BestHunt — AI model pricing changes

107 pricing changes on 2026-10-12

Mon, 12 Oct 2026 09:00:00 +0000

Qwen3 VL 32B Instruct is no longer offered by any host we track.
Qwen3 VL 8B Thinking is no longer offered by any host we track.
Qwen3 8B is no longer offered by any host we track.
Qwen3.6 Max Preview is no longer offered by any host we track.
Qwen3 235B A22B is no longer offered by any host we track.
Qwen3 Coder Plus is no longer offered by any host we track.
Qwen3 Max is no longer offered by any host we track.
Qwen3 VL 235B A22B Thinking is no longer offered by any host we track.
Qwen Plus 0728 is no longer offered by any host we track.
Qwen3 30B A3B Thinking 2507 is no longer offered by any host we track.
Qwen3 Max Thinking is no longer offered by any host we track.
GLM 5.3 Flash input price fell 85%, $0.150 to $0.023 per million tokens.
GLM 5.3 Flash output price rose 99%, $0.500 to $1.20 per million tokens.
GLM 5.3 Flash is now served by 32 hosts, down from 33.
Qwen3 VL 8B Instruct input price rose 99%, $0.117 to $0.250 per million tokens.
Qwen3 VL 8B Instruct output price rose 65%, $0.455 to $0.750 per million tokens.
Qwen3 VL 8B Instruct is now served by 1 hosts, down from 2.
Qwen3 VL 8B Instruct context most hosts serve moved from 131K to 262K.
Qwen3 Coder 30B A3B Instruct is now served by 2 hosts, down from 3.
GLM 5.3 Flash (batch) is now served by 32 hosts, down from 33.
Qwen3.7 Flash is now served by 2 hosts, up from 1.
Qwen3 VL 30B A3B Instruct is now served by 3 hosts, down from 4.
Qwen3 VL 30B A3B Instruct context most hosts serve moved from 131K to 262K.
gpt-oss-120b (batch) is now served by 24 hosts, up from 23.
GPT-6.1 Sol (batch) became best value — nothing cheaper now matches it.
Qwen3 235B A22B Instruct 2507 is now served by 7 hosts, down from 9.
Kimi K2.5 input price rose 11%, $0.450 to $0.500 per million tokens.
Kimi K2.5 output price rose 11%, $2.25 to $2.50 per million tokens.
Qwen3 14B is now served by 2 hosts, down from 3.
Qwen3.8 Max (0902) is now served by 2 hosts, up from 1.
Kimi K2.6 input price rose 40%, $0.465 to $0.650 per million tokens.
Kimi K2.6 output price rose 39%, $2.45 to $3.41 per million tokens.
Qwen3 30B A3B is now served by 1 hosts, down from 2.
DeepSeek V3.2 output price rose 90%, $0.420 to $0.800 per million tokens.
DeepSeek V3.2 is now served by 12 hosts, down from 13.
Qwen3 Next 80B A3B Thinking is now served by 1 hosts, down from 2.
DeepSeek Flash Latest input price rose 99%, $0.016 to $0.034 per million tokens.
DeepSeek V4 Flash Latest input price fell 11%, $0.014 to $0.013 per million tokens.
DeepSeek V4 Flash Latest output price rose 99%, $0.121 to $0.768 per million tokens.
DeepSeek V4 Flash 0731 input price fell 11%, $0.018 to $0.016 per million tokens.
DeepSeek V4 Flash 0731 output price fell 50%, $1.28 to $0.640 per million tokens.
DeepSeek V4 Flash 0731 is now served by 27 hosts, up from 26.
Qwen3.8 27B input price fell 91%, $0.425 to $0.040 per million tokens.
Qwen3.8 27B output price fell 10%, $2.55 to $2.30 per million tokens.
Qwen3.8 27B is now served by 20 hosts, up from 18.
Nemotron 3.5 Lightning input price rose 49%, $0.047 to $0.070 per million tokens.
Nemotron 3.5 Lightning output price rose 49%, $0.134 to $0.200 per million tokens.
Nemotron 3.5 Lightning is now served by 5 hosts, down from 6.
GLM 5.3 (batch) is now served by 41 hosts, down from 42.
GLM Flash Latest input price fell 28%, $0.032 to $0.023 per million tokens.
GLM Flash Latest output price fell 7%, $1.29 to $1.20 per million tokens.
Qwen3 VL 235B A22B Instruct is now served by 3 hosts, down from 4.
Qwen3 VL 235B A22B Instruct context most hosts serve moved from 131K to 262K.
Qwen3.6 35B A3B input price fell 33%, $0.150 to $0.100 per million tokens.
Qwen3.6 35B A3B output price fell 5%, $1.00 to $0.950 per million tokens.
Nemotron 3 Ultra input price rose 20%, $0.500 to $0.600 per million tokens.
Nemotron 3 Ultra output price rose 9%, $2.20 to $2.40 per million tokens.
gpt-oss-120b is now served by 24 hosts, up from 23.
Qwen3.8 Flash is now served by 2 hosts, up from 1.
Qwen3 Coder 480B A35B is now served by 3 hosts, down from 4.
Qwen3.7 Plus is now served by 2 hosts, up from 1.
Kimi K3 input price rose 46%, $0.500 to $0.730 per million tokens.
Kimi K3 output price fell 17%, $12.00 to $10.00 per million tokens.
Muse Glimmer 30B is now served by 2 hosts, down from 3.
Qwen3 Coder Next is now served by 1 hosts, down from 3.
DeepSeek Pro Latest input price rose 26%, $0.198 to $0.250 per million tokens.
DeepSeek Pro Latest output price fell 38%, $8.00 to $5.00 per million tokens.
Ling 3.0 Flash Fin is now served by 1 hosts, down from 2.
Qwen3 235B A22B Thinking 2507 input price rose 96%, $0.230 to $0.450 per million tokens.
Qwen3 235B A22B Thinking 2507 output price rose 52%, $2.30 to $3.50 per million tokens.
Qwen3 235B A22B Thinking 2507 is now served by 1 hosts, down from 2.
Qwen3 235B A22B Thinking 2507 context most hosts serve moved from 131K to 128K.
Qwen3.6 27B input price fell 29%, $0.450 to $0.320 per million tokens.
Qwen3.6 27B output price rose 19%, $2.70 to $3.20 per million tokens.
GLM 4.6 input price rose 16%, $0.430 to $0.500 per million tokens.
GLM 4.6 output price rose 14%, $1.75 to $2.00 per million tokens.
Qwen3 30B A3B Instruct 2507 is now served by 3 hosts, down from 5.
Qwen3.7 Max is now served by 2 hosts, up from 1.
GLM 5.2 input price fell 29%, $0.084 to $0.060 per million tokens.
GLM 5.2 output price fell 12%, $8.00 to $7.00 per million tokens.
GLM 5.3 input price rose 99%, $0.039 to $0.079 per million tokens.
GLM 5.3 output price fell 31%, $7.00 to $4.80 per million tokens.
GLM 5.3 is now served by 41 hosts, down from 42.
Qwen3 Next 80B A3B Instruct is now served by 3 hosts, down from 4.
Qwen3 VL 30B A3B Thinking input price rose 45%, $0.200 to $0.290 per million tokens.
Qwen3 VL 30B A3B Thinking output price fell 58%, $2.40 to $1.00 per million tokens.
Qwen3 VL 30B A3B Thinking is now served by 1 hosts, down from 2.
Qwen3 VL 30B A3B Thinking context most hosts serve moved from 131K to 262K.
DeepSeek V4 Flash 0423 input price rose 99%, $0.007 to $0.030 per million tokens.
DeepSeek V4 Flash 0423 is now served by 16 hosts, down from 17.
Kimi Latest input price rose 47%, $0.490 to $0.720 per million tokens.
Kimi Latest output price rose 85%, $13.00 to $24.00 per million tokens.
GLM Latest input price rose 76%, $0.031 to $0.055 per million tokens.
GLM Latest output price rose 14%, $4.40 to $5.00 per million tokens.
Tenstorrent started serving GLM 5.3 at $0.600 per million.
Nebius stopped serving GLM 5.3.
Relace stopped serving GLM 5.3.
Relace stopped serving GLM 5.2.
DekaLLM stopped serving GLM 5.3 Flash.
BaseTen switched DeepSeek V4.1 Flash from fp8 to fp32.
DekaLLM stopped serving DeepSeek V4.1 Flash.
Venice started serving gpt-oss-120b at $0.030 per million.
Near AI started serving Qwen3.8 27B at $0.040 per million.
Tenstorrent started serving Qwen3.8 27B at $0.040 per million.
Relace stopped serving DeepSeek V4 Pro 0813.
Novita stopped serving DeepSeek V4 Flash 0423.
Relace stopped serving DeepSeek V4 Pro 0423.

