Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions evalboard/lib/pricing.generated.ts
Original file line number Diff line number Diff line change
Expand Up @@ -72,10 +72,13 @@ export const PRICING: Record<string, Pricing> = {
"gpt-5.6-luna": { inputPerMTok: 0.2, outputPerMTok: 1.2, cacheWritePerMTok: 0.25, cacheReadPerMTok: 0.02 },
"gpt-5.6-sol": { inputPerMTok: 4.0, outputPerMTok: 20.0, cacheWritePerMTok: 5.0, cacheReadPerMTok: 0.4 },
"gpt-5.6-terra": { inputPerMTok: 2.0, outputPerMTok: 12.0, cacheWritePerMTok: 2.5, cacheReadPerMTok: 0.2 },
"gpt-6-1-sol": { inputPerMTok: 2.0, outputPerMTok: 10.0, cacheWritePerMTok: 2.5, cacheReadPerMTok: 0.1 },
"gpt-6-1-terra": { inputPerMTok: 1.0, outputPerMTok: 5.0, cacheWritePerMTok: 1.25, cacheReadPerMTok: 0.05 },
"gpt-6-astra": { inputPerMTok: 10.0, outputPerMTok: 50.0, cacheWritePerMTok: 12.5, cacheReadPerMTok: 1.0 },
"gpt-6-luna": { inputPerMTok: 0.1, outputPerMTok: 0.5, cacheWritePerMTok: 0.125, cacheReadPerMTok: 0.01 },
"gpt-6-sol": { inputPerMTok: 2.0, outputPerMTok: 10.0, cacheWritePerMTok: 2.5, cacheReadPerMTok: 0.2 },
"gpt-6.1-sol": { inputPerMTok: 2.0, outputPerMTok: 10.0, cacheWritePerMTok: 2.5, cacheReadPerMTok: 0.1 },
"gpt-6.1-terra": { inputPerMTok: 1.0, outputPerMTok: 5.0, cacheWritePerMTok: 1.25, cacheReadPerMTok: 0.05 },
"jev-1.13.0": { inputPerMTok: 0.042, outputPerMTok: 0.0, cacheWritePerMTok: 0.042, cacheReadPerMTok: 0.0 },
"jev-latest": { inputPerMTok: 0.042, outputPerMTok: 0.0, cacheWritePerMTok: 0.042, cacheReadPerMTok: 0.0 },
"kimi-k2-7-code": { inputPerMTok: 0.95, outputPerMTok: 4.0, cacheWritePerMTok: 0.0, cacheReadPerMTok: 0.19 },
Expand Down
10 changes: 7 additions & 3 deletions src/coder_eval/pricing.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@
https://developers.openai.com/api/docs/pricing,
https://ai.google.dev/gemini-api/docs/pricing, and OpenRouter's live
``/api/v1/models`` (every row re-verified 2026-10-07, except the Bedrock
open-weight block: AWS publishes no eu-north-1 figures for those three).
open-weight block: AWS publishes no eu-north-1 figures for those three; the
GPT-6.1 Terra rows and the Delegate GPT-6.1 rows were added 2026-11-18).

SSOT for rates on both halves of the repo: ``evalboard/lib/pricing.generated.ts`` is
generated from it by ``make pricing-mirror`` and guarded by CE065. Never hand-edit the
Expand Down Expand Up @@ -51,6 +52,8 @@ class ModelPricing:
"gpt-5-6-sol": ModelPricing(5.0, 30.0, 6.25, 0.50),
"gpt-5-6-terra": ModelPricing(2.0, 12.0, 2.50, 0.20),
"gpt-5-6-luna": ModelPricing(0.20, 1.20, 0.25, 0.02),
"gpt-6-1-sol": ModelPricing(2.0, 10.0, 2.50, 0.10),
"gpt-6-1-terra": ModelPricing(1.0, 5.0, 1.25, 0.05),
"kimi-k2-7-code": ModelPricing(0.95, 4.0, 0.0, 0.19),
"glm-5-3-flash": ModelPricing(0.15, 0.50, 0.0, 0.03),
}
Expand Down Expand Up @@ -122,11 +125,12 @@ class ModelPricing:
"gpt-5.6-sol": ModelPricing(4.0, 20.0, 5.0, 0.40),
"gpt-5.6-terra": ModelPricing(2.0, 12.0, 2.50, 0.20),
"gpt-5.6-luna": ModelPricing(0.20, 1.20, 0.25, 0.02),
# CAVEAT: flat rate; GPT-6's >272K-input tier (2x input / 1.5x output) is not modelled and reads low.
# CAVEAT: flat rate; GPT-6/6.1's >272K-input tier (2x input / 1.5x output) is not modelled and reads low.
"gpt-6-astra": ModelPricing(10.0, 50.0, 12.50, 1.00),
"gpt-6.1-sol": ModelPricing(2.0, 10.0, 2.50, 0.10),
"gpt-6-sol": ModelPricing(2.0, 10.0, 2.50, 0.20),
"gpt-6-luna": ModelPricing(0.10, 0.50, 0.125, 0.01),
"gpt-6.1-sol": ModelPricing(2.0, 10.0, 2.50, 0.10),
"gpt-6.1-terra": ModelPricing(1.0, 5.0, 1.25, 0.05),
# Keyed on the literal ids ListModels returns. No cache-write fee, so
# cache_write == input (unused). CAVEAT: Pro's >200K-token tier costs more, so
# a very-large-context run reads LOW. List rates; 3.6-3.8 Flash are discounted
Expand Down
2 changes: 2 additions & 0 deletions tests/test_delegate_agent_registration.py
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,8 @@
"gpt-5-6-sol": (5.0 + 30.0, 6.25),
"gpt-5-6-terra": (2.0 + 12.0, 2.50),
"gpt-5-6-luna": (0.20 + 1.20, 0.25),
"gpt-6-1-sol": (2.0 + 10.0, 2.50),
"gpt-6-1-terra": (1.0 + 5.0, 1.25),
"kimi-k2-7-code": (0.95 + 4.0, 0.0),
"glm-5-3-flash": (0.15 + 0.50, 0.0),
}
Expand Down
Loading