diff --git a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.1.toml b/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.1.toml index b526038c0..ddcbe8001 100644 --- a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.1.toml +++ b/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.1.toml @@ -12,11 +12,11 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.55 -output = 2.19 +input = 0.30 +output = 1.20 [limit] -context = 204_800 +context = 196_608 output = 131_072 [modalities] diff --git a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.5.toml b/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.5.toml index bec4811bd..1d73e2106 100644 --- a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.5.toml +++ b/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.5.toml @@ -1,7 +1,7 @@ name = "MiniMax-M2.5" family = "minimax" release_date = "2026-02-07" -last_updated = "2026-02-07" +last_updated = "2026-02-12" attachment = false reasoning = true temperature = true @@ -13,9 +13,8 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.60 -output = 3.00 -cache_read = 0.60 +input = 0.40 +output = 2.00 [limit] context = 191_488 diff --git a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.toml b/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.toml deleted file mode 100644 index 6e489610b..000000000 --- a/providers/synthetic/models/hf:MiniMaxAI/MiniMax-M2.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "MiniMax-M2" -family = "minimax" -release_date = "2025-10-27" -last_updated = "2025-10-27" -attachment = false -reasoning = true -temperature = true -tool_call = true -# knowledge = "2025-04" # Not listed on model page. -open_weights = true - -[cost] -input = 0.55 -output = 2.19 - -[limit] -context = 196_608 -output = 131_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:Qwen/Qwen2.5-Coder-32B-Instruct.toml b/providers/synthetic/models/hf:Qwen/Qwen2.5-Coder-32B-Instruct.toml deleted file mode 100644 index e76153e7f..000000000 --- a/providers/synthetic/models/hf:Qwen/Qwen2.5-Coder-32B-Instruct.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Qwen2.5-Coder-32B-Instruct" -family = "qwen" -release_date = "2024-11-11" -last_updated = "2024-11-11" -attachment = false -reasoning = false -temperature = true -knowledge = "2024-10" -tool_call = false -open_weights = true - -[cost] -input = 0.8 -output = 0.8 - -[limit] -context = 32768 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Instruct-2507.toml b/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Instruct-2507.toml deleted file mode 100644 index 318664d11..000000000 --- a/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Instruct-2507.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Qwen 3 235B Instruct" -family = "qwen" -release_date = "2025-04-28" -last_updated = "2025-07-21" -attachment = false -reasoning = false -temperature = true -knowledge = "2025-04" -tool_call = true -open_weights = true - -[cost] -input = 0.2 -output = 0.6 - -[limit] -context = 256_000 -output = 32_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Thinking-2507.toml b/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Thinking-2507.toml index 6c6576614..4efc12805 100644 --- a/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Thinking-2507.toml +++ b/providers/synthetic/models/hf:Qwen/Qwen3-235B-A22B-Thinking-2507.toml @@ -11,10 +11,10 @@ open_weights = true [cost] input = 0.65 -output = 3.0 +output = 3.00 [limit] -context = 256_000 +context = 262_144 output = 32_000 [modalities] diff --git a/providers/synthetic/models/hf:Qwen/Qwen3.5-397B-A17B.toml b/providers/synthetic/models/hf:Qwen/Qwen3.5-397B-A17B.toml index dc66cc72c..ed0443aaf 100644 --- a/providers/synthetic/models/hf:Qwen/Qwen3.5-397B-A17B.toml +++ b/providers/synthetic/models/hf:Qwen/Qwen3.5-397B-A17B.toml @@ -1,4 +1,4 @@ -name = "Qwen3.5-97B-A17B" +name = "Qwen3.5-397B-A17B" family = "qwen" release_date = "2026-02-11" last_updated = "2026-02-11" @@ -15,8 +15,7 @@ field = "reasoning_content" [cost] input = 0.60 -output = 3.00 -cache_read = 0.60 +output = 3.60 [limit] context = 262_144 diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1-0528.