GPT 6 Astraopenai/gpt-6-astraAvailable
- Declared context
- 1M
- Known input modality
- Text
- Declared input / 1M
- See billing
- Declared output / 1M
- See billing
RouteMesh Live
One clear route to every capable model
Explicit routing, transparent pricing, automatic failover. One API for explicit model routing, visible provider health, and auditable usage.
Transparent pricingAutomatic failoverBring the client you already use.
RouteMesh Route Status
AI gateway health board
Operational
Observed routes
3
Average latency
35.30 s
Availability
100%
GPT 6 Astra
openai/gpt-6-astra
GPT 5.6 Sol
openai/gpt-5.6-sol
Omni Moderation
aihubmix/omni-moderation-latest
Observed route: openai/gpt-6-astra
Provider OpenAI, region eu-west
routemeshroute --task "build homepage" --mode fastest
Model catalog
A model catalog for the first call.
Compare models, context, pricing, and availability before you send a request.
RouteMesh session
route selectedopenai/gpt-6-astra
curl https://api.routemesh.ai/v1/chat/completions \
-H "Authorization: Bearer $ROUTEMESH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6-astra",
"messages": [{"role": "user", "content": "Hello"}]
}'OpenAIeu-west, us-east$0 / 1M
Less setup, faster first call.
One Base URLOne endpoint
Model selectionCatalog driven
Usage recordAuditable
Failover pathSame model
3 listed
| Model | Declared context | Known input modality | Declared input / 1M | Declared output / 1M | Health observation | |
|---|---|---|---|---|---|---|
| GPT 6 Astraopenai/gpt-6-astra+ 9 billing items | 1M | Text | See billing | See billing | Available | |
| GPT 5.6 Solopenai/gpt-5.6-sol+ 9 billing items | 1M | Text | See billing | See billing | Available | |
| Omni Moderationaihubmix/omni-moderation-latest | 33K | Text | $0.02 | $0.02 | Available |
GPT 5.6 Solopenai/gpt-5.6-solAvailable
- Declared context
- 1M
- Known input modality
- Text
- Declared input / 1M
- See billing
- Declared output / 1M
- See billing
- Declared context
- 33K
- Known input modality
- Text
- Declared input / 1M
- $0.02
- Declared output / 1M
- $0.02
Compatible by design
Bring the client you already use.
Chat Completions
OpenAI-compatible requests and Server-Sent Events.
Responses
OpenAI Responses input items, output events, and streaming; image_generation tools are not enabled.
Images
OpenAI-compatible image generation, JSON or multipart edits, variations, and streams.
Messages
Anthropic-compatible messages and event streams.
Embeddings
Normalized vector responses across supported endpoints.