Models

42 models behind one OpenAI-compatible endpoint. GPT & Claude 50% below official; all others 25% off — compared with OpenRouter, no platform fee.

✓ Browse in Dashboard → Models  ·  ✓ Or call GET /v1/models
Model naming

Provider-style IDs

Models use provider-style IDs. Always use the exact ID returned by the API or shown in the dashboard.

claude-sonnet-4-6
claude-opus-4-8
gpt-5.5
gpt-5.4

Pass the ID as the model field in any chat completion request. Pricing is listed in USD per 1M tokens.

Browse the full catalog in Dashboard → Models, or fetch it programmatically with GET /v1/models.

See the Pricing page for the complete rate card.

Catalog

All models, one API

Boundless vs official vs OpenRouter · OpenRouter = official + 5% · GPT & Claude −50% · Others −25% · Token models per 1M · Veo per second · Image output per image

Model Context Boundless / 1M Official / 1M OpenRouter / 1M vs Official Status
Claude
claude-opus-4-8$2.5 / $12.5$5 / $25$5.25 / $26.25−50%Live
claude-opus-4-7$2.5 / $12.5$5 / $25$5.25 / $26.25−50%Live
claude-opus-4-6$2.5 / $12.5$5 / $25$5.25 / $26.25−50%Coming soon
claude-sonnet-4-6$1.5 / $7.5$3 / $15$3.15 / $15.75−50%Live
claude-haiku-4-5-20251001$0.4 / $2$0.8 / $4$0.84 / $4.2−50%Live
OpenAI GPT
gpt-5.5$1.25 / $7.5$2.5 / $15$2.62 / $15.75−50%Live
gpt-5.4$1.25 / $7.5$2.5 / $15$2.62 / $15.75−50%Live
gpt-5.3-codex$0.875 / $7$1.75 / $14$1.84 / $14.7−50%Coming soon
gpt-5.2$0.875 / $7$1.75 / $14$1.84 / $14.7−50%Coming soon
Google Gemini
gemini-3.5-flash-low$0.188 / $1.12$0.25 / $1.5$0.263 / $1.58−25%Coming soon
gemini-3.5-flash-high$2.03 / $12.15$2.7 / $16.2$2.84 / $17.01−25%Coming soon
gemini-3.5-flash$1.12 / $6.75$1.5 / $9$1.58 / $9.45−25%Coming soon
gemini-3.1-pro-preview$1.5 / $9$2 / $12$2.1 / $12.6−25%Coming soon
gemini-3-flash-preview$0.375 / $2.25$0.5 / $3$0.525 / $3.15−25%Coming soon
gemini-3.1-flash-lite-preview$0.188 / $1.12$0.25 / $1.5$0.263 / $1.58−25%Coming soon
gemini-3.1-flash-lite$0.188 / $1.12$0.25 / $1.5$0.263 / $1.58−25%Coming soon
gemini-2.5-pro$0.938 / $7.5$1.25 / $10$1.31 / $10.5−25%Coming soon
gemini-2.5-flash-nothingk$0.225 / $1.88$0.3 / $2.5$0.315 / $2.62−25%Coming soon
gemini-2.5-flash$0.225 / $1.88$0.3 / $2.5$0.315 / $2.62−25%Coming soon
gemini-2.5-flash-lite$0.075 / $0.3$0.1 / $0.4$0.105 / $0.42−25%Coming soon
Google Veo (video)
veo-3.1-video-audio$0.3/s$0.4/s$0.42/s−25%Coming soon
veo-3.1-video-only$0.15/s$0.2/s$0.21/s−25%Coming soon
veo-3.1-fast-video-audio$0.112/s$0.15/s$0.158/s−25%Coming soon
veo-3.1-fast-video-only$0.075/s$0.1/s$0.105/s−25%Coming soon
veo-3-video-audio$0.3/s$0.4/s$0.42/s−25%Coming soon
veo-3-video-only$0.15/s$0.2/s$0.21/s−25%Coming soon
veo-3-fast-video-audio$0.112/s$0.15/s$0.158/s−25%Coming soon
veo-3-fast-video-only$0.075/s$0.1/s$0.105/s−25%Coming soon
veo-2-video-only$0.375/s$0.5/s$0.525/s−25%Coming soon
Google Image
gemini-3-pro-image-preview$1.5 / $0.101/img$2 / $0.134/img$2.1 / $0.141/img−25%Coming soon
gemini-3.1-flash-image-preview$0.188 / $0.05/img$0.25 / $0.067/img$0.263 / $0.07/img−25%Coming soon
gemini-2.5-flash-image$0.225 / $0.029/img$0.3 / $0.039/img$0.315 / $0.041/img−25%Coming soon
Open source LLMs
deepseek-v4-flash$0.75 / $1.5$1 / $2$1.05 / $2.1−25%Coming soon
deepseek-v4-pro$9 / $18$12 / $24$12.6 / $25.2−25%Coming soon
qwen3.7-max$9 / $27$12 / $36$12.6 / $37.8−25%Coming soon
kimi-k2.7-code$4.88 / $20.25$6.5 / $27$6.83 / $28.35−25%Coming soon
kimi-k2.6$4.88 / $20.25$6.5 / $27$6.83 / $28.35−25%Coming soon
kimi-k2.5$3 / $15.75$4 / $21$4.2 / $22.05−25%Coming soon
glm-5.2$6 / $21$8 / $28$8.4 / $29.4−25%Coming soon
glm-5.1$4.5 / $18$6 / $24$6.3 / $25.2−25%Coming soon
glm-5$3 / $13.5$4 / $18$4.2 / $18.9−25%Coming soon
minimax-m3$3.15 / $12.6$4.2 / $16.8$4.41 / $17.64−25%Coming soon
Signup bonus

$5 on signup

Sign up with Google, GitHub, or email — we add $5.00 to your balance. No credit card required.

Models available now

Use the exact model IDs below. Copy-paste from the dashboard or this list — spaces and wrong casing will fail.

Quickstart →
  • claude-sonnet-4-6
  • claude-opus-4-8
  • claude-opus-4-7
  • claude-haiku-4-5-20251001
  • gpt-5.5
  • gpt-5.4
Capabilities

What each model supports

Capability tags tell you what a model can do. Check the model detail page for supported parameters.

chat

Text chat completions

vision

Image input

tools

Function calling

json

Structured output

reasoning

Extended thinking tokens

Lifecycle

Deprecation & availability

We give you room to migrate, and surface real-time status when something degrades.

Deprecation policy

  • Minimum 30 days notice before removing a model
  • Announced via the Changelog and email
  • A suggested migration path is always provided

Availability

Real-time status: System status

Per-model status is shown in the Dashboard whenever a model is degraded, so you can route around incidents.

Start with $5 in credits

Sign up with Google, GitHub, or email · $5 added to your balance · No card required

Create free account View pricing →