131 pricing changes on 2026-10-09

Fri, 09 Oct 2026 09:00:00 +0000

Claude Haiku 5.5 (batch) appeared, served by 10 host(s) at $0.050 per million input tokens.
Nano Banana 2.1 appeared, served by 1 host(s) at $1.50 per million input tokens.
GPT-6.1 Sol Pro (batch) appeared, served by 7 host(s) at $1.00 per million input tokens.
Step 5 Preview appeared, served by 1 host(s) at $1.00 per million input tokens.
Claude Haiku 5.5 appeared, served by 10 host(s) at $0.105 per million input tokens.
GPT-6.1 Sol (batch) appeared, served by 8 host(s) at $1.00 per million input tokens.
Ling 3.0 Flash Sante appeared, served by 1 host(s) at $0.042 per million input tokens.
Mistral Large 4 appeared, served by 3 host(s) at $0.680 per million input tokens.
KAT-Coder-Pro V2.5 is no longer offered by any host we track.
ERNIE 4.5 VL 424B A47B is no longer offered by any host we track.
MiniMax M2 is now served by 2 hosts, down from 3.
GLM 4.7 is now served by 6 hosts, down from 7.
Qwen3 Coder 30B A3B Instruct is now served by 3 hosts, down from 4.
Llama 3.1 Euryale 70B v2.2 is now served by 1 hosts, down from 2.
Qwen3 235B A22B Instruct 2507 input price rose 3%, $0.087 to $0.090 per million tokens.
Qwen3 235B A22B Instruct 2507 output price rose 57%, $0.350 to $0.550 per million tokens.
Qwen3 235B A22B Instruct 2507 is now served by 9 hosts, down from 10.
MiniMax M2.7 is now served by 6 hosts, down from 7.
DeepSeek V3 input price rose 24%, $0.257 to $0.320 per million tokens.
DeepSeek V3 output price fell 13%, $1.03 to $0.890 per million tokens.
DeepSeek V3.1 Terminus is now served by 2 hosts, down from 3.
DeepSeek V4 Flash Vision Exp is now served by 3 hosts, down from 4.
Qwen3.5-35B-A3B input price fell 47%, $0.150 to $0.080 per million tokens.
Qwen3.5-35B-A3B output price fell 25%, $1.00 to $0.750 per million tokens.
MiniMax M2.1 is now served by 2 hosts, down from 3.
Kimi K2.6 input price fell 51%, $0.950 to $0.465 per million tokens.
Kimi K2.6 output price fell 39%, $4.00 to $2.45 per million tokens.
Kimi K2.6 is now served by 17 hosts, down from 18.
Kimi K3 (batch) is now served by 25 hosts, up from 24.
DeepSeek V4 Pro 0813 input price rose 99%, $0.450 to $1.32 per million tokens.
DeepSeek V4 Pro 0813 output price fell 21%, $5.00 to $3.96 per million tokens.
DeepSeek V4 Pro 0813 is now served by 21 hosts, up from 20.
Hy3 is now served by 5 hosts, down from 6.
DeepSeek V3.2 input price fell 8%, $0.280 to $0.259 per million tokens.
DeepSeek Flash Latest input price rose 99%, $0.003 to $0.016 per million tokens.
DeepSeek Flash Latest output price fell 50%, $2.40 to $1.20 per million tokens.
Llama 3.3 70B Instruct input price rose 99%, $0.100 to $0.220 per million tokens.
Llama 3.3 70B Instruct output price rose 56%, $0.320 to $0.500 per million tokens.
DeepSeek V4 Flash Latest input price fell 5%, $0.015 to $0.014 per million tokens.
DeepSeek V4 Flash Latest output price fell 91%, $1.28 to $0.121 per million tokens.
DeepSeek V4 Flash 0731 input price rose 18%, $0.015 to $0.018 per million tokens.
DeepSeek V4 Flash 0731 is now served by 26 hosts, down from 28.
DeepSeek V4.1 Flash is now served by 31 hosts, up from 30.
Qwen3.8 27B is now served by 18 hosts, up from 17.
Nemotron 3.5 Lightning input price fell 22%, $0.060 to $0.047 per million tokens.
Nemotron 3.5 Lightning output price fell 16%, $0.160 to $0.134 per million tokens.
Nemotron 3.5 Lightning is now served by 6 hosts, up from 5.
gpt-oss-20b (batch) is now served by 11 hosts, down from 12.
GPT-6.1 Sol Pro is now served by 7 hosts, up from 6.
GLM 5.3 (batch) is now served by 42 hosts, up from 41.
GLM Flash Latest input price fell 9%, $0.035 to $0.032 per million tokens.
GLM Flash Latest output price rose 99%, $0.500 to $1.29 per million tokens.
Qwen2.5 72B Instruct is now served by 1 hosts, down from 2.
Qwen3 VL 235B A22B Instruct is now served by 4 hosts, down from 5.
Muse Spark 1.3 lost best value; something cheaper now matches its score.
Qwen3.6 35B A3B is now served by 10 hosts, up from 9.
Claude Opus 5.5 (batch) became best value — nothing cheaper now matches it.
DeepSeek V4.1 Flash (batch) is now served by 31 hosts, up from 30.
MiMo-V2.6-Flash is now served by 8 hosts, up from 7.
GPT-6.1 Sol is now served by 8 hosts, up from 7.
Inkling input price rose 5%, $0.950 to $1.00 per million tokens.
gpt-oss-20b is now served by 11 hosts, down from 12.
Qwen3 Coder 480B A35B is now served by 4 hosts, down from 5.
Kimi K3 input price fell 25%, $0.670 to $0.500 per million tokens.
Kimi K3 output price fell 14%, $14.00 to $12.00 per million tokens.
Kimi K3 is now served by 25 hosts, up from 24.
Muse Glimmer 30B input price fell 14%, $0.350 to $0.300 per million tokens.
Muse Glimmer 30B output price fell 20%, $1.50 to $1.20 per million tokens.
Qwen3.5-27B input price rose 33%, $0.195 to $0.260 per million tokens.
Qwen3.5-27B output price rose 67%, $1.56 to $2.60 per million tokens.
Gemma 3 27B is now served by 5 hosts, up from 4.
Qwen3 Coder Next is now served by 3 hosts, down from 4.
DeepSeek V4 Pro 0423 input price rose 99%, $0.209 to $0.955 per million tokens.
DeepSeek V4 Pro 0423 output price rose 99%, $0.418 to $1.91 per million tokens.
DeepSeek V4 Pro 0423 is now served by 15 hosts, down from 16.
DeepSeek Pro Latest input price rose 4%, $0.190 to $0.198 per million tokens.
DeepSeek Pro Latest output price rose 90%, $4.20 to $8.00 per million tokens.
Qwen3 235B A22B Thinking 2507 is now served by 2 hosts, down from 3.
Qwen3.6 27B input price rose 41%, $0.320 to $0.450 per million tokens.
Qwen3.6 27B output price fell 17%, $3.25 to $2.70 per million tokens.
Qwen3.6 27B is now served by 7 hosts, up from 6.
Qwen3 30B A3B Instruct 2507 input price rose 99%, $0.048 to $0.100 per million tokens.
Qwen3 30B A3B Instruct 2507 output price rose 55%, $0.193 to $0.300 per million tokens.
DeepSeek V3.1 is now served by 5 hosts, down from 7.
GLM 5.2 input price rose 99%, $0.022 to $0.084 per million tokens.
GLM 5.2 output price fell 50%, $16.00 to $8.00 per million tokens.
GLM 5.2 is now served by 34 hosts, up from 32.
Claude Haiku Latest input price fell 90%, $1.00 to $0.100 per million tokens.
Claude Haiku Latest output price fell 90%, $5.00 to $0.500 per million tokens.
Claude Haiku Latest context most hosts serve moved from 200K to 1000K.
GLM 5.3 input price fell 22%, $0.050 to $0.039 per million tokens.
GLM 5.3 is now served by 42 hosts, up from 41.
Qwen3 VL 235B A22B Thinking is now served by 1 hosts, down from 2.
Nemotron 3 Nano 30B A3B input price rose 20%, $0.050 to $0.060 per million tokens.
Nemotron 3 Nano 30B A3B output price rose 20%, $0.200 to $0.240 per million tokens.
Nemotron 3 Nano 30B A3B is now served by 2 hosts, down from 4.
Qwen3 Next 80B A3B Instruct is now served by 4 hosts, down from 5.
Gemma 3 12B is now served by 2 hosts, up from 1.
Mistral Nemo input price rose 53%, $0.019 to $0.029 per million tokens.
Mistral Nemo is now served by 5 hosts, down from 6.
Llama 3 8B Lunaris is now served by 2 hosts, down from 3.
Kimi K2.7 Code is now served by 12 hosts, down from 13.
GLM 5.1 input price fell 31%, $1.40 to $0.966 per million tokens.
GLM 5.1 output price fell 31%, $4.40 to $3.04 per million tokens.
DeepSeek V4 Flash 0423 input price fell 75%, $0.030 to $0.007 per million tokens.
DeepSeek V4 Flash 0423 is now served by 17 hosts, up from 16.
Kimi Latest input price rose 63%, $0.300 to $0.490 per million tokens.
Kimi Latest output price fell 35%, $20.00 to $13.00 per million tokens.
GLM Latest input price rose 4%, $0.030 to $0.031 per million tokens.
GLM Latest output price fell 63%, $12.00 to $4.40 per million tokens.
InferenceNet switched GLM 5.3 from unknown to fp4 — a 4-bit build at the same price.
Io Net started serving GLM 5.3 at $1.20 per million.
InferenceNet switched GLM 5.2 from unknown to fp4 — a 4-bit build at the same price.
Nebius started serving GLM 5.2 at $1.40 per million.
Phala switched GLM 5.3 Flash from fp8 to nvfp4.
Cloudflare stopped serving GLM 5.3 Flash.
NextBit stopped serving GLM 5.3 Flash.
InferenceNet switched DeepSeek V4.1 Flash from unknown to fp8.
Crusoe started serving DeepSeek V4.1 Flash at $0.290 per million.
OpenInference started serving DeepSeek V4.1 Flash at $0.020 per million.
NextBit stopped serving DeepSeek V4.1 Flash.
NextBit stopped serving DeepSeek V4 Flash 0731.
Morph stopped serving DeepSeek V4 Flash 0731.
Makora switched Kimi K3 from unknown to fp4 — a 4-bit build at the same price.
Sail Research started serving DeepSeek V4 Pro 0813 at $0.400 per million.
NextBit stopped serving DeepSeek V4 Pro 0813.
Reka switched Qwen3.8 27B from unknown to fp8.
ModelRun started serving Qwen3.8 27B at $0.800 per million.
Wafer started serving DeepSeek V4 Flash 0423 at $0.035 per million.
Decart stopped serving Kimi K2.6.
NextBit stopped serving DeepSeek V4 Pro 0423.

