AI API changes: June 2026
18 changes shipped without an announcement, and 0 that came with a published date. Compiled automatically from provider catalogs and endpoints; every figure below links to the model it came from.
4
capacity cuts
context or output shrank
7
price changes
same call, different bill
5
capabilities lost
0
announced
deprecations with a date
Unannounced, biggest first
| Impact | Provider | What changed | Detected |
|---|---|---|---|
| truncation | fireworks_ai | -75% max out · fireworks_ai/accounts/fireworks/models/gpt-oss-120b: max_output_tokens cut 131,072 to 32,768 +1 alias | 2026-06-18 |
| cost | cohere_chat | 4.00x price · command-r7b-12-2024: output_price_per_mtok $0.04/Mtok to $0.15/Mtok | 2026-06-18 |
| cost | mistral | 3.75x price · mistral/mistral-medium-latest: input_price_per_mtok $0.40/Mtok to $1.50/Mtok | 2026-06-26 |
| cost | mistral | 3.75x price · mistral/mistral-medium-latest: output_price_per_mtok $2.00/Mtok to $7.50/Mtok | 2026-06-26 |
| capability | gemini | lost code_execution, file_search, service_tier · gemini/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search, service_tier +1 alias | 2026-06-27 |
| capability | vertex_ai-language-models | lost code_execution, file_search, service_tier · gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search, service_tier +2 aliases | 2026-06-27 |
| truncation | openai | -53% max out · gpt-5-pro-2025-10-06: max_output_tokens cut 272,000 to 128,000 +1 alias | 2026-06-26 |
| capability | vertex_ai-language-models | lost code_execution, file_search · vertex_ai/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search | 2026-06-27 |
| capability | openrouter | lost code_execution, file_search · openrouter/google/gemini-3.1-flash-lite-preview: capabilities lost code_execution, file_search +1 alias | 2026-06-27 |
| cost | sambanova | 2.00x price · sambanova/MiniMax-M2.7: output_price_per_mtok $1.20/Mtok to $2.40/Mtok | 2026-06-26 |
| cost | sambanova | 2.00x price · sambanova/MiniMax-M2.7: input_price_per_mtok $0.30/Mtok to $0.60/Mtok | 2026-06-26 |
| truncation | fireworks_ai | -35% max out · fireworks_ai/accounts/fireworks/models/glm-5p1: max_output_tokens cut 202,800 to 131,072 +1 alias inferred | 2026-06-18 |
| cost | fireworks_ai | 1.50x price · fireworks_ai/accounts/fireworks/models/gpt-oss-20b: output_price_per_mtok $0.20/Mtok to $0.30/Mtok | 2026-06-18 |
| cost | fireworks_ai | 1.40x price · fireworks_ai/accounts/fireworks/models/gpt-oss-20b: input_price_per_mtok $0.05/Mtok to $0.07/Mtok | 2026-06-18 |
| truncation | sambanova | -4% ctx · sambanova/MiniMax-M2.7: context_tokens cut 204,800 to 196,608 | 2026-06-26 |
| capability | perplexity | lost preset · perplexity/preset/advanced-deep-research: capabilities lost preset +3 aliases inferred | 2026-06-27 |
| availability | fireworks_ai | fireworks_ai/accounts/fireworks/models/whisper-v3-turbo is no longer listed by this source — calls to it are expected to fail | 2026-06-23 |
| availability | fireworks_ai | fireworks_ai/accounts/fireworks/models/whisper-v3 is no longer listed by this source — calls to it are expected to fail | 2026-06-23 |
Announced this period
| Impact | Provider | What changed | Detected |
|---|---|---|---|
| Nothing yet. | |||
Who changed the most
| Provider | Unannounced changes |
|---|---|
| fireworks_ai | 6 |
| sambanova | 3 |
| mistral | 2 |
| vertex_ai-language-models | 2 |
| cohere_chat | 1 |
| gemini | 1 |
| openai | 1 |
| openrouter | 1 |
| perplexity | 1 |