* fix(pricing): add undated azure aliases for gpt-audio-mini and gpt-realtime-mini
Azure deployments are commonly created against the undated model name,
and the cost-tracking docs say to set base_model to azure/<model> — but
only the dated -2025-10-06 entries existed for these two models (the
openai provider has undated aliases for both). base_model:
azure/gpt-audio-mini therefore resolved to nothing and, depending on the
fallback path, text tokens billed at $0 while audio tokens billed fine.
Mirror the -2025-10-06 entries as undated aliases, exactly like the
undated openai entries mirror their newest dated variant.
Fixes#33170
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* test(pricing): assert undated azure audio aliases exactly mirror their dated entries
Review follow-up: COST_FIELDS missed realtime-specific cost keys
(cache_creation_input_audio_token_cost, cache_read_input_token_cost,
input_cost_per_image). Full-entry equality catches drift on every field.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(pricing): mirror updated mode=realtime on the undated gpt-realtime-mini alias
Upstream changed the dated entry's mode from chat to realtime after this
branch was cut; the undated alias must stay a byte-for-byte mirror.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(pricing): mirror the new deprecation_date onto the undated gpt-audio-mini alias
* test(pricing): use shared local_model_cost_map fixture so get_model_info's lru_cache never crosses maps
---------
Co-authored-by: Mihidum Hettiyahandi <55163074+mihidumh@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
OpenAI's model page for gpt-5.6 serves the GPT-5.6 Sol page and states
that the gpt-5.6 alias routes requests to GPT-5.6 Sol, so the alias bills
at Sol's rates. The registry entry was left on the pre-cut rates while
gpt-5.6-sol took the cut, overbilling gpt-5.6 callers by 25 percent on
input and 50 percent on output.
All 23 cost fields on gpt-5.6 now match gpt-5.6-sol, and a regression
test pins the two entries together so they cannot drift again.
The three lite-image keys landed on the deploy branch separately while this
branch was open, so merging left every key defined twice in both price maps.
The merge is clean as text and the file still parses, but JSON keeps the last
occurrence of a repeated key, so the first copy's supported_endpoints,
supported_modalities and supports_system_messages were being dropped without
any error.
Each key is now one entry, placed next to its gemini-3.1-flash-image sibling
rather than at the end of the file.
supports_reasoning goes to false on all three, matching every other Gemini
image model. Leaving it off is not neutral: _supports_factory falls through to
the vertex_ai provider config, which answers true, and reasoning_effort then
gets forwarded to an image endpoint that rejects it. That was fixed for the
rest of the family in 75dd70a678 and these entries had drifted back.
Also fills in what the entries were missing against Google's published
pricing: the Vertex implicit cache read rate, batch rates on the Vertex
routes, and the pdf/video input flags.
The two overlapping test files are folded into one, and the price map suite
grows a duplicate-key guard so the next clean-but-lossy merge fails loudly.
GPT-5.6 Sol, Terra and Luna reached the bedrock-runtime data plane on
2026-08-17, separately from the existing bedrock-mantle path. On runtime
they are served only through cross-region inference profiles, so
bedrock/us.openai.gpt-5.6-* had no cost map entry and fell through to the
Invoke route, which rewrites the token cap to max_tokens and is rejected
as unsupported_parameter on both /v1/chat/completions and /v1/responses.
Register the Geo and Global profiles as bedrock_converse so routing
reaches Converse, which AWS documents and serves for these models, and
price each profile from its own published rate table. No bare key: the
control plane reports inferenceTypesSupported INFERENCE_PROFILE with no
on-demand throughput, so a bare id is not invocable.
Declare the published cache-read and cache-write rates. Bedrock rejects
an explicit cachePoint block for these models, so supports_prompt_caching
stays off, but it caches long prefixes implicitly and reports the cache
tokens in usage either way. Without the cost fields a cache-read turn
bills only its uncached tokens: measured against live Bedrock, a
15609-token cached prefix came to $0.000176 instead of $0.00876095.
Clients that resend a long prefix every turn are the worst affected.
Reasoning stays unadvertised. Converse rejects the Anthropic-shaped
thinking block LiteLLM sends for reasoning_effort; the shape these models
accept is additionalModelRequestFields {"reasoning": {"effort": ...}},
which needs a transform change tracked by #34105. Advertising it without
that change is what made the earlier attempt in #37307 fail.
Applies the review suggestions. The cost map now carries the rates published on
https://scx.ai/pricing, GLM-5.2 at 0.61 in, 0.22 cached, 1.98 out and
Qwen3.8-Max at 1.65 in, 0.21 cached, 4.99 out per million tokens, and cites that
page as the source rather than a third party gateway. The provider link is
corrected to https://docs.litellm.ai/docs/providers/scx_ai to match the page
that shipped as scx_ai.md. Both the primary files and their backup mirrors are
updated.
Resolves the three conflicts against the JSON provider registry refactor. The
hardcoded api.scx.ai base-url branch in get_llm_provider_logic.py is dropped in
favour of the generic JSONProviderRegistry.get_by_base_url lookup, which reads
the same base_url and api_key_env from providers.json and additionally honours
an explicitly passed api_key. constants.py and types/utils.py keep both the
cognition and scx-ai entries added on either side.