202 pricing changes on 2026-10-05

Mon, 05 Oct 2026 09:00:00 +0000

Aion 3.5 appeared, served by 1 host(s) at $3.00 per million input tokens.
GLM 5.3 Prime appeared, served by 1 host(s) at $2.80 per million input tokens.
Mistral Large 3 2512 appeared, served by 2 host(s) at $0.525 per million input tokens.
gpt-oss-120b (batch) appeared, served by 23 host(s) at $0.030 per million input tokens.
Pareto 26.10 Preview appeared, served by 1 host(s) at $0.800 per million input tokens.
Perceptron Mk1.5 appeared, served by 1 host(s) at $0.150 per million input tokens.
Claude Sonnet 5.5 (batch) appeared, served by 8 host(s) at $1.00 per million input tokens.
Aion 3.5 Mini appeared, served by 1 host(s) at $0.700 per million input tokens.
GPT-6.1 Sol Pro appeared, served by 6 host(s) at $2.10 per million input tokens.
Ember-1 appeared, served by 1 host(s) at $3.00 per million input tokens.
Qwen3.8 Max Prime appeared, served by 1 host(s) at $4.00 per million input tokens.
GPT-6.1 Sol appeared, served by 7 host(s) at $2.20 per million input tokens.
Claude Sonnet 5.5 appeared, served by 8 host(s) at $2.00 per million input tokens.
Claude 3 Haiku is no longer offered by any host we track.
R1 Distill Llama 70B is no longer offered by any host we track.
GLM 5.3 Flash is now served by 33 hosts, up from 31.
MiniMax M2 input price rose 18%, $0.255 to $0.300 per million tokens.
MiniMax M2 output price rose 18%, $1.02 to $1.20 per million tokens.
GLM 4.7 input price rose 50%, $0.400 to $0.600 per million tokens.
GLM 4.7 output price rose 26%, $1.75 to $2.20 per million tokens.
GLM 5.3 Flash (batch) is now served by 33 hosts, up from 31.
Gemma 4 26B A4B is now served by 13 hosts, up from 12.
Qwen3 VL 30B A3B Instruct input price rose 15%, $0.130 to $0.150 per million tokens.
Qwen3 VL 30B A3B Instruct output price rose 15%, $0.520 to $0.600 per million tokens.
Inkling Small is now served by 1 hosts, down from 2.
MiniMax M2.7 input price fell 30%, $0.300 to $0.210 per million tokens.
MiniMax M2.7 output price fell 30%, $1.20 to $0.840 per million tokens.
MiniMax M2.7 is now served by 7 hosts, down from 9.
DeepSeek V3 input price fell 20%, $0.320 to $0.257 per million tokens.
DeepSeek V3 output price rose 16%, $0.890 to $1.03 per million tokens.
DeepSeek V3.1 Terminus is now served by 3 hosts, down from 4.
DeepSeek V3.1 Terminus context most hosts serve moved from 131K to 163K.
DeepSeek V4 Flash Vision Exp input price fell 2%, $0.220 to $0.216 per million tokens.
DeepSeek V4 Flash Vision Exp is now served by 4 hosts, down from 5.
Qwen3.5-35B-A3B input price fell 52%, $0.312 to $0.150 per million tokens.
Qwen3.5-35B-A3B output price fell 20%, $1.25 to $1.00 per million tokens.
MiMo-V2.5 is now served by 5 hosts, down from 6.
MiMo-V2.5-Pro is now served by 6 hosts, down from 7.
Kimi K2.6 is now served by 18 hosts, down from 22.
Mistral Small 3.2 24B is now served by 4 hosts, up from 3.
Kimi K3 (batch) is now served by 24 hosts, up from 20.
Mistral Small 4 is now served by 4 hosts, up from 3.
DeepSeek V4 Pro 0813 input price fell 10%, $0.499 to $0.450 per million tokens.
DeepSeek V4 Pro 0813 output price rose 99%, $1.50 to $5.00 per million tokens.
DeepSeek V4 Pro 0813 is now served by 20 hosts, down from 24.
Grok Latest input price rose 25%, $1.60 to $2.00 per million tokens.
Grok Latest output price rose 25%, $4.80 to $6.00 per million tokens.
GPT-6 Astra Pro (batch) is now served by 6 hosts, up from 5.
DeepSeek V3.2 input price rose 4%, $0.269 to $0.280 per million tokens.
DeepSeek V3.2 output price rose 5%, $0.400 to $0.420 per million tokens.
DeepSeek V3.2 is now served by 13 hosts, down from 15.
DeepSeek Flash Latest input price fell 97%, $0.100 to $0.003 per million tokens.
DeepSeek Flash Latest output price rose 99%, $0.500 to $2.40 per million tokens.
DeepSeek V4 Flash Latest input price fell 60%, $0.038 to $0.015 per million tokens.
DeepSeek V4 Flash Latest output price rose 99%, $0.550 to $1.28 per million tokens.
DeepSeek V4 Flash Latest context most hosts serve moved from 1310K to 1048K.
DeepSeek V4 Flash 0731 input price fell 62%, $0.040 to $0.015 per million tokens.
DeepSeek V4 Flash 0731 output price rose 99%, $0.640 to $1.28 per million tokens.
DeepSeek V4 Flash 0731 is now served by 28 hosts, down from 30.
Step 3.7 Flash is now served by 2 hosts, down from 3.
MiMo-V2.6-Pro is now served by 4 hosts, up from 2.
Qwen3 32B is now served by 3 hosts, up from 2.
Grok 4.7 input price rose 25%, $1.60 to $2.00 per million tokens.
Grok 4.7 output price rose 25%, $4.80 to $6.00 per million tokens.
Grok 4.7 is now served by 5 hosts, up from 4.
DeepSeek V4.1 Flash input price rose 99%, $0.150 to $0.300 per million tokens.
DeepSeek V4.1 Flash output price rose 99%, $0.600 to $1.20 per million tokens.
DeepSeek V4.1 Flash is now served by 30 hosts, up from 26.
Qwen3.8 27B output price fell 15%, $3.00 to $2.55 per million tokens.
Qwen3.8 27B is now served by 17 hosts, up from 16.
Voxtral Small 24B 2507 context most hosts serve moved from 32K to 32K.
Nemotron 3.5 Lightning input price fell 25%, $0.080 to $0.060 per million tokens.
Nemotron 3.5 Lightning output price fell 20%, $0.200 to $0.160 per million tokens.
Nemotron 3.5 Lightning is now served by 5 hosts, up from 4.
GLM 5.3 (batch) input price fell 38%, $0.720 to $0.450 per million tokens.
GLM 5.3 (batch) output price fell 17%, $2.40 to $2.00 per million tokens.
GLM 5.3 (batch) is now served by 41 hosts, up from 35.
Llama 4 Maverick is now served by 4 hosts, down from 5.
Llama 4 Maverick context most hosts serve moved from 1048K to 524K.
GLM Flash Latest input price fell 53%, $0.075 to $0.035 per million tokens.
GLM Flash Latest output price rose 99%, $0.250 to $0.500 per million tokens.
GLM Flash Latest context most hosts serve moved from 1310K to 1048K.
Mistral Medium 3.5 is now served by 3 hosts, up from 2.
DeepSeek V3 0324 input price rose 16%, $0.250 to $0.290 per million tokens.
DeepSeek V3 0324 output price rose 14%, $1.00 to $1.14 per million tokens.
DeepSeek V3 0324 is now served by 2 hosts, down from 3.
Mistral Small 4 (batch) is now served by 4 hosts, up from 3.
DeepSeek V4.1 Flash (batch) is now served by 30 hosts, up from 26.
Nano Banana (Gemini 2.5 Flash Image) is now served by 1 hosts, down from 4.
Nemotron 3 Ultra input price fell 17%, $0.600 to $0.500 per million tokens.
Nemotron 3 Ultra output price fell 8%, $2.40 to $2.20 per million tokens.
Hy4 preview is now served by 4 hosts, up from 2.
MiMo-V2.6-Flash is now served by 7 hosts, up from 2.
