Model Catalog

Available models, capabilities, and pricing across all providers.

Listing Models

Fetch all available models for your tenant:

curl https://api.brainstormrouter.com/v1/models \
  -H "Authorization: Bearer br_live_..."

Models are available based on which provider API keys are configured for your tenant.

Model ID Format

BrainstormRouter accepts models in several formats:

Format	Example	Description
`provider/model`	`anthropic/claude-sonnet-5`	Explicit provider + model
Bare model ID	`claude-sonnet-5`	Auto-resolved to the right provider
Alias	`fast`, `smart`	Tenant-defined alias (via `/v1/aliases`)
`auto`	`auto`	Intelligent routing based on request complexity

Providers

The registered catalog is 55 models across 9 providers. GET /v1/models is always the live source of truth; the tables below mirror it (pricing is USD per million tokens).

Anthropic

Model	$/M in	$/M out	Vision	Tools	Reasoning
`claude-fable-5-1`	10.00	50.00	Yes	Yes	Yes
`claude-opus-5-5`	4.00	20.00	Yes	Yes	Yes
`claude-opus-5`	5.00	25.00	Yes	Yes	Yes
`claude-sonnet-5`	2.00	10.00	Yes	Yes	Yes
`claude-fable-5`	10.00	50.00	Yes	Yes	Yes
`claude-opus-4-8`	5.00	25.00	Yes	Yes	Yes
`claude-opus-4-7`	5.00	25.00	Yes	Yes	Yes
`claude-opus-4-6`	5.00	25.00	Yes	Yes	Yes
`claude-sonnet-4-6`	3.00	15.00	Yes	Yes	Yes
`claude-haiku-4-5-20251001`	1.00	5.00	Yes	Yes	Yes

OpenAI

Model	$/M in	$/M out	Vision	Tools	Reasoning
`gpt-6-astra`	10.00	50.00	Yes	Yes	Yes
`gpt-6-sol`	2.00	10.00	Yes	Yes	Yes
`gpt-6-luna`	0.10	0.50	Yes	Yes	Yes
`gpt-5.6-sol`	4.00	20.00	Yes	Yes	Yes
`gpt-5.6-terra`	2.00	12.00	Yes	Yes	Yes
`gpt-5.6-luna`	0.20	1.20	Yes	Yes	Yes
`gpt-5.5`	5.00	30.00	Yes	Yes	Yes
`gpt-4.1`	2.00	8.00	Yes	Yes	No
`gpt-4.1-mini`	0.40	1.60	Yes	Yes	No
`gpt-4.1-nano`	0.10	0.40	Yes	Yes	No
`gpt-4o`	2.50	10.00	Yes	Yes	No
`gpt-4o-mini`	0.15	0.60	Yes	Yes	No
`o3`	2.00	8.00	Yes	Yes	Yes
`o3-mini`	1.10	4.40	No	Yes	Yes
`o4-mini`	1.10	4.40	Yes	Yes	Yes

Embeddings: text-embedding-3-small (0.02/M) and text-embedding-3-large (0.13/M).

Google

Model	$/M in	$/M out
`gemini-3.8-flash`	0.75	3.75
`gemini-3.7-flash`	0.75	3.75
`gemini-3.6-flash`	0.75	3.75
`gemini-3.5-flash`	1.50	9.00
`gemini-3.5-flash-lite`	0.30	2.50
`gemini-3.1-flash-lite`	0.25	1.50
`gemini-2.5-pro`	1.25	10.00
`gemini-2.5-flash`	0.30	2.50
`gemini-2.5-flash-lite`	0.075	0.30

Gemini 3.6–3.8 Flash are at launch pricing through 2026-12-31, then $1.50 / $7.50.

DeepSeek

Model	$/M in	$/M out
`deepseek-v4-pro`	0.66	1.98
`deepseek-v4-flash`	0.15	0.60

DeepSeek bills by time of day: peak hours (01:00–04:00 and 06:00–10:00 UTC, Monday–Friday) cost 2x the off-peak rates listed here. BrainstormRouter currently reports the off-peak rate.

xAI

Model	$/M in	$/M out
`grok-4.7`	2.00	6.00
`grok-4.6`	2.00	6.00
`grok-4.5`	2.00	6.00
`grok-4.3`	1.25	2.50
`grok-4.20`	1.25	2.50

Perplexity

Model	$/M in	$/M out
`sonar-pro`	3.00	15.00
`sonar-reasoning-pro`	2.00	8.00
`sonar-deep-research`	2.00	8.00
`sonar`	1.00	1.00

Moonshot

Model	$/M in	$/M out
`kimi-k3`	3.00	15.00
`kimi-k2.6`	0.60	2.50
`kimi-k2.5`	0.60	2.50

Groq

Model	$/M in	$/M out
`openai/gpt-oss-120b`	0.15	0.60
`openai/gpt-oss-20b`	0.075	0.30
`qwen/qwen3.8-27b`	0.80	4.00

Z.ai

Model	$/M in	$/M out
`glm-5.2`	1.40	4.40
`glm-5`	1.40	4.40

Bring Your Own Key

Add any provider's API key via the dashboard or the /v1/providers endpoint; models become available in your tenant's catalog once the key is configured.

Capabilities Query

Check if a model supports specific features before sending requests:

curl https://api.brainstormrouter.com/v1/models \
  -H "Authorization: Bearer br_live_..." | \
  jq '.data[] | select(.id == "anthropic/claude-sonnet-5")'

Pricing

Pricing is per million tokens. Check the latest pricing via the OpenAPI spec:

curl https://api.brainstormrouter.com/openapi.json | jq .

Or view actual spend via the usage endpoints:

curl https://api.brainstormrouter.com/v1/usage/summary?groupBy=model \
  -H "Authorization: Bearer br_live_..."