feat(code): add Fireworks built-in pricing overrides

[Mason Daugherty (mdrxy)]

Fireworks cost estimates for three new serverless models now fall back to built-in pricing instead of showing $0: accounts/fireworks/models/kimi-k3 ($3.00 / $0.30 / $15.00), accounts/fireworks/models/inkling ($1.00 / $0.17 / $4.05), and accounts/fireworks/models/deepseek-v4-flash-0731 ($0.14 / $0.028 / $0.28) per 1M input / cached-input / output tokens.

---

These models shipped on Fireworks serverless without genai-prices coverage, so estimate_cost returned None for them and those requests dropped out of the session total. This adds a fireworks provider block to bundled_prices.json (#5304's fallback-on-miss override), priced from each model's pricing page: Kimi K3, Inkling, DeepSeek-V4-Flash-0731.

This is a stopgap. Every entry carries price_comments: "Stopgap pending pydantic/genai-prices#550" per the bundled_prices.README.md policy, enforced by test_every_bundled_override_entry_is_priced_and_links_upstream. The upstream addition is open at pydantic/genai-prices#550; once that merges and the hourly auto-update picks it up, these entries go inert automatically (upstream always wins on a primary-catalog hit) and can be removed as housekeeping.

Rates per 1M tokens (input / cached input / output):

Model	Slug	Input	Cache	Output
Kimi K3	accounts/fireworks/models/kimi-k3	3.00	0.30	15.00
Inkling	accounts/fireworks/models/inkling	1.00	0.17	4.05
DeepSeek-V4-Flash-0731	accounts/fireworks/models/deepseek-v4-flash-0731	0.14	0.028	0.28

Notes:

• deepseek-v4-flash-0731 is the official release of DeepSeek-V4-Flash at the same rates as the existing deepseek-v4-flash preview.
• All other Fireworks models with published serverless prices are already covered by upstream fireworks.yml, so no other entries are needed.

[open-swe]

✅ Open SWE Review: No issues found

Open SWE reviewed this PR and found no potential bugs to report.

Open in Web • View Open SWE trace

[Mason Daugherty (mdrxy)]

No longer needed following pydantic/genai-prices#552