Inkling input price fell 5%, $1.00 to $0.950 per million tokens.
Inkling is now served by 2 hosts, down from 4.
gpt-oss-120b input price fell 75%, $0.150 to $0.037 per million tokens.
gpt-oss-120b output price fell 72%, $0.600 to $0.170 per million tokens.
gpt-oss-120b is now served by 23 hosts, down from 24.
GPT-6 Astra is now served by 7 hosts, up from 6.
GPT-6 Astra Pro is now served by 6 hosts, up from 5.
Kimi K3 input price fell 78%, $3.00 to $0.670 per million tokens.
Kimi K3 output price fell 7%, $15.00 to $14.00 per million tokens.
Kimi K3 is now served by 24 hosts, up from 20.
DeepSeek V3.2 Exp is now served by 1 hosts, down from 3.
GPT-6 Astra (batch) is now served by 7 hosts, up from 6.
MiniMax M1 input price rose 38%, $0.400 to $0.550 per million tokens.
Muse Glimmer 30B input price rose 17%, $0.300 to $0.350 per million tokens.
Muse Glimmer 30B output price rose 25%, $1.20 to $1.50 per million tokens.
Muse Glimmer 30B is now served by 3 hosts, down from 4.
Qwen3.5-122B-A10B is now served by 4 hosts, down from 5.
Grok 4.6 is now served by 6 hosts, up from 5.
DeepSeek V4 Pro 0423 input price fell 78%, $0.955 to $0.209 per million tokens.
DeepSeek V4 Pro 0423 output price fell 78%, $1.91 to $0.418 per million tokens.
DeepSeek Pro Latest input price fell 52%, $0.400 to $0.190 per million tokens.
DeepSeek Pro Latest output price fell 2%, $4.30 to $4.20 per million tokens.
Ling 3.0 Flash Fin input price fell 30%, $0.060 to $0.042 per million tokens.
Ling 3.0 Flash Fin output price fell 32%, $0.180 to $0.123 per million tokens.
Ling 3.0 Flash Fin is now served by 2 hosts, up from 1.
Qwen3.6 27B output price rose 20%, $2.70 to $3.25 per million tokens.
Mistral Medium 3.5 (batch) is now served by 3 hosts, up from 2.
DeepSeek V3.1 is now served by 7 hosts, down from 8.
DeepSeek V3.1 context most hosts serve moved from 131K to 163K.
GLM 5.2 input price fell 97%, $0.650 to $0.022 per million tokens.
GLM 5.2 output price rose 99%, $2.04 to $16.00 per million tokens.
GLM 5.2 is now served by 32 hosts, up from 29.
Ling 3.0 Flash VL input price fell 65%, $0.060 to $0.021 per million tokens.
Ling 3.0 Flash VL output price fell 66%, $0.180 to $0.062 per million tokens.
Ling 3.0 Flash VL is now served by 2 hosts, up from 1.
Ling 3.0 Flash VL context most hosts serve moved from 131K to 262K.
GLM 5.3 input price fell 94%, $0.840 to $0.050 per million tokens.
GLM 5.3 output price rose 99%, $2.64 to $7.00 per million tokens.
GLM 5.3 is now served by 41 hosts, up from 35.
Qwen3 Next 80B A3B Instruct input price rose 11%, $0.090 to $0.100 per million tokens.
MiniMax M2.5 is now served by 9 hosts, up from 8.
MiniMax M2.5 context most hosts serve moved from 204K to 196K.
Mistral Nemo is now served by 6 hosts, up from 4.
Kimi K2.7 Code input price fell 5%, $0.706 to $0.671 per million tokens.
Kimi K2.7 Code is now served by 13 hosts, down from 15.
GLM 5.1 input price rose 45%, $0.966 to $1.40 per million tokens.
GLM 5.1 output price rose 45%, $3.04 to $4.40 per million tokens.
GLM 5.1 is now served by 13 hosts, down from 14.
DeepSeek V4 Flash 0423 input price fell 66%, $0.089 to $0.030 per million tokens.
DeepSeek V4 Flash 0423 output price rose 99%, $0.177 to $1.28 per million tokens.
DeepSeek V4 Flash 0423 is now served by 16 hosts, up from 15.
Kimi Latest input price fell 80%, $1.50 to $0.300 per million tokens.
Kimi Latest output price rose 86%, $10.76 to $20.00 per million tokens.
GLM Latest input price fell 95%, $0.562 to $0.030 per million tokens.
GLM Latest output price rose 99%, $2.50 to $12.00 per million tokens.
GLM Latest context most hosts serve moved from 1310K to 1048K.
InferenceNet switched GLM 5.3 from fp4 to unknown.
Morph switched GLM 5.3 from unknown to fp8.
Reka switched GLM 5.3 from fp8 to unknown.
Nebius started serving GLM 5.3 at $1.40 per million.
Relace started serving GLM 5.3 at $0.030 per million.
Io Net stopped serving GLM 5.3.
Sail Research switched GLM 5.3 Flash from fp8 to fp4 — a 4-bit build at the same price.
Morph switched GLM 5.3 Flash from unknown to fp8.
Modal switched GLM 5.3 Flash from fp8 to nvfp4.
Reka switched GLM 5.3 Flash from fp8 to unknown.
Parasail switched GLM 5.3 Flash from fp8 to fp4 — a 4-bit build at the same price.
Decart started serving GLM 5.3 Flash at $0.090 per million.
DekaLLM started serving GLM 5.3 Flash at $0.100 per million.
Io Net stopped serving GLM 5.3 Flash.
Mistral started serving GLM 5.2 at $1.54 per million.
InferenceNet started serving GLM 5.2 at $0.028 per million.
Relace started serving GLM 5.2 at $0.022 per million.
Morph started serving GLM 5.2 at $0.170 per million.
Fireworks stopped serving GLM 5.2.
Relace switched DeepSeek V4.1 Flash from fp4 to unknown.
Morph switched DeepSeek V4.1 Flash from unknown to fp8.
Makora switched DeepSeek V4.1 Flash from unknown to fp8.
InferenceNet started serving DeepSeek V4.1 Flash at $0.070 per million.
Ionstream started serving DeepSeek V4.1 Flash at $0.119 per million.
Decart started serving DeepSeek V4.1 Flash at $0.090 per million.
NextBit started serving DeepSeek V4.1 Flash at $0.210 per million.
Baidu started serving DeepSeek V4.1 Flash at $0.300 per million.
Krea stopped serving DeepSeek V4.1 Flash.
OpenInference stopped serving DeepSeek V4.1 Flash.
OpenInference switched DeepSeek V4 Flash 0731 from fp8 to fp4 — a 4-bit build at the same price.
Reka switched DeepSeek V4 Flash 0731 from fp4 to unknown.
Morph switched DeepSeek V4 Flash 0731 from unknown to bf16.
Makora stopped serving DeepSeek V4 Flash 0731.
Fireworks stopped serving DeepSeek V4 Flash 0731.
Nebius stopped serving DeepSeek V4 Flash 0731.
Morph switched Kimi K3 from unknown to fp8.
DeepInfra switched Kimi K3 from bf16 to mxfp4.
Amazon Bedrock started serving Kimi K3 at $3.00 per million.
Decart started serving Kimi K3 at $1.80 per million.
AkashML started serving Kimi K3 at $3.00 per million.
DeepInfra switched gpt-oss-120b from fp8 to bf16.
Relace started serving DeepSeek V4 Pro 0813 at $0.190 per million.
BaseTen stopped serving DeepSeek V4 Pro 0813.
Fireworks stopped serving DeepSeek V4 Pro 0813.
Sail Research stopped serving DeepSeek V4 Pro 0813.
Reka switched Qwen3.8 27B from fp8 to unknown.
Cerebras started serving Qwen3.8 27B at $0.990 per million.
BaseTen stopped serving Kimi K2.6.
Fireworks stopped serving Kimi K2.6.
Sail Research stopped serving Kimi K2.6.
Relace started serving DeepSeek V4 Pro 0423 at $0.207 per million.
Reka started serving DeepSeek V4 Pro 0423 at $0.812 per million.
BaseTen stopped serving DeepSeek V4 Pro 0423.

