← directory / providers / fireworks
Fireworks AI
cloud3
models served
FIREWORKS_API_KEY
auth
api.fireworks.ai/inference/v1
base url
Open-weights serving; OpenAI-compatible. docs →
01Request template
Every model below is invoked with this shape — swap in the provider model ID from the table.
curl https://api.fireworks.ai/inference/v1/chat/completions \
-H "Authorization: Bearer $FIREWORKS_API_KEY" \
-H "content-type: application/json" \
-d '{
"model": "{{MODEL_ID}}",
"messages": [{"role": "user", "content": "Hello, world"}]
}'02Models served · newest first
| Model | Provider model ID | In $/M | Out $/M | Context |
|---|---|---|---|---|
| gpt-oss-120bOpenAI | accounts/fireworks/models/gpt-oss-120b | — | — | 131K |
| Qwen3 Coder 480BAlibaba Qwen | accounts/fireworks/models/qwen3-coder-480b-a35b-instruct | — | — | 262K |
| Qwen3 235B-A22BAlibaba Qwen | accounts/fireworks/models/qwen3-235b-a22b-instruct-2507 | — | — | 262K |