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1-0528.toml index 6e2991a18..3dba6b8bf 100644 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1-0528.toml +++ b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1-0528.toml @@ -9,11 +9,11 @@ tool_call = true open_weights = false [cost] -input = 3 -output = 8 +input = 3.00 +output = 8.00 [limit] -context = 128_000 +context = 131_072 output = 128_000 [modalities] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1.toml deleted file mode 100644 index baef21028..000000000 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-R1.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "DeepSeek R1" -family = "deepseek-thinking" -release_date = "2025-01-20" -last_updated = "2025-01-20" -attachment = false -reasoning = true -temperature = true -knowledge = "2025-01" -tool_call = true -open_weights = true - -[cost] -input = 0.55 -output = 2.19 - -[limit] -context = 128_000 -output = 128_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3-0324.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3-0324.toml deleted file mode 100644 index 4054b02df..000000000 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3-0324.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "DeepSeek V3 (0324)" -family = "deepseek" -release_date = "2025-08-01" -last_updated = "2025-08-01" -attachment = false -reasoning = false -temperature = true -tool_call = true -open_weights = false - -[cost] -input = 1.20 -output = 1.20 - -[limit] -context = 128_000 -output = 128_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1-Terminus.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1-Terminus.toml deleted file mode 100644 index 4442cb640..000000000 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1-Terminus.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "DeepSeek V3.1 Terminus" -family = "deepseek" -release_date = "2025-09-22" -last_updated = "2025-09-25" -attachment = false -reasoning = true -temperature = true -tool_call = true -open_weights = false - -[cost] -input = 1.20 -output = 1.20 - -[limit] -context = 128_000 -output = 128_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1.toml deleted file mode 100644 index e26369be2..000000000 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.1.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "DeepSeek V3.1" -family = "deepseek" -release_date = "2025-08-21" -last_updated = "2025-08-21" -attachment = false -reasoning = true -temperature = true -tool_call = true -open_weights = false - -[cost] -input = 0.56 -output = 1.68 - -[limit] -context = 128_000 -output = 128_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.2.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.2.toml index bd98c9aae..68c5e19aa 100644 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.2.toml +++ b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.2.toml @@ -10,14 +10,11 @@ open_weights = true structured_output = true [cost] -input = 0.27 -output = 0.40 -cache_read = 0.27 -cache_write = 0.0 +input = 0.56 +output = 1.68 [limit] context = 162_816 -input = 162_816 output = 8_000 [modalities] diff --git a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.toml b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.toml index 86dc93181..eebde502b 100644 --- a/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.toml +++ b/providers/synthetic/models/hf:deepseek-ai/DeepSeek-V3.toml @@ -14,7 +14,7 @@ input = 1.25 output = 1.25 [limit] -context = 128_000 +context = 131_072 output = 128_000 [modalities] diff --git a/providers/synthetic/models/hf:meta-llama/Llama-3.1-405B-Instruct.toml b/providers/synthetic/models/hf:meta-llama/Llama-3.1-405B-Instruct.toml deleted file mode 100644 index a33b0d9ec..000000000 --- a/providers/synthetic/models/hf:meta-llama/Llama-3.1-405B-Instruct.