218 pricing changes on 2026-09-23

Wed, 23 Sep 2026 09:00:00 +0000

GPT-6 Sol appeared, served by 7 host(s) at $2.20 per million input tokens.
GPT-6 Luna appeared, served by 7 host(s) at $0.110 per million input tokens.
GPT-6 Luna (batch) appeared, served by 7 host(s) at $0.050 per million input tokens.
MiMo-V2.6-Pro-UltraSpeed appeared, served by 1 host(s) at $4.35 per million input tokens.
GPT-6 Sol (batch) appeared, served by 7 host(s) at $1.00 per million input tokens.
Schematron V2 Turbo appeared, served by 1 host(s) at $0.030 per million input tokens.
Mistral Medium 3.1 (batch) appeared, served by 3 host(s) at $0.200 per million input tokens.
DeepSeek Pro Latest appeared, served by 0 host(s) at $0.400 per million input tokens.
GPT-6 Luna Pro (batch) appeared, served by 6 host(s) at $0.050 per million input tokens.
Grok 4.7 appeared, served by 4 host(s) at $2.40 per million input tokens.
Ternary Bonsai 2 27B appeared, served by 1 host(s) at $0.075 per million input tokens.
DeepSeek V4.1 Flash appeared, served by 26 host(s) at $0.280 per million input tokens.
GPT Astra Latest appeared, served by 0 host(s) at $10.00 per million input tokens.
Solar Mini 4 appeared, served by 2 host(s) at $0.050 per million input tokens.
GPT Luna Latest appeared, served by 0 host(s) at $0.100 per million input tokens.
GPT Terra Latest appeared, served by 0 host(s) at $2.00 per million input tokens.
Claude Opus 5.5 appeared, served by 11 host(s) at $4.40 per million input tokens.
Qwen3.8 Omni Flash appeared, served by 1 host(s) at $0.150 per million input tokens.
GPT-6 Sol Pro (batch) appeared, served by 6 host(s) at $1.00 per million input tokens.
Command A+ appeared, served by 1 host(s) at $0.300 per million input tokens.
Codestral 2508 (batch) appeared, served by 2 host(s) at $0.150 per million input tokens.
Mistral Small 4 (batch) appeared, served by 3 host(s) at $0.075 per million input tokens.
Mistral Large 3 2512 (batch) appeared, served by 0 host(s) at $0.250 per million input tokens.
DeepSeek Flash Latest appeared, served by 0 host(s) at $0.100 per million input tokens.
Claude Opus 5.5 (batch) appeared, served by 11 host(s) at $2.00 per million input tokens.
Nex-N2.5-Mini appeared, served by 1 host(s) at $0.025 per million input tokens.
GPT-6 Luna Pro appeared, served by 6 host(s) at $0.105 per million input tokens.
DeepSeek V4.1 Flash (batch) appeared, served by 26 host(s) at $0.112 per million input tokens.
Schematron V2 Small appeared, served by 1 host(s) at $0.050 per million input tokens.
Ministral 3 8B 2512 (batch) appeared, served by 3 host(s) at $0.075 per million input tokens.
Ling 3.0 Flash VL appeared, served by 1 host(s) at $0.060 per million input tokens.
Fugu Ultra v2 appeared, served by 1 host(s) at $5.00 per million input tokens.
MiMo-V2.6-Flash appeared, served by 2 host(s) at $0.140 per million input tokens.
Nex-N2.5-Pro appeared, served by 1 host(s) at $0.075 per million input tokens.
GPT-6 Sol Pro appeared, served by 6 host(s) at $2.10 per million input tokens.
MiMo-V2.6-Pro appeared, served by 2 host(s) at $0.435 per million input tokens.
Fugu Max appeared, served by 1 host(s) at $2.00 per million input tokens.
GPT Sol Latest appeared, served by 0 host(s) at $2.00 per million input tokens.
GLM 5.3 FlashX appeared, served by 1 host(s) at $0.370 per million input tokens.
Pareto appeared, served by 1 host(s) at $2.50 per million input tokens.
OpenAI GPT Latest is no longer offered by any host we track.
Inkling (batch) is no longer offered by any host we track.
Qwen3.8 2.4T A95B (batch) is no longer offered by any host we track.
KAT-Coder-Pro V2 is no longer offered by any host we track.
Hermes 4 70B is no longer offered by any host we track.
Gemma 4 31B (batch) is no longer offered by any host we track.
Inkling Small (batch) is no longer offered by any host we track.
Gemini 2.5 Pro Preview 05-06 is no longer offered by any host we track.
GPT-4 Turbo Preview is no longer offered by any host we track.
Qwen3.5-9B (batch) is no longer offered by any host we track.
Claude Opus 4 is no longer offered by any host we track.
DeepSeek V4 Pro 0813 (batch) is no longer offered by any host we track.
MiniMax M3 (batch) is no longer offered by any host we track.
GLM 5.2 (batch) is no longer offered by any host we track.
DeepSeek V4 Flash Vision Exp (batch) is no longer offered by any host we track.
Muse Glimmer 30B (batch) is no longer offered by any host we track.
DeepSeek V4 Flash 0731 (batch) is no longer offered by any host we track.
GLM 5.3 Flash input price rose 99%, $0.075 to $0.150 per million tokens.
GLM 5.3 Flash output price rose 99%, $0.250 to $0.500 per million tokens.
GLM 5.3 Flash is now served by 31 hosts, up from 25.
GLM 5.3 Flash (batch) input price fell 20%, $0.075 to $0.060 per million tokens.
GLM 5.3 Flash (batch) output price fell 20%, $0.250 to $0.200 per million tokens.
GLM 5.3 Flash (batch) is now served by 31 hosts, up from 25.
MiniMax M3 is now served by 13 hosts, up from 12.
Gemma 4 26B A4B input price rose 29%, $0.070 to $0.090 per million tokens.
Gemma 4 26B A4B output price fell 12%, $0.340 to $0.300 per million tokens.
Gemma 4 26B A4B is now served by 12 hosts, up from 9.
Qwen3 VL 30B A3B Instruct input price fell 13%, $0.150 to $0.130 per million tokens.
Qwen3 VL 30B A3B Instruct output price fell 13%, $0.600 to $0.520 per million tokens.
Inkling Small is now served by 2 hosts, down from 3.
Gemini 3.6 Flash (batch) lost best value; something cheaper now matches its score.
Solar Pro 4 input price rose 99%, $0.030 to $0.090 per million tokens.
Solar Pro 4 output price rose 99%, $0.120 to $0.360 per million tokens.
Solar Pro 4 lost best value; something cheaper now matches its score.
Claude Opus 4.1 is now served by 1 hosts, down from 2.
Qwen3 235B A22B Instruct 2507 input price fell 60%, $0.220 to $0.087 per million tokens.
Qwen3 235B A22B Instruct 2507 output price fell 60%, $0.880 to $0.350 per million tokens.
Qwen3 235B A22B Instruct 2507 is now served by 10 hosts, down from 11.
MiniMax M2.7 is now served by 9 hosts, down from 10.
Kimi K2.5 is now served by 5 hosts, down from 6.
DeepSeek V4 Flash Vision Exp is now served by 5 hosts, down from 6.
GLM 4.7 Flash is now served by 3 hosts, down from 4.
MiMo-V2.5 is now served by 6 hosts, up from 5.
MiMo-V2.5 lost best value; something cheaper now matches its score.
Qwen3 14B input price fell 47%, $0.227 to $0.120 per million tokens.
Qwen3 14B output price fell 74%, $0.910 to $0.240 per million tokens.
Kimi K2.6 is now served by 22 hosts, up from 21.
Mistral Small 3.2 24B input price rose 25%, $0.075 to $0.094 per million tokens.
Mistral Small 3.2 24B output price rose 25%, $0.200 to $0.250 per million tokens.
Mistral Small 3.2 24B is now served by 3 hosts, up from 2.
Kimi K3 (batch) input price fell 24%, $3.00 to $2.28 per million tokens.
Kimi K3 (batch) output price fell 24%, $15.00 to $11.40 per million tokens.
Kimi K3 (batch) is now served by 20 hosts, up from 19.
Mistral Small 4 is now served by 3 hosts, down from 4.
DeepSeek V4 Pro 0813 input price fell 14%, $0.579 to $0.499 per million tokens.
DeepSeek V4 Pro 0813 output price fell 14%, $1.74 to $1.50 per million tokens.
DeepSeek V4 Pro 0813 is now served by 24 hosts, up from 20.
Grok Latest input price fell 20%, $2.00 to $1.60 per million tokens.
Grok Latest output price fell 20%, $6.00 to $4.80 per million tokens.