The cost map shipped cognition/swe-1.7 at $2.50 in / $12.50 out per million with
$1.00 cache reads. Those are the Lightning numbers. Cognition's own model list at
https://docs.devin.ai/desktop/models has uid swe-1-7 at $0.50 / $2.50 with $0.20
cache reads, and uid swe-1-7-lightning at $2.50 / $12.50 with $1.00 cache reads,
so every swe-1.7 call has been costed at 5x since the entry landed.
swe-1.7 now carries the standard rates and the Lightning tier gets its own entry,
in both cost map copies. The source field on both moves to the desktop models page,
which is the one that lists both tiers.
The swe-1.7 rates were briefly lowered to the standard tier. The docs page
records the API-served swe-1.7 as the Cerebras-served Lightning tier, so put
the matching rates back rather than have the cost map and the docs disagree.
Cognition also answers /v1/responses through the chat-completions bridge, the
same as every other provider in the JSON registry, so the endpoints support
matrix should say so instead of under-declaring it.
The swe-1.7 rates were carried over from the closed prior attempt and
match SWE-1.7 Lightning, 5x the SWE-1.7 Max and Medium rates the vendor
publishes. swe-1.6 was already on the standard tier, so the two entries
disagreed with each other. Both now read 0.5 in, 2.5 out, 0.2 cached per
million tokens.
Also drops the redundant registry comment in constants.py.
Cognition serves an OpenAI-compatible /v1/chat/completions endpoint, so it has been onboarded as
custom_llm_provider: openai. That books its traffic as OpenAI, which means OpenAI-specific cost
discounts and provider-level reporting apply to it.
Registers cognition through the JSON provider registry: a providers.json entry with
COGNITION_API_KEY and COGNITION_API_BASE, LlmProviders.COGNITION, the constants.py provider lists,
cost map entries for swe-1.6 and swe-1.7, the provider endpoints matrix, the dashboard provider
fields, and tests. JSON providers can now also be resolved from their base url alone, so an
api_base pointing at a known provider no longer falls through to an unresolved provider.
The edit model is reached through the image generation path with fal's
image_urls param; /v1/images/edits is not wired for fal_ai and errors.
Point supported_endpoints at /v1/images/generations and say so in the
entry notes.
OpenAI documents computer_use as a supported tool for Daybreak Blue and its
default snapshot gpt-5.6-sol, but neither entry carried supports_computer_use.
Sibling gpt-5.6-cyber and daybreak-red-latest already set it, so /model/info
and the capability gates reported blue as unable to use computer tools.
The gap came in with the source PR rather than the consolidation: #37029 sets
the flag on cyber and red only. Pinned by a new metadata test covering the
daybreak family and the blue alias agreeing with its snapshot.
Route fal.ai's openai/gpt-image-2 endpoints through a dedicated transformation that maps OpenAI image params (n, size, quality, output_format) into fal's schema, and register the model in the cost map.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
The new perplexity/perplexity/glm-5.2 row carried 2.6e-07, which is glm-5.3's
cache read rate. api.perplexity.ai/v1/models publishes 0.14 usd per 1M cached
input tokens for glm-5.2, so the rate is 1.4e-07.
Combines the model-cost-map data from #35911, #36017, #36080, #36113, #36188, #36444, #37029, #37252 and #37632 onto current litellm_internal_staging, merged per entry field so older branches no longer revert fields the base has gained since they were opened. Drops the Gemini deprecation dates from #36188 and the text-embedding-004 date from #36080 that the official docs contradict.
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Mistral's live /v1/models reports max_context_length 1048576 and capabilities.reasoning
true for zai-glm-5-2, and its docs price cached input at $0.14/M. Without
cache_read_input_token_cost LiteLLM billed every cached prompt token at $0, so a repeat
request against a 21k-token cached prefix logged $0.0000135 instead of its real cost.
Mistral also serves the model under the short glm-5-2 name, which had no cost map entry
at all and therefore no pricing, so add it alongside.
The cache control hook also runs on litellm.responses() input. On a
GPT-5.6 deployment it wrapped a string-content item into a chat-shaped
{"type": "text"} part, which the Responses API rejects, and it never
marked input_text, input_image or input_file parts, so no breakpoint and
no prompt_cache_options reached the provider. Add the Responses part
types to the eligible block set and translate chat-shaped text parts on
non-assistant items to input_text in
ResponsesAPIRequestUtils.merge_prompt_management_input, which both the
async and the sync prompt management sites go through.
The dialect also fired for any GPT-5.6 name that resolved to provider
openai, including deployments pointed at a custom api_base that does not
understand prompt_cache_breakpoint. Decide it once per request from the
provider, the model map and the resolved api_base (request, then
litellm.api_base, then OPENAI_BASE_URL / OPENAI_API_BASE): only
api.openai.com and *.api.openai.com hosts speak the dialect, a top-level
prompt_cache_options opts a custom target in, and litellm_proxy/ targets
never get it. maybe_seed_default_injection_points takes api_base and
stamps the finished decision on the points as _litellm_openai_dialect so
the sync completion() path, whose hook params do not carry api_base,
honors it; maybe_inject_cache_control takes api_base from the
/v1/messages handler.
Eligibility now comes from a supports_prompt_cache_breakpoint model map
flag on the OpenAI gpt-5.6 entries, exposed through
litellm.utils.supports_prompt_cache_breakpoint, with the GPT version rule
kept only for models the map does not know. The OpenAI dialect no longer
reserves a slot for tool_config points, which OpenAI has no cache block
for, and with_prompt_cache_breakpoint plus the chat bridge helper return
a new block instead of mutating their input.
