Model fleet
Per-model reference generated from the live Riven gateway catalog. Every entry is callable through the API with the same key.
The gateway serves 75 live models — three on the on-prem fleet and 33 across nine cloud providers. The 65 entries below include the alias IDs that resolve onto those models, which is why the catalog is longer than the model count. See Riven Ultra Router for the mapping.
Riven (on-prem and routed aliases) 22
| Model ID | Tier | Capabilities |
|---|---|---|
| glm-5.2 | frontier | chat, reasoning |
| nomic-embed-text | embed | embeddings |
| qwen3.6-35b-a3b-fp8 | frontier | chat, reasoning |
| riven-best | all plans | chat, auto-routing |
| riven-code | all plans | chat, code |
| riven-core | core | chat |
| riven-embed | all plans | embeddings |
| riven-fast | fast | chat, fast |
| riven-image | all plans | image |
| riven-instant | instant | chat, fast |
| riven-max | max | chat, reasoning |
| riven-pro | pro | chat, reasoning |
| riven-research | research | chat, reasoning, web, web_search, citations |
| riven-vision | vision | chat, vision |
| riven-agent | all plans | chat |
| riven-chat-lg | all plans | chat |
| riven-chat-md | standard | chat |
| riven-chat-sm | standard | chat |
| riven-chat-xl | all plans | chat |
| riven-embed-fast | all plans | embeddings |
| riven-reason | reason | chat, reasoning |
| rvn-assistant-v2 | custom | chat |
OpenAI 10
| Model ID | Tier | Capabilities |
|---|---|---|
| gpt-4o | core | chat, reasoning |
| gpt-4o-mini | fast | chat, fast |
| gpt-5 | core | chat, reasoning |
| gpt-5.4-mini | fast | chat, fast |
| gpt-5.4-nano | instant | chat, fast |
| gpt-5.5 | pro | chat, reasoning |
| gpt-5.6 | pro | chat, reasoning |
| gpt-5.6-luna | fast | chat, reasoning, fast |
| gpt-5.6-sol | pro | chat, reasoning |
| gpt-5.6-terra | core | chat, reasoning |
NVIDIA NIM 9
| Model ID | Tier | Capabilities |
|---|---|---|
| deepseek-ai/deepseek-v4-flash | paid plans | chat |
| deepseek-ai/deepseek-v4-pro | paid plans | chat |
| z-ai/glm-5.2 | paid plans | chat |
| moonshotai/kimi-k2.6 | paid plans | chat |
| meta/llama-4-maverick-17b-128e-instruct | paid plans | chat |
| nvidia/nemotron-3-super-120b-a12b | paid plans | chat |
| nvidia/nemotron-3-ultra-550b-a55b | paid plans | chat |
| nvidia/llama-3.3-nemotron-super-49b-v1.5 | paid plans | chat |
| qwen/qwen3.5-397b-a17b | paid plans | chat |
Mistral 7
| Model ID | Tier | Capabilities |
|---|---|---|
| codestral-2508 | fast | chat, code |
| mistral-large-2512 | core | chat |
| mistral-large-latest | core | chat |
| mistral-medium-3 | fast | chat, fast |
| mistral-medium-3.5 | core | chat, reasoning |
| mistral-medium-latest | core | chat |
| mistral-small-latest | instant | chat, fast |
Anthropic 5
| Model ID | Tier | Capabilities |
|---|---|---|
| claude-fable-5 | max | chat, reasoning |
| claude-haiku-4-5 | fast | chat, fast |
| claude-opus-4-7 | pro | chat, reasoning |
| claude-opus-4-8 | pro | chat, reasoning |
| claude-sonnet-4-6 | core | chat, reasoning |
Moonshot 5
| Model ID | Tier | Capabilities |
|---|---|---|
| kimi-k2.5 | core | chat |
| kimi-k2.6 | core | chat |
| kimi-k2.7-code | core | chat, reasoning |
| kimi-k2.7-code-highspeed | core | chat, reasoning |
| kimi-k3 | pro | chat |
Perplexity 3
| Model ID | Tier | Capabilities |
|---|---|---|
| sonar | research | chat, search, citations |
| sonar-pro | research | chat, web_search, citations |
| sonar-reasoning-pro | research | chat, reasoning, web_search, citations |
Groq 2
| Model ID | Tier | Capabilities |
|---|---|---|
| llama-3.1-8b-instant | instant | chat, fast |
| llama-3.3-70b-versatile | fast | chat |
Fireworks 1
| Model ID | Tier | Capabilities |
|---|---|---|
| gpt-oss-120b | fast | chat |
Cerebras 1
| Model ID | Tier | Capabilities |
|---|---|---|
| zai-glm-4.7 | instant | chat |