Nemotron 3 Super input price fell 6%, $0.085 to $0.080 per million tokens.
Nemotron 3 Super output price rose 12%, $0.400 to $0.450 per million tokens.
Nemotron 3 Super is now served by 2 hosts, up from 1.
Claude Opus 5 (batch) is now served by 11 hosts, up from 10.
Llama 3.3 70B Instruct is now served by 11 hosts, down from 13.
DeepSeek V4 Flash Latest input price fell 24%, $0.050 to $0.038 per million tokens.
DeepSeek V4 Flash Latest output price rose 99%, $0.160 to $0.550 per million tokens.
DeepSeek V4 Flash 0731 input price fell 38%, $0.065 to $0.040 per million tokens.
DeepSeek V4 Flash 0731 output price rose 99%, $0.180 to $0.640 per million tokens.
DeepSeek V4 Flash 0731 is now served by 30 hosts, up from 29.
Qwen3.8 27B is now served by 16 hosts, up from 13.
Nemotron 3.5 Lightning is now served by 4 hosts, up from 2.
Claude Sonnet 5 (batch) is now served by 10 hosts, up from 9.
GLM 5 is now served by 8 hosts, down from 9.
gpt-oss-20b (batch) input price fell 52%, $0.050 to $0.024 per million tokens.
gpt-oss-20b (batch) output price fell 44%, $0.200 to $0.112 per million tokens.
gpt-oss-20b (batch) is now served by 12 hosts, down from 13.
gpt-oss-20b (batch) became best value — nothing cheaper now matches it.
GLM 5.3 (batch) input price rose 3%, $0.700 to $0.720 per million tokens.
GLM 5.3 (batch) output price rose 9%, $2.20 to $2.40 per million tokens.
GLM 5.3 (batch) is now served by 35 hosts, up from 28.
Llama 4 Maverick input price fell 6%, $0.200 to $0.188 per million tokens.
Llama 4 Maverick output price fell 6%, $0.696 to $0.652 per million tokens.
Mistral Medium 3.5 is now served by 2 hosts, down from 3.
DeepSeek V3 0324 input price fell 14%, $0.290 to $0.250 per million tokens.
DeepSeek V3 0324 output price fell 12%, $1.14 to $1.00 per million tokens.
DeepSeek V3 0324 is now served by 3 hosts, down from 4.
UnslopNemo 12B is now served by 1 hosts, down from 2.
Claude Sonnet 5 is now served by 10 hosts, up from 9.
Qwen3.6 35B A3B input price rose 50%, $0.100 to $0.150 per million tokens.
Qwen3.6 35B A3B output price rose 11%, $0.900 to $1.00 per million tokens.
Qwen3.6 35B A3B is now served by 9 hosts, down from 10.
Gemini 3.7 Flash (batch) lost best value; something cheaper now matches its score.
Nemotron 3 Ultra input price fell 4%, $0.625 to $0.600 per million tokens.
Nemotron 3 Ultra output price fell 23%, $3.12 to $2.40 per million tokens.
Hy4 preview is now served by 2 hosts, up from 1.
Claude Opus 5 is now served by 11 hosts, up from 10.
gpt-oss-120b input price rose 99%, $0.037 to $0.150 per million tokens.
gpt-oss-120b output price rose 99%, $0.170 to $0.600 per million tokens.
gpt-oss-120b is now served by 24 hosts, up from 22.
gpt-oss-20b input price fell 40%, $0.030 to $0.018 per million tokens.
gpt-oss-20b output price fell 31%, $0.130 to $0.090 per million tokens.
gpt-oss-20b is now served by 12 hosts, down from 13.
GPT-6 Astra is now served by 6 hosts, up from 5.
Claude Sonnet 4 is now served by 2 hosts, down from 5.
Claude Sonnet 4 context most hosts serve moved from 1000K to 200K.
Kimi K3 is now served by 20 hosts, up from 19.
GPT-6 Astra (batch) is now served by 6 hosts, up from 5.
MiniMax M1 input price fell 27%, $0.550 to $0.400 per million tokens.
Muse Glimmer 30B output price rose 9%, $1.10 to $1.20 per million tokens.
Qwen3.5-122B-A10B input price fell 10%, $0.290 to $0.260 per million tokens.
Qwen3.5-122B-A10B output price fell 13%, $2.40 to $2.08 per million tokens.
Claude Opus Latest input price fell 20%, $5.00 to $4.00 per million tokens.
Claude Opus Latest output price fell 20%, $25.00 to $20.00 per million tokens.
Qwen3.6 27B input price rose 7%, $0.300 to $0.320 per million tokens.
Qwen3.6 27B output price rose 35%, $2.00 to $2.70 per million tokens.
Mistral Medium 3.5 (batch) is now served by 2 hosts, down from 3.
GLM 4.6 is now served by 4 hosts, down from 5.
Qwen3 30B A3B Instruct 2507 is now served by 5 hosts, up from 4.
MythoMax 13B input price rose 33%, $0.060 to $0.080 per million tokens.
MythoMax 13B output price rose 83%, $0.060 to $0.110 per million tokens.
MythoMax 13B is now served by 3 hosts, down from 4.
GLM 5.2 input price fell 33%, $0.966 to $0.650 per million tokens.
GLM 5.2 output price fell 33%, $3.04 to $2.04 per million tokens.
GLM 5.2 is now served by 29 hosts, down from 33.
GLM 5.3 input price fell 40%, $1.40 to $0.840 per million tokens.
GLM 5.3 output price fell 40%, $4.40 to $2.64 per million tokens.
GLM 5.3 is now served by 35 hosts, up from 28.
Claude Opus 4.1 (batch) is now served by 1 hosts, down from 2.
Gemma 4 31B is now served by 13 hosts, down from 15.
MiniMax M2.5 is now served by 8 hosts, down from 9.
MiniMax M2.5 context most hosts serve moved from 196K to 204K.
Gemini 3.8 Flash (batch) lost best value; something cheaper now matches its score.
Kimi K2.7 Code output price fell 6%, $3.50 to $3.30 per million tokens.
GLM 5.1 is now served by 14 hosts, down from 15.
Kimi Latest input price fell 38%, $2.40 to $1.50 per million tokens.
Kimi Latest output price fell 10%, $12.00 to $10.76 per million tokens.
GLM Latest input price fell 49%, $1.11 to $0.562 per million tokens.
GLM Latest output price fell 29%, $3.50 to $2.50 per million tokens.
Morph switched GLM 5.3 Flash from fp8 to unknown.
Relace switched GLM 5.3 Flash from fp4 to unknown.
CoreWeave switched GLM 5.3 Flash from fp8 to nvfp4.
AtlasCloud started serving GLM 5.3 Flash at $0.150 per million.
InferenceNet started serving GLM 5.3 Flash at $0.090 per million.
Near AI started serving GLM 5.3 Flash at $0.150 per million.
Reka started serving GLM 5.3 Flash at $0.150 per million.
Inceptron started serving GLM 5.3 Flash at $0.150 per million.
OpenInference started serving GLM 5.3 Flash at $0.100 per million.
Makora stopped serving GLM 5.3 Flash.
Io Net switched GLM 5.3 from fp4 to fp8.
Morph switched GLM 5.3 from fp4 to unknown.
Mistral started serving GLM 5.3 at $1.40 per million.
InferenceNet started serving GLM 5.3 at $0.900 per million.
PrimeIntellect started serving GLM 5.3 at $1.40 per million.
Alibaba started serving GLM 5.3 at $1.19 per million.
Baidu started serving GLM 5.3 at $1.40 per million.
StreamLake stopped serving GLM 5.3.
Morph switched DeepSeek V4 Flash 0731 from bf16 to unknown.
Cohere started serving DeepSeek V4 Flash 0731 at $0.140 per million.
Nebius started serving DeepSeek V4 Flash 0731 at $0.140 per million.
DeepSeek stopped serving DeepSeek V4 Flash 0731.
Wafer started serving GLM 5.2 at $1.40 per million.
Mistral stopped serving GLM 5.2.
Ambient stopped serving GLM 5.2.
Crusoe stopped serving GLM 5.2.
Ionstream switched DeepSeek V4 Pro 0813 from fp4 to unknown.
AtlasCloud started serving DeepSeek V4 Pro 0813 at $1.32 per million.
Venice started serving DeepSeek V4 Pro 0813 at $1.65 per million.
Wafer started serving DeepSeek V4 Pro 0813 at $0.500 per million.
DekaLLM started serving gpt-oss-120b at $0.030 per million.
Crusoe started serving gpt-oss-120b at $0.050 per million.
Sail Research started serving Kimi K2.6 at $1.00 per million.
Morph switched Kimi K3 from fp4 to unknown.
InferenceNet started serving Kimi K3 at $1.95 per million.
DekaLLM started serving gpt-oss-20b at $0.029 per million.
Together stopped serving gpt-oss-20b.
Phala stopped serving gpt-oss-20b.
Cloudflare started serving DeepSeek V4 Pro 0423 at $1.15 per million.
Fireworks stopped serving DeepSeek V4 Pro 0423.

