Open Models

Use auto, version-tracking aliases, fast tiers, or pinned Fireworks open models in coding workflows.

Use a Fireworks open model directly when you want Fireworks to serve every turn. Choosing a specific open model requires an Enterprise plan. On Pro and Team, use auto, which still routes turns to open models.

​

Start with auto

auto picks a model for each new user turn. Nexus CLI makes it the default in every harness.

nexus claude

After you restart Claude Code, Auto is the default model in /model, and no --model flag is required.

​

Choose a family, tier, or version

On Enterprise, use --model when you want a specific family, tier, or version:

nexus claude --model glm-latest

Kind	Example IDs	Behavior
Latest	kimi-latest, glm-latest, deepseek-flash-latest	Tracks the current version in the model family
Fast	kimi-fast-latest, glm-fast-latest	Favors lower latency at a higher token price
Pinned	kimi-k3, glm-5p3, glm-5p3-flash	Stays on the named version

Prefer *-latest unless you need a pinned version. Aliases can move to newer models or be retired, so check the current list before you hard-code one.

​

Find a model ID

List current models and aliases with Nexus CLI:

nexus model list
nexus model list --search glm

Without Nexus CLI, call the serverless models endpoint:

curl "https://api.fireworks.ai/v1/serverless/models?use_cases=coding" \
  -H "Authorization: Bearer $FIREWORKS_API_KEY"

Nexus Auto has its own setting for which models it can use.

​

Check image support

glm-latest and glm-fast-latest are text-only. If an image reaches a text-only model in Claude Code, use /rewind, then switch to a vision-capable model such as Kimi or glm-5p3-flash.

​

Pricing

Open models bill to your Fireworks account at Serverless Pricing. Per-session estimates and account usage are in Usage and Cost. US-only model IDs, the endpoint, and pricing are in US-only Serverless.