summaryrefslogtreecommitdiff
path: root/internal/provider/anthropic/pricing.go
diff options
context:
space:
mode:
authorClaude Sonnet 5 <noreply@anthropic.com>2026-07-03 09:03:01 +0000
committerClaude Sonnet 5 <noreply@anthropic.com>2026-07-03 09:03:13 +0000
commite38f673edc7428c0c836c39f40707cb681defb14 (patch)
tree97a704b2d83b9d572ae67d057315a6781ddf1470 /internal/provider/anthropic/pricing.go
parentbbd58e8d77f7c996add29b69f600e835a922542e (diff)
feat(provider): add native Anthropic Messages API adapter (Phase 2)
Adds internal/provider/anthropic, the first genuinely new provider.Provider implementation on top of Phase 1's provider-neutral tool-use loop, alongside (not replacing) the existing Docker/CLI-subprocess ContainerRunner path for the "claude" agent type: - internal/provider/anthropic: translates the neutral ChatRequest/ChatResponse shape to/from Anthropic's Messages API content-block format (system as a top-level field, tool_use/tool_result blocks, no "tool" role -- tool results become user-role messages), with a per-model-prefix pricing table for CostUSD - internal/retry: IsRateLimitError additively extended to recognize Anthropic's rate_limit_error/overloaded_error/529 shapes - internal/config: RunnersConfig.Anthropic/AnthropicEnabled() gate - internal/cli/serve.go, run.go: register runners["anthropic"] as a NativeRunner when [providers.anthropic].api_key is set and enabled -- tracked as a distinct executions.agent="anthropic" budget bucket, separate from the CLI-subprocess "claude" runner even though both bill the same Anthropic account go build/vet/test -race all pass. No live Anthropic API key is available in this environment, so verification is via fake-httptest-server adapter tests (12 cases, incl. multi-turn tool_result round-trip and rate-limit error matching) plus a Pool/NativeRunner routing test proving agent.type: "anthropic" actually reaches the new provider. Live end-to-end verification against the real API is a follow-up once a key is configured. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs
Diffstat (limited to 'internal/provider/anthropic/pricing.go')
-rw-r--r--internal/provider/anthropic/pricing.go70
1 files changed, 70 insertions, 0 deletions
diff --git a/internal/provider/anthropic/pricing.go b/internal/provider/anthropic/pricing.go
new file mode 100644
index 0000000..c5b5298
--- /dev/null
+++ b/internal/provider/anthropic/pricing.go
@@ -0,0 +1,70 @@
+package anthropic
+
+import "strings"
+
+// modelPrice is USD cost per million tokens for one model (or model family
+// prefix).
+type modelPrice struct {
+ InputPerMTok float64
+ OutputPerMTok float64
+}
+
+// pricingTable maps a model-name *prefix* to its per-million-token pricing.
+// Keyed by prefix (rather than exact model string) so dated/versioned model
+// IDs (e.g. "claude-3-5-sonnet-20241022") still resolve without needing an
+// entry per snapshot. Edit this table as Anthropic's pricing or model
+// lineup changes — it intentionally has no other logic attached.
+//
+// Prices below are cached from training/skill data as of mid-2026 and are
+// not fetched live; verify against https://platform.claude.com/docs/en/pricing
+// before relying on them for real billing decisions.
+var pricingTable = map[string]modelPrice{
+ // Claude Fable 5 / Mythos family (most capable, most expensive tier).
+ "claude-fable-5": {InputPerMTok: 10.00, OutputPerMTok: 50.00},
+ "claude-mythos-5": {InputPerMTok: 10.00, OutputPerMTok: 50.00},
+ "claude-mythos-preview": {InputPerMTok: 10.00, OutputPerMTok: 50.00},
+
+ // Opus tier.
+ "claude-opus-4-8": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4-7": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4-6": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4-5": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4-1": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4-0": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-opus-4": {InputPerMTok: 5.00, OutputPerMTok: 25.00},
+ "claude-3-opus": {InputPerMTok: 15.00, OutputPerMTok: 75.00},
+
+ // Sonnet tier.
+ "claude-sonnet-5": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-sonnet-4-6": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-sonnet-4-5": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-sonnet-4-0": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-sonnet-4": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-3-7-sonnet": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-3-5-sonnet": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+ "claude-3-sonnet": {InputPerMTok: 3.00, OutputPerMTok: 15.00},
+
+ // Haiku tier.
+ "claude-haiku-4-5": {InputPerMTok: 1.00, OutputPerMTok: 5.00},
+ "claude-3-5-haiku": {InputPerMTok: 0.80, OutputPerMTok: 4.00},
+ "claude-3-haiku": {InputPerMTok: 0.25, OutputPerMTok: 1.25},
+}
+
+// defaultPricing is used for unrecognized models rather than erroring —
+// Sonnet-tier pricing is a reasonable mid-point default.
+var defaultPricing = modelPrice{InputPerMTok: 3.00, OutputPerMTok: 15.00}
+
+// pricingFor returns the per-million-token input/output pricing for model,
+// matching the longest pricingTable prefix that model starts with. Falls
+// back to defaultPricing for unrecognized models.
+func pricingFor(model string) (inputPerMTok, outputPerMTok float64) {
+ price := defaultPricing
+ bestLen := -1
+ for prefix, p := range pricingTable {
+ if len(prefix) > bestLen && strings.HasPrefix(model, prefix) {
+ bestLen = len(prefix)
+ price = p
+ }
+ }
+ return price.InputPerMTok, price.OutputPerMTok
+}