82 pricing changes on 2026-09-09

Wed, 09 Sep 2026 09:00:00 +0000

GLM 5.3 (batch) appeared, served by 28 host(s) at $0.700 per million input tokens.
GLM 5.2 (batch) appeared, served by 33 host(s) at $0.700 per million input tokens.
DeepSeek V4 Flash Vision Exp (batch) appeared, served by 6 host(s) at $0.110 per million input tokens.
Mercury 2.5 appeared, served by 1 host(s) at $0.040 per million input tokens.
Nex-N2-Pro is no longer offered by any host we track.
Nex-N2-Mini is no longer offered by any host we track.
Mercury 2.5 Preview is no longer offered by any host we track.
GLM 5.3 Flash is now served by 25 hosts, up from 23.
GLM 5.3 Flash (batch) input price fell 50%, $0.150 to $0.075 per million tokens.
GLM 5.3 Flash (batch) output price fell 50%, $0.500 to $0.250 per million tokens.
GLM 5.3 Flash (batch) is now served by 25 hosts, up from 23.
MiniMax M3 context most hosts serve moved from 524K to 1048K.
Qwen3 235B A22B Instruct 2507 input price rose 99%, $0.090 to $0.220 per million tokens.
Qwen3 235B A22B Instruct 2507 output price rose 60%, $0.550 to $0.880 per million tokens.
Qwen3.5 397B A17B input price rose 41%, $0.390 to $0.550 per million tokens.
Qwen3.5 397B A17B output price rose 50%, $2.34 to $3.50 per million tokens.
Kimi K2.5 is now served by 6 hosts, down from 8.
MiMo-V2.5 became best value — nothing cheaper now matches it.
Qwen3 14B input price rose 90%, $0.120 to $0.227 per million tokens.
Qwen3 14B output price rose 99%, $0.240 to $0.910 per million tokens.
Kimi K3 (batch) is now served by 19 hosts, up from 18.
Kimi K3 (batch) lost best value; something cheaper now matches its score.
Granite 4.2 8B input price fell 40%, $0.100 to $0.060 per million tokens.
Granite 4.2 8B output price rose 67%, $0.150 to $0.250 per million tokens.
DeepSeek V4 Pro 0813 is now served by 20 hosts, up from 19.
Nemotron 3 Super is now served by 1 hosts, down from 2.
Hy3 input price rose 60%, $0.083 to $0.132 per million tokens.
Hy3 output price rose 60%, $0.330 to $0.528 per million tokens.
DeepSeek V4 Flash Latest input price rose 11%, $0.045 to $0.050 per million tokens.
DeepSeek V4 Flash Latest output price rose 78%, $0.090 to $0.160 per million tokens.
DeepSeek V4 Flash 0731 input price rose 30%, $0.050 to $0.065 per million tokens.
DeepSeek V4 Flash 0731 output price rose 80%, $0.100 to $0.180 per million tokens.
DeepSeek V4 Flash 0731 lost best value; something cheaper now matches its score.
GLM 5 is now served by 9 hosts, down from 10.
gpt-oss-20b (batch) is now served by 13 hosts, down from 14.
DeepSeek V3 0324 input price rose 16%, $0.250 to $0.290 per million tokens.
DeepSeek V3 0324 output price rose 14%, $1.00 to $1.14 per million tokens.
gpt-oss-20b is now served by 13 hosts, down from 14.
DeepSeek V4 Pro 0813 (batch) input price fell 50%, $1.32 to $0.660 per million tokens.
DeepSeek V4 Pro 0813 (batch) output price fell 50%, $3.96 to $1.98 per million tokens.
DeepSeek V4 Pro 0813 (batch) is now served by 20 hosts, up from 19.
MiniMax M3 (batch) context most hosts serve moved from 524K to 1048K.
Kimi K3 is now served by 19 hosts, up from 18.
Kimi K3 lost best value; something cheaper now matches its score.
Qwen3.5-9B is now served by 6 hosts, up from 5.
DeepSeek V4 Pro 0423 input price rose 50%, $0.637 to $0.955 per million tokens.
DeepSeek V4 Pro 0423 output price rose 50%, $1.27 to $1.91 per million tokens.
DeepSeek V4 Pro 0423 is now served by 16 hosts, down from 17.
GLM 4.6 input price fell 22%, $0.550 to $0.430 per million tokens.
GLM 4.6 output price fell 20%, $2.20 to $1.75 per million tokens.
Qwen3.5-9B (batch) is now served by 6 hosts, up from 5.
DeepSeek V4 Flash 0731 (batch) input price fell 21%, $0.140 to $0.110 per million tokens.
DeepSeek V4 Flash 0731 (batch) output price rose 18%, $0.280 to $0.330 per million tokens.
DeepSeek V4 Flash 0731 (batch) became best value — nothing cheaper now matches it.
DeepSeek V3.1 input price fell 55%, $0.550 to $0.250 per million tokens.
DeepSeek V3.1 output price fell 42%, $1.65 to $0.950 per million tokens.
GLM 5.3 is now served by 28 hosts, up from 27.
Qwen3 Next 80B A3B Instruct input price fell 10%, $0.100 to $0.090 per million tokens.
Kimi K2.7 Code input price rose 8%, $0.660 to $0.710 per million tokens.
Kimi K2.7 Code output price rose 3%, $3.40 to $3.50 per million tokens.
Kimi K2.7 Code is now served by 15 hosts, down from 16.
GLM 5.1 is now served by 15 hosts, down from 16.
DeepSeek V4 Flash 0423 input price rose 11%, $0.080 to $0.089 per million tokens.
DeepSeek V4 Flash 0423 output price rose 11%, $0.159 to $0.177 per million tokens.
MoonshotAI Kimi Latest input price fell 6%, $2.55 to $2.40 per million tokens.
MoonshotAI Kimi Latest output price fell 6%, $12.75 to $12.00 per million tokens.
GLM Latest input price fell 5%, $1.17 to $1.11 per million tokens.
GLM Latest output price fell 12%, $3.96 to $3.50 per million tokens.
Muse Glimmer 30B (batch) input price fell 50%, $0.350 to $0.175 per million tokens.
Muse Glimmer 30B (batch) output price fell 50%, $1.50 to $0.750 per million tokens.
Io Net switched GLM 5.3 from fp8 to fp4 — a 4-bit build at the same price.
Crusoe switched GLM 5.3 from fp8 to fp4 — a 4-bit build at the same price.
StreamLake started serving GLM 5.3 at $1.11 per million.
Baidu switched GLM 5.2 from fp8 to fp4 — a 4-bit build at the same price.
StreamLake switched GLM 5.3 Flash from unknown to fp8.
Crusoe started serving GLM 5.3 Flash at $0.150 per million.
Relace started serving GLM 5.3 Flash at $0.090 per million.
Phala started serving GLM 5.3 Flash at $0.150 per million.
Reka stopped serving GLM 5.3 Flash.
Ionstream started serving DeepSeek V4 Pro 0813 at $1.10 per million.
Relace started serving Kimi K3 at $2.40 per million.
Ionstream stopped serving DeepSeek V4 Pro 0423.