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Llama-3.1-405B-Instruct" -family = "llama" -release_date = "2024-07-23" -last_updated = "2024-07-23" -attachment = false -reasoning = true -temperature = true -knowledge = "2023-12" -tool_call = true -open_weights = true - -[cost] -input = 3.00 -output = 3.00 - -[limit] -context = 128_000 -output = 32_768 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:meta-llama/Llama-3.3-70B-Instruct.toml b/providers/synthetic/models/hf:meta-llama/Llama-3.3-70B-Instruct.toml index fabb905b7..de145c7d5 100644 --- a/providers/synthetic/models/hf:meta-llama/Llama-3.3-70B-Instruct.toml +++ b/providers/synthetic/models/hf:meta-llama/Llama-3.3-70B-Instruct.toml @@ -10,11 +10,11 @@ tool_call = true open_weights = true [cost] -input = 0.90 -output = 0.90 +input = 0.88 +output = 0.88 [limit] -context = 128_000 +context = 131_072 output = 32_768 [modalities] diff --git a/providers/synthetic/models/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8.toml b/providers/synthetic/models/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8.toml deleted file mode 100644 index b13b65fa0..000000000 --- a/providers/synthetic/models/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Llama-4-Maverick-17B-128E-Instruct-FP8" -family = "llama" -release_date = "2025-04-05" -last_updated = "2025-04-05" -attachment = true -reasoning = false -temperature = true -knowledge = "2024-08" -tool_call = true -open_weights = true - -[cost] -input = 0.22 -output = 0.88 - -[limit] -context = 524_000 -output = 4_096 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/synthetic/models/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct.toml b/providers/synthetic/models/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct.toml deleted file mode 100644 index 10b99176c..000000000 --- a/providers/synthetic/models/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Llama-4-Scout-17B-16E-Instruct" -family = "llama" -release_date = "2025-04-05" -last_updated = "2025-04-05" -attachment = true -reasoning = false -temperature = true -knowledge = "2024-08" -tool_call = true -open_weights = true - -[cost] -input = 0.15 -output = 0.60 - -[limit] -context = 328_000 -output = 4_096 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/synthetic/models/hf:moonshotai/Kimi-K2-Instruct-0905.toml b/providers/synthetic/models/hf:moonshotai/Kimi-K2-Instruct-0905.toml index da780855e..726adf802 100644 --- a/providers/synthetic/models/hf:moonshotai/Kimi-K2-Instruct-0905.toml +++ b/providers/synthetic/models/hf:moonshotai/Kimi-K2-Instruct-0905.toml @@ -15,7 +15,7 @@ output = 1.20 [limit] context = 262_144 -output = 32_768 +output = 65_536 [modalities] input = ["text"] diff --git a/providers/synthetic/models/hf:moonshotai/Kimi-K2-Thinking.toml b/providers/synthetic/models/hf:moonshotai/Kimi-K2-Thinking.toml index e3e321756..0f843f265 100644 --- a/providers/synthetic/models/hf:moonshotai/Kimi-K2-Thinking.toml +++ b/providers/synthetic/models/hf:moonshotai/Kimi-K2-Thinking.toml @@ -10,12 +10,12 @@ knowledge = "2025-11" open_weights = true [cost] -input = 0.55 -output = 2.19 +input = 0.60 +output = 2.50 [limit] context = 262_144 -output = 262_144 +output = 65_536 [modalities] input = ["text"] diff --git a/providers/synthetic/models/hf:moonshotai/Kimi-K2.5.toml b/providers/synthetic/models/hf:moonshotai/Kimi-K2.5.toml index ffc709122..119997621 100644 --- a/providers/synthetic/models/hf:moonshotai/Kimi-K2.5.toml +++ b/providers/synthetic/models/hf:moonshotai/Kimi-K2.5.toml @@ -1,11 +1,12 @@ name = "Kimi K2.5" family = "kimi" release_date = "2026-01" -last_updated = "2026-01" +last_updated = "2026-01-27" attachment = false reasoning = true temperature = true tool_call = true +structured_output = true knowledge = "2025-01" open_weights = true @@ -13,8 +14,8 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.55 -output = 2.19 +input = 0.45 +output = 3.40 [limit] context = 262_144 diff --git a/providers/synthetic/models/hf:nvidia/Kimi-K2.5-NVFP4.toml b/providers/synthetic/models/hf:nvidia/Kimi-K2.5-NVFP4.toml index 989c7bc33..61b7e903c 100644 --- a/providers/synthetic/models/hf:nvidia/Kimi-K2.5-NVFP4.toml +++ b/providers/synthetic/models/hf:nvidia/Kimi-K2.5-NVFP4.toml @@ -1,11 +1,12 @@ name = "Kimi K2.5 (NVFP4)" family = "kimi" release_date = "2026-01" -last_updated = "2026-01" +last_updated = "2026-01-27" attachment = false reasoning = true temperature = true tool_call = true +structured_output = true knowledge = "2025-01" open_weights = true @@ -13,8 +14,8 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.55 -output = 2.19 +input = 0.45 +output = 3.40 [limit] context = 262_144 diff --git a/providers/synthetic/models/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4.toml b/providers/synthetic/models/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4.toml new file mode 100644 index 000000000..e693c901e --- /dev/null +++ b/providers/synthetic/models/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4.toml @@ -0,0 +1,25 @@ +name = "NVIDIA Nemotron 3 Super 120B A12B NVFP4" +family = "nemotron" +release_date = "2026-03-11" +last_updated = "2026-03-11" +attachment = false +reasoning = true +temperature = true +tool_call = true +structured_output = true +open_weights = true + +[interleaved] +field = "reasoning_content" + +[cost] +input = 0.30 +output = 1.00 + +[limit] +context = 262_144 +output = 65_536 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/synthetic/models/hf:openai/gpt-oss-120b.toml b/providers/synthetic/models/hf:openai/gpt-oss-120b.toml index 19b195095..ca3b49043 100644 --- a/providers/synthetic/models/hf:openai/gpt-oss-120b.toml +++ b/providers/synthetic/models/hf:openai/gpt-oss-120b.toml @@ -13,7 +13,7 @@ input = 0.10 output = 0.10 [limit] -context = 128_000 +context = 131_072 output = 32_768 [modalities] diff --git a/providers/synthetic/models/hf:zai-org/GLM-4.6.toml b/providers/synthetic/models/hf:zai-org/GLM-4.6.toml deleted file mode 100644 index ee30bfa4d..000000000 --- a/providers/synthetic/models/hf:zai-org/GLM-4.6.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "GLM 4.6" -family = "glm" -release_date = "2025-09-30" -last_updated = "2025-09-30" -attachment = false -reasoning = true -temperature = true -tool_call = true -knowledge = "2025-04" -open_weights = true - -[cost] -input = 0.55 -output = 2.19 - -[limit] -context = 200_000 -output = 64_000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/providers/synthetic/models/hf:zai-org/GLM-4.7-Flash.toml b/providers/synthetic/models/hf:zai-org/GLM-4.7-Flash.toml index 1099427f3..b11a34d36 100644 --- a/providers/synthetic/models/hf:zai-org/GLM-4.7-Flash.toml +++ b/providers/synthetic/models/hf:zai-org/GLM-4.7-Flash.toml @@ -1,7 +1,7 @@ name = "GLM-4.7-Flash" family = "glm" release_date = "2026-01-18" -last_updated = "2026-01-18" +last_updated = "2026-01-19" attachment = false reasoning = true temperature = true @@ -13,9 +13,8 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.06 -output = 0.40 -cache_read = 0.06 +input = 0.10 +output = 0.50 [limit] context = 196_608 diff --git a/providers/synthetic/models/hf:zai-org/GLM-4.7.toml b/providers/synthetic/models/hf:zai-org/GLM-4.7.toml index a9fd240f0..bbd0b990e 100644 --- a/providers/synthetic/models/hf:zai-org/GLM-4.7.toml +++ b/providers/synthetic/models/hf:zai-org/GLM-4.7.toml @@ -6,6 +6,7 @@ attachment = false reasoning = true temperature = true tool_call = true +structured_output = true knowledge = "2025-04" open_weights = true @@ -13,12 +14,12 @@ open_weights = true field = "reasoning_content" [cost] -input = 0.55 +input = 0.45 output = 2.19 [limit] -context = 200_000 -output = 64_000 +context = 202_752 +output = 65_536 [modalities] input = ["text"] diff --git a/providers/synthetic/models/hf:zai-org/GLM-5.toml b/providers/synthetic/models/hf:zai-org/GLM-5.toml new file mode 100644 index 000000000..0f9bb9083 --- /dev/null +++ b/providers/synthetic/models/hf:zai-org/GLM-5.toml @@ -0,0 +1,25 @@ +name = "GLM-5" +family = "glm" +release_date = "2026-02-11" +last_updated = "2026-02-11" +attachment = false +reasoning = true +temperature = true +tool_call = true +structured_output = true +open_weights = true + +[interleaved] +field = "reasoning_content" + +[cost] +input = 1.00 +output = 6.00 + +[limit] +context = 196_608 +output = 65_536 + +[modalities] +input = ["text"] +output = ["text"]