Orbitrage routes across models from Azure (GPT and open models via Foundry),
Anthropic, OpenAI, Groq, and xAI. Let the router pick (model: "auto") or pin
any model by id.
The catalog below is representative. The live, authoritative list for your
account is always GET https://api.orbitrage.ai/v1/models — see
List models. Availability depends on which
providers are configured and any BYOK keys you’ve saved. Pricing & tiers
Prices are USD per 1M tokens (input / output). Pooled-credit calls add a small
platform markup (currently 2.5%); BYOK calls cost nothing against your
Orbitrage credits.
Frontier
| Model | Provider | Input | Output | Vision | Context |
|---|
claude-fable-5 | Anthropic | $10.00 | $50.00 | ✓ | 200K |
claude-opus-4-8 | Anthropic | $5.00 | $25.00 | ✓ | 200K |
claude-opus-4-7 | Anthropic | $5.00 | $25.00 | ✓ | 200K |
claude-sonnet-4-6 | Anthropic | $3.00 | $15.00 | ✓ | 200K |
gpt-5.5 | Azure | $5.00 | $20.00 | ✓ | 400K |
claude-fable-5 is Anthropic’s top-tier model (above Opus) — the highest-quality
option in the catalog, used for the hardest reasoning and agentic tasks.
High
| Model | Provider | Input | Output | Vision | Context |
|---|
gpt-5.4 | Azure | $1.25 | $5.00 | ✓ | 400K |
gpt-5.3-chat | Azure | $1.50 | $6.00 | ✓ | 400K |
Kimi-K2.6 | Azure Foundry | $0.95 | $4.00 | ✓ | 200K |
DeepSeek-V3.2 | Azure Foundry | $0.40 | $1.10 | — | 131K |
grok-4 | xAI | $1.25 | $2.50 | ✓ | 256K |
Mid
| Model | Provider | Input | Output | Vision | Context |
|---|
gpt-5.4-nano | Azure | $0.20 | $1.25 | ✓ | 256K |
gpt-4o | Azure | $2.50 | $10.00 | ✓ | 128K |
FW-MiniMax-M2.5 | Azure Foundry | $0.30 | $1.20 | — | 262K |
DeepSeek-V4-Flash | Azure Foundry | $0.14 | $0.28 | — | 131K |
Basic
| Model | Provider | Input | Output | Vision | Context |
|---|
gpt-5-nano | Azure | $0.10 | $0.40 | ✓ | — |
gpt-4o-mini | Azure | $0.165 | $0.66 | ✓ | — |
gpt-5.4-mini | Azure | $0.10 | $0.40 | ✓ | 256K |
llama-3.1-8b-instant | Groq | $0.05 | $0.08 | — | 131K |
Image
| Model | Provider | Billing |
|---|
gpt-image-2 | Azure | Per image |
Audio (managed, included)
Speech-to-text and text-to-speech are offered as a managed service on
Deepgram — no BYOK needed. See Audio.
| Model | Provider | Type | Billing |
|---|
nova-3 | Deepgram | Speech-to-text | Per minute of audio |
nova-3-multilingual | Deepgram | Speech-to-text | Per minute of audio |
nova-2 | Deepgram | Speech-to-text | Per minute of audio |
aura-2-thalia-en | Deepgram | Text-to-speech | Per 1,000 characters |
The full catalog also includes the DeepSeek R1 reasoning model, additional GPT-5
variants (gpt-5.3, gpt-chat-latest), llama-3.1-70b-versatile on Groq, and
the full xAI Grok family (grok-4.3, grok-4-fast, grok-3 variants, and
more). Query /v1/models for everything enabled on your account.
Cost, savings, and the markup
Every call records four cost figures, so you can see exactly where your money goes:
| Field | Meaning |
|---|
Cost (cost_usd) | What you’re billed — upstream price plus the 2.5% markup. 0 for BYOK. |
| Provider cost | The raw upstream price Orbitrage paid (internal). |
| Baseline cost | What the same call would have cost on a frontier baseline (claude-sonnet-4-6). |
Saved (saved_usd) | baseline − cost — the routing savings, never negative. |
Vision & multimodal
Vision-capable models accept image content blocks in the standard OpenAI format,
and the router prefers one automatically when your prompt contains images. The
engine also exposes image generation/editing and audio (transcription,
translation, speech) endpoints — see
the API reference.
Pinning vs. aliases
- Pin a model by passing its exact id — no scoring, straight to that model.
- Route by passing
auto (or router / default / orbitrage).
- Model ids match flexibly —
claude-sonnet-4.6 and claude-sonnet-4-6 resolve
to the same model, and family names (e.g. claude-opus, grok-4) resolve to
the appropriate provider and tier.