11 pricing changes on 2026-09-07

Mon, 07 Sep 2026 09:00:00 +0000

Qwen3.5 397B A17B input price fell 29%, $0.550 to $0.390 per million tokens.
Qwen3.5 397B A17B output price fell 33%, $3.50 to $2.34 per million tokens.
DeepSeek V4 Pro 0813 input price fell 48%, $1.12 to $0.579 per million tokens.
DeepSeek V4 Pro 0813 output price fell 48%, $3.36 to $1.74 per million tokens.
Hy3 input price fell 37%, $0.132 to $0.083 per million tokens.
Hy3 output price fell 37%, $0.528 to $0.330 per million tokens.
DeepSeek V4 Pro 0423 input price fell 9%, $0.698 to $0.637 per million tokens.
DeepSeek V4 Pro 0423 output price fell 9%, $1.40 to $1.27 per million tokens.
GLM 5.2 is now served by 33 hosts, up from 32.
GLM 5.3 is now served by 27 hosts, up from 26.
Crusoe started serving GLM 5.3 at $1.40 per million.

25 pricing changes on 2026-09-06

Sun, 06 Sep 2026 09:00:00 +0000

GPT-6 Astra Pro (batch) appeared, served by 5 host(s) at $5.00 per million input tokens.
GPT-6 Astra appeared, served by 5 host(s) at $10.00 per million input tokens.
Qwen3.8 Max (0902) appeared, served by 1 host(s) at $2.00 per million input tokens.
GPT-6 Astra (batch) appeared, served by 5 host(s) at $5.00 per million input tokens.
GPT-6 Astra Pro appeared, served by 5 host(s) at $10.00 per million input tokens.
Granite 4.1 8B is no longer offered by any host we track.
Qwen3.8 Max is no longer offered by any host we track.
Qwen3 235B A22B Instruct 2507 input price rose 3%, $0.087 to $0.090 per million tokens.
Qwen3 235B A22B Instruct 2507 output price rose 57%, $0.350 to $0.550 per million tokens.
DeepSeek V4 Flash Vision Exp input price fell 50%, $0.440 to $0.220 per million tokens.
DeepSeek V4 Flash Vision Exp output price fell 50%, $1.32 to $0.660 per million tokens.
Qwen3.5-35B-A3B input price rose 25%, $0.250 to $0.312 per million tokens.
DeepSeek V4 Flash Latest input price fell 10%, $0.050 to $0.045 per million tokens.
DeepSeek V4 Flash Latest output price fell 44%, $0.160 to $0.090 per million tokens.
DeepSeek V4 Flash 0731 input price fell 23%, $0.065 to $0.050 per million tokens.
DeepSeek V4 Flash 0731 output price fell 44%, $0.180 to $0.100 per million tokens.
DeepSeek V4 Pro 0423 input price fell 33%, $1.04 to $0.698 per million tokens.
DeepSeek V4 Pro 0423 output price fell 33%, $2.08 to $1.40 per million tokens.
Qwen3.6 27B input price fell 50%, $0.600 to $0.300 per million tokens.
Qwen3.6 27B output price fell 44%, $3.60 to $2.00 per million tokens.
DeepSeek V4 Flash 0423 input price fell 9%, $0.089 to $0.081 per million tokens.
DeepSeek V4 Flash 0423 output price fell 9%, $0.177 to $0.162 per million tokens.
MoonshotAI Kimi Latest input price rose 2%, $2.50 to $2.55 per million tokens.
MoonshotAI Kimi Latest output price fell 9%, $14.00 to $12.75 per million tokens.
GLM Latest output price rose 13%, $3.50 to $3.96 per million tokens.

Claude Haiku 5.5 released

Wed, 07 Oct 2026 09:00:00 +0000

Intelligence 1303, $0.215 per 1,000 tasks, 10 hosts. Launched already beaten on price by an equally capable model.

Mistral Large 4 released

Tue, 06 Oct 2026 09:00:00 +0000

Intelligence 1249, $1.004 per 1,000 tasks, 3 hosts. Launched already beaten on price by an equally capable model.

GPT-6.1 Sol released

Tue, 29 Sep 2026 09:00:00 +0000

Intelligence 1372, $4.428 per 1,000 tasks, 8 hosts. Launched already beaten on price by an equally capable model.

Claude Sonnet 5.5 released

Mon, 28 Sep 2026 09:00:00 +0000

Intelligence 1382, $4.032 per 1,000 tasks, 8 hosts. Launched already beaten on price by an equally capable model.

Solar Mini 4 released

Wed, 23 Sep 2026 09:00:00 +0000

Intelligence 1158, $0.088 per 1,000 tasks, 2 hosts. Arrived cheaper than anything matching its score.

Claude Opus 5.5 released

Tue, 22 Sep 2026 09:00:00 +0000

Intelligence 1401, $8.856 per 1,000 tasks, 11 hosts. Launched already beaten on price by an equally capable model.

MiMo-V2.6-Pro released

Mon, 21 Sep 2026 09:00:00 +0000

Intelligence 1328, $0.472 per 1,000 tasks, 4 hosts. Arrived cheaper than anything matching its score.

Grok 4.7 released

Mon, 21 Sep 2026 09:00:00 +0000

Intelligence 1272, $3.396 per 1,000 tasks, 5 hosts. Launched already beaten on price by an equally capable model.

Muse Spark 1.3 released

Wed, 02 Sep 2026 09:00:00 +0000

Intelligence 1344, $1.983 per 1,000 tasks, 1 hosts. Launched already beaten on price by an equally capable model.

Gemini 3.8 Flash released

Wed, 02 Sep 2026 09:00:00 +0000

Intelligence 1296, $1.539 per 1,000 tasks, 6 hosts. Launched already beaten on price by an equally capable model.

Claude Fable 5.1 released

Tue, 01 Sep 2026 09:00:00 +0000

Intelligence 1344, $19.980 per 1,000 tasks, 4 hosts. Launched already beaten on price by an equally capable model.

GLM 5.3 Flash released

Wed, 26 Aug 2026 09:00:00 +0000

Intelligence 1289, $0.230 per 1,000 tasks, 32 hosts. Launched already beaten on price by an equally capable model.

GLM 5.3 released

Tue, 18 Aug 2026 09:00:00 +0000

Intelligence 1295, $1.934 per 1,000 tasks, 41 hosts. Launched already beaten on price by an equally capable model.

Gemini 3.7 Flash released

Thu, 13 Aug 2026 09:00:00 +0000

Intelligence 1305, $1.539 per 1,000 tasks, 6 hosts. Launched already beaten on price by an equally capable model.

Grok 4.6 released

Wed, 12 Aug 2026 09:00:00 +0000

Intelligence 1284, $3.396 per 1,000 tasks, 6 hosts. Launched already beaten on price by an equally capable model.

Solar Pro 4 released

Mon, 10 Aug 2026 09:00:00 +0000

Intelligence 1177, $0.164 per 1,000 tasks, 2 hosts. Launched already beaten on price by an equally capable model.

Muse Spark 1.2 released

Wed, 05 Aug 2026 09:00:00 +0000

Intelligence 1310, $1.983 per 1,000 tasks, 1 hosts. Launched already beaten on price by an equally capable model.

DeepSeek V4 Flash 0731 released

Fri, 31 Jul 2026 09:00:00 +0000

Intelligence 1200, $0.233 per 1,000 tasks, 27 hosts. Launched already beaten on price by an equally capable model.

Claude Opus 5 released

Fri, 24 Jul 2026 09:00:00 +0000

Intelligence 1333, $11.250 per 1,000 tasks, 11 hosts. Launched already beaten on price by an equally capable model.

Gemini 3.6 Flash released

Tue, 21 Jul 2026 09:00:00 +0000

Intelligence 1287, $1.539 per 1,000 tasks, 7 hosts. Launched already beaten on price by an equally capable model.