fix: update Fireworks model metadata for accounts/fireworks/models/gpt-oss-20b

[github-actions]

fix: update Fireworks model metadata for accounts/fireworks/models/gpt-oss-20b

Closes #684

Source issue: #684

Summary

Field	Value
Provider	fireworks
Primary model	accounts/fireworks/models/gpt-oss-20b
Changed models	accounts/fireworks/models/gpt-oss-20b
Added models	None
Updated models	accounts/fireworks/models/gpt-oss-20b
Verification sources	1

Verified metadata

Model	Display name	Parent	Providers	Format	Flavor	Token limits	Pricing	Lifecycle
accounts/fireworks/models/gpt-oss-20b	OpenAI GPT-OSS (20B)		fireworks	openai	chat	input=131072, output=131072	in/out=0.07/0.3 per 1M; cache read=0.035 per 1M	reasoning=true

Verification notes

Verification

• Source 1: Fireworks AI serverless pricing docs (https://docs.fireworks.ai/serverless/pricing) — lists OpenAI GPT OSS 20B at $0.07 input / $0.30 output / $0.035 cached input per 1M tokens (Standard tier, on-demand).
  • Verified fields: input_cost_per_mil_tokens (0.07), output_cost_per_mil_tokens (0.30), input_cache_read_cost_per_mil_tokens (0.035)
• sync_models cross-check: The LiteLLM model_prices_and_context_window_backup.json catalog does not contain an entry for fireworks_ai/gpt-oss-20b or any Fireworks-provider GPT-OSS 20B variant. No sync_models comparison is possible for this model's pricing. The only GPT-OSS entry in sync_models is azure_ai/gpt-oss-120b which is a different model on a different provider.
• Token limits: The existing catalog values of max_input_tokens: 131072 and max_output_tokens: 131072 are retained as-is since the issue only concerns pricing and these are consistent with other GPT-OSS entries.
• Fields not changed: format, flavor, displayName, reasoning, max_input_tokens, max_output_tokens, available_providers — all remain at their current catalog values. No official source indicates these have changed.
• Fields not applicable: parent (this is not a dated snapshot or variant of another model), supported_regions (Fireworks models do not use region metadata), deprecated/deprecation_date (model is active).

sync_models vs proposed update

sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.

Model	Field	Proposed update	sync_models	sync_models source models
accounts/fireworks/models/gpt-oss-20b	input_cost_per_mil_tokens	0.07	0.05	fireworks_ai/accounts/fireworks/models/gpt-oss-20b
accounts/fireworks/models/gpt-oss-20b	output_cost_per_mil_tokens	0.3	0.2	fireworks_ai/accounts/fireworks/models/gpt-oss-20b
accounts/fireworks/models/gpt-oss-20b	input_cache_read_cost_per_mil_tokens	0.035	n/a	fireworks_ai/accounts/fireworks/models/gpt-oss-20b

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
ai-proxy	Ready	Preview, Comment	May 30, 2026 4:29pm