeepSeek | 128K | $0.14 | $0.28 | High-efficiency chain-of-thought reasoning at a fraction of frontier prices. |
| Qwen 3 Max | Alibaba | 1M | $0.60 | $1.80 | Long-context bilingual frontier model with strong tool-use and code skills. |
| Mistral Large 3 | Mistral | 256K | $2.00 | $6.00 | European frontier model with strong reasoning, code and function calling. |
| Grok 3.5 | xAI | 128K | $3.00 | $15.00 | Real-time reasoning grounded in live X data, with playful tone. |
Image generation
5 models
Video generation
4 models
Speech & audio
4 modelsNative audio-in, audio-out conversation model with sub-300ms latency.
State-of-the-art speech recognition across 99 languages with diarization.
Expressive multilingual text-to-speech with voice cloning and styles.
Real-time audio streaming with simultaneous video understanding.
Built for teams shipping LLM products in production.
Smart routing
Route by cost, latency, capability, or region. Failover across providers in milliseconds — your users never see a 503.
Cost & latency analytics
Per-route dashboards. Set spend caps and alerts. Export usage to your warehouse.
Zero retention
Prompts never leave your perimeter. SOC 2 Type II, HIPAA, EU residency.
OpenAI-compatible
Drop-in replacement for openai-sdk. Same shape for tools, vision, streaming.
Evals & A/B
Compare two models on the same prompt, side-by-side, with cost & quality scores.