Tooluck logoTooluck
SKILL.md

fireworks-inference

Agent skill fromLeanmcp/gateway-skills

Run inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"

How to install fireworks-inference

install fireworks-inference
# install the gateway-skills pack with the skills CLI
npx skills add Leanmcp/gateway-skills

# or add only this skill to Claude Code: copy the folder

skills/fireworks-inference/

# into

~/.claude/skills/fireworks-inference/ (all projects)

.claude/skills/fireworks-inference/ (one project)

skills/fireworks-inference/SKILL.md

MITFull file
1# Fireworks inference
2
3Inference on Fireworks is three independent choices, and nearly every confusing
4failure is one of them being wrong while you debug another:
5
6```
7 TRANSPORT ROUTE MODEL
8 ───────── ───── ─────
9 raw HTTP direct Fireworks serverless
10 openai SDK × api.fireworks.ai × accounts/fireworks/models/<slug>
11 litellm Leanmcp gateway dedicated deployment
12 aigateway.leanmcp.com accounts/<acct>/deployments/<id>
13```
14
15This skill's job is to let you isolate them one at a time instead of guessing.
16
17## The route matrix — memorize this
18
19| | base URL | key |
20| --- | --- | --- |
21| **direct Fireworks** | `https://api.fireworks.ai/inference/v1` | `FIREWORKS_API_KEY` |
22| **Leanmcp gateway** | `https://aigateway.leanmcp.com/v1/fireworks` | `LEANMCP_API_KEY` |
23
24Same models, same request and response shape. **Only the endpoint and the key
25change** — which is why routing should be a flag, never a code path. Note the
26key swap: through the gateway you send your *Leanmcp* key; the gateway holds the
27Fireworks credential.
28
29Gateway keys at <https://app.leanmcp.com/api-keys> (top up credits first at
30<https://app.leanmcp.com/billing>); every request then shows up at
31<https://app.leanmcp.com/observability>.
32
33## Start here
34
35**Something is broken.** Climb the ladder in
36…

Excerpt shown under the repository's MIT license.

More skills in gateway-skills

Keep exploring

Similar skill